Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

ViPE: Video Pose Engine for 3D Geometric Perception Contributions: • A robust and efficient framework, ViPE, for estimating camera parameters and dense depth from diverse, in-the-wild videos. • A system design that integrates the strengths of classical SLAM (efficiency, scalability) and learned models (robustness), with key improvements in efficiency,...

janusch_patas's profile picture

MrNeRF

16,805 subscribers

42,553 görüntüleme • 11 ay önce •via X (Twitter)

Bilim & TeknolojiEğitim
LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

NVIDIA AI Open-Sources ViPE (Video Pose Engine): A Powerful and Versatile 3D Video Annotation Tool for Spatial AI ViPE integrates bundle adjustment with dense optical flow, sparse keypoint tracking, and metric depth priors to estimate camera intrinsics, poses, and dense depth maps at 3–5 FPS on a single GPU. It significantly improves over prior uncalibrated pose estimation methods, achieving 18% and 50% error reduction on TUM and KITTI benchmarks, respectively, and shows robustness to dynamic scenes and diverse camera models. Beyond the method, the NVIDIA team also released a large-scale dataset comprising ~100K real-world internet videos, 1M AI-generated videos, and 2K panoramic videos (≈96M frames) annotated with metric depth and poses. This dataset and engine aim to accelerate training for spatial AI tasks such as 3D reconstruction, video generation, and robotics.... full analysis: paper: codes: NVIDIA NVIDIA AI NVIDIAnewsroom NVIDIA Robotics NVIDIA AIDev NVIDIAdeveloper
1:13

NVIDIA AI Open-Sources ViPE (Video Pose Engine): A Powerful and Versatile 3D Video Annotation Tool for Spatial AI ViPE integrates bundle adjustment with dense optical flow, sparse keypoint tracking, and metric depth priors to estimate camera intrinsics, poses, and dense depth maps at 3–5 FPS on a single GPU. It significantly improves over prior uncalibrated pose estimation methods, achieving 18% and 50% error reduction on TUM and KITTI benchmarks, respectively, and shows robustness to dynamic scenes and diverse camera models. Beyond the method, the NVIDIA team also released a large-scale dataset comprising ~100K real-world internet videos, 1M AI-generated videos, and 2K panoramic videos (≈96M frames) annotated with metric depth and poses. This dataset and engine aim to accelerate training for spatial AI tasks such as 3D reconstruction, video generation, and robotics.... full analysis: paper: codes: NVIDIA NVIDIA AI NVIDIAnewsroom NVIDIA Robotics NVIDIA AIDev NVIDIAdeveloper

Marktechpost AI Dev News ⚡

217,453 görüntüleme • 10 ay önce

This seemingly obvious prediction didn't take long to become reality. MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors Contributions: • The first real-time SLAM system using the two-view 3D reconstruction prior MASt3R [20] as a foundation. • Efficient techniques for pointmap matching, tracking and local fusion, graph construction and loop closure, and second-order global optimization. • A state-of-the-art dense SLAM system capable of handling generic, time-varying camera models. Abstract: We present a real-time monocular dense SLAM system, designed from the ground up using MASt3R, a two-view 3D reconstruction and matching prior. Equipped with this strong prior, our system remains robust on in-the-wild video sequences, making no assumptions on a fixed or parametric camera model beyond a unique camera center. Key features include: - Efficient methods for pointmap matching, camera tracking, and local fusion - Graph construction and loop closure - Second-order global optimization With known calibration, a simple modification achieves state-of-the-art performance across various benchmarks. Altogether, we propose a plug-and-play monocular SLAM system capable of producing globally-consistent poses and dense geometry while operating at 15 FPS.
0:23

This seemingly obvious prediction didn't take long to become reality. MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors Contributions: • The first real-time SLAM system using the two-view 3D reconstruction prior MASt3R [20] as a foundation. • Efficient techniques for pointmap matching, tracking and local fusion, graph construction and loop closure, and second-order global optimization. • A state-of-the-art dense SLAM system capable of handling generic, time-varying camera models. Abstract: We present a real-time monocular dense SLAM system, designed from the ground up using MASt3R, a two-view 3D reconstruction and matching prior. Equipped with this strong prior, our system remains robust on in-the-wild video sequences, making no assumptions on a fixed or parametric camera model beyond a unique camera center. Key features include: - Efficient methods for pointmap matching, camera tracking, and local fusion - Graph construction and loop closure - Second-order global optimization With known calibration, a simple modification achieves state-of-the-art performance across various benchmarks. Altogether, we propose a plug-and-play monocular SLAM system capable of producing globally-consistent poses and dense geometry while operating at 15 FPS.

MrNeRF

29,961 görüntüleme • 1 yıl önce

The team at NVIDIA AI Developer really nailed it with ViPE!! This SLAM system generated pose, depth, point clouds, etc, in a few seconds! Now to get the output to work with GEN3C... If you are interested in running this yourself, it took about 5 minutes to get up and running from scratch.
0:28

The team at NVIDIA AI Developer really nailed it with ViPE!! This SLAM system generated pose, depth, point clouds, etc, in a few seconds! Now to get the output to work with GEN3C... If you are interested in running this yourself, it took about 5 minutes to get up and running from scratch.

Jonathan Stephens

34,947 görüntüleme • 11 ay önce

🚀 Meta FAIR is releasing several new research artifacts on our road to advanced machine intelligence (AMI). These latest advancements are transforming our understanding of perception. 1️⃣ Meta Perception Encoder: A large-scale vision encoder that excels across several image & video tasks. 2️⃣ Meta Perception Language Model: A fully open & reproducible vision-language model designed to tackle visual recognition tasks. 3️⃣ Meta Locate 3D: An end-to-end model for accurate object localization in 3D environments. 4️⃣ Releasing model weights for our 8B-parameter Dynamic Byte Latent Transformer, an alternative to traditional tokenization methods with the potential to redefine the standards for language model efficiency and reliability. 5️⃣Collaborative Reasoner: A framework for evaluating & improving collaborative reasoning skills in language models. Download the code, datasets, and research papers and learn more about how these artifacts are paving the way for more efficient and accurate AI systems.➡️
2:10

🚀 Meta FAIR is releasing several new research artifacts on our road to advanced machine intelligence (AMI). These latest advancements are transforming our understanding of perception. 1️⃣ Meta Perception Encoder: A large-scale vision encoder that excels across several image & video tasks. 2️⃣ Meta Perception Language Model: A fully open & reproducible vision-language model designed to tackle visual recognition tasks. 3️⃣ Meta Locate 3D: An end-to-end model for accurate object localization in 3D environments. 4️⃣ Releasing model weights for our 8B-parameter Dynamic Byte Latent Transformer, an alternative to traditional tokenization methods with the potential to redefine the standards for language model efficiency and reliability. 5️⃣Collaborative Reasoner: A framework for evaluating & improving collaborative reasoning skills in language models. Download the code, datasets, and research papers and learn more about how these artifacts are paving the way for more efficient and accurate AI systems.➡️

AI at Meta

163,313 görüntüleme • 1 yıl önce

Progressively Optimized Local Radiance Fields for Robust View Synthesis paper page: present an algorithm for reconstructing the radiance field of a large-scale scene from a single casually captured video. The task poses two core challenges. First, most existing radiance field reconstruction approaches rely on accurate pre-estimated camera poses from Structure-from-Motion algorithms, which frequently fail on in-the-wild videos. Second, using a single, global radiance field with finite representational capacity does not scale to longer trajectories in an unbounded scene. For handling unknown poses, we jointly estimate the camera poses with radiance field in a progressive manner. We show that progressive optimization significantly improves the robustness of the reconstruction. For handling large unbounded scenes, we dynamically allocate new local radiance fields trained with frames within a temporal window. This further improves robustness (e.g., performs well even under moderate pose drifts) and allows us to scale to large scenes. Our extensive evaluation on the Tanks and Temples dataset and our collected outdoor dataset, Static Hikes, show that our approach compares favorably with the state-of-the-art.
4:28

Progressively Optimized Local Radiance Fields for Robust View Synthesis paper page: present an algorithm for reconstructing the radiance field of a large-scale scene from a single casually captured video. The task poses two core challenges. First, most existing radiance field reconstruction approaches rely on accurate pre-estimated camera poses from Structure-from-Motion algorithms, which frequently fail on in-the-wild videos. Second, using a single, global radiance field with finite representational capacity does not scale to longer trajectories in an unbounded scene. For handling unknown poses, we jointly estimate the camera poses with radiance field in a progressive manner. We show that progressive optimization significantly improves the robustness of the reconstruction. For handling large unbounded scenes, we dynamically allocate new local radiance fields trained with frames within a temporal window. This further improves robustness (e.g., performs well even under moderate pose drifts) and allows us to scale to large scenes. Our extensive evaluation on the Tanks and Temples dataset and our collected outdoor dataset, Static Hikes, show that our approach compares favorably with the state-of-the-art.

AK

140,624 görüntüleme • 3 yıl önce

We have seen a lot of legged robots doing navigation in the wild. But how about mobile manipulation in the wild? I have been pushing the direction of learning a unified, efficient, and dynamic 3D representation of scenes (for navigation) and objects (for manipulation) for the past two years. And now we have GeFF --- our large-scale, generalizable feature field, that combines the speed of a feed-forward neural network with the rich semantics from Foundation Models, to handle dynamically changing scenes, and enable open-ended, language-grounded scene and object understanding.
1:45

We have seen a lot of legged robots doing navigation in the wild. But how about mobile manipulation in the wild? I have been pushing the direction of learning a unified, efficient, and dynamic 3D representation of scenes (for navigation) and objects (for manipulation) for the past two years. And now we have GeFF --- our large-scale, generalizable feature field, that combines the speed of a feed-forward neural network with the rich semantics from Foundation Models, to handle dynamically changing scenes, and enable open-ended, language-grounded scene and object understanding.

Xiaolong Wang

42,767 görüntüleme • 2 yıl önce

Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors paper page: present Magic123, a two-stage coarse-to-fine approach for high-quality, textured 3D meshes generation from a single unposed image in the wild using both2D and 3D priors. In the first stage, we optimize a neural radiance field to produce a coarse geometry. In the second stage, we adopt a memory-efficient differentiable mesh representation to yield a high-resolution mesh with a visually appealing texture. In both stages, the 3D content is learned through reference view supervision and novel views guided by a combination of 2D and 3D diffusion priors. We introduce a single trade-off parameter between the 2D and 3D priors to control exploration (more imaginative) and exploitation (more precise) of the generated geometry. Additionally, we employ textual inversion and monocular depth regularization to encourage consistent appearances across views and to prevent degenerate solutions, respectively. Magic123 demonstrates a significant improvement over previous image-to-3D techniques, as validated through extensive experiments on synthetic benchmarks and diverse real-world images.
0:34

Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors paper page: present Magic123, a two-stage coarse-to-fine approach for high-quality, textured 3D meshes generation from a single unposed image in the wild using both2D and 3D priors. In the first stage, we optimize a neural radiance field to produce a coarse geometry. In the second stage, we adopt a memory-efficient differentiable mesh representation to yield a high-resolution mesh with a visually appealing texture. In both stages, the 3D content is learned through reference view supervision and novel views guided by a combination of 2D and 3D diffusion priors. We introduce a single trade-off parameter between the 2D and 3D priors to control exploration (more imaginative) and exploitation (more precise) of the generated geometry. Additionally, we employ textual inversion and monocular depth regularization to encourage consistent appearances across views and to prevent degenerate solutions, respectively. Magic123 demonstrates a significant improvement over previous image-to-3D techniques, as validated through extensive experiments on synthetic benchmarks and diverse real-world images.

AK

305,663 görüntüleme • 3 yıl önce

Meta presents Sapiens Foundation for Human Vision Models discuss: We present Sapiens, a family of models for four fundamental human-centric vision tasks - 2D pose estimation, body-part segmentation, depth estimation, and surface normal prediction. Our models natively support 1K high-resolution inference and are extremely easy to adapt for individual tasks by simply fine-tuning models pretrained on over 300 million in-the-wild human images. We observe that, given the same computational budget, self-supervised pretraining on a curated dataset of human images significantly boosts the performance for a diverse set of human-centric tasks. The resulting models exhibit remarkable generalization to in-the-wild data, even when labeled data is scarce or entirely synthetic. Our simple model design also brings scalability - model performance across tasks improves as we scale the number of parameters from 0.3 to 2 billion. Sapiens consistently surpasses existing baselines across various human-centric benchmarks. We achieve significant improvements over the prior state-of-the-art on Humans-5K (pose) by 7.6 mAP, Humans-2K (part-seg) by 17.1 mIoU, Hi4D (depth) by 22.4% relative RMSE, and THuman2 (normal) by 53.5% relative angular error.
2:00

Meta presents Sapiens Foundation for Human Vision Models discuss: We present Sapiens, a family of models for four fundamental human-centric vision tasks - 2D pose estimation, body-part segmentation, depth estimation, and surface normal prediction. Our models natively support 1K high-resolution inference and are extremely easy to adapt for individual tasks by simply fine-tuning models pretrained on over 300 million in-the-wild human images. We observe that, given the same computational budget, self-supervised pretraining on a curated dataset of human images significantly boosts the performance for a diverse set of human-centric tasks. The resulting models exhibit remarkable generalization to in-the-wild data, even when labeled data is scarce or entirely synthetic. Our simple model design also brings scalability - model performance across tasks improves as we scale the number of parameters from 0.3 to 2 billion. Sapiens consistently surpasses existing baselines across various human-centric benchmarks. We achieve significant improvements over the prior state-of-the-art on Humans-5K (pose) by 7.6 mAP, Humans-2K (part-seg) by 17.1 mIoU, Hi4D (depth) by 22.4% relative RMSE, and THuman2 (normal) by 53.5% relative angular error.

AK

151,582 görüntüleme • 1 yıl önce

GauS-SLAM: Dense RGB-D SLAM with Gaussian Surfels • We propose a 2D Gaussian-based incremental reconstruction strategy and a Surface-aware Depth Rendering mechanism. This approach effectively mitigates geometry distortions and improves tracking accuracy. • Our dense SLAM system features a front-end/back-end architecture and incorporates a local map design, ensuring tracking accuracy and efficiency. • We conduct extensive experiments demonstrating the superiority of our approach in both tracking accuracy and reconstruction quality compared to SOTA methods.
0:24

GauS-SLAM: Dense RGB-D SLAM with Gaussian Surfels • We propose a 2D Gaussian-based incremental reconstruction strategy and a Surface-aware Depth Rendering mechanism. This approach effectively mitigates geometry distortions and improves tracking accuracy. • Our dense SLAM system features a front-end/back-end architecture and incorporates a local map design, ensuring tracking accuracy and efficiency. • We conduct extensive experiments demonstrating the superiority of our approach in both tracking accuracy and reconstruction quality compared to SOTA methods.

MrNeRF

11,004 görüntüleme • 1 yıl önce

Painting with 3D Gaussian Splat Brushes Contributions: • Designing a set of interactive tools and brush parameters for artistic brush creation and control using 3DGS content. • Computing oriented 3D Gaussian splat brushes for stamp-based painting on 3D surfaces represented as meshes or 3DGS scenes. • Deforming the splats in a brush stamp to ensure a smooth appearance of the painted 3D stroke. • Producing seamless brush strokes despite overlapping brush stamps, using diffusion inpainting. • Efficient modeling and rendering of brush strokes to facilitate 3DGS painting in real time.
0:27

Painting with 3D Gaussian Splat Brushes Contributions: • Designing a set of interactive tools and brush parameters for artistic brush creation and control using 3DGS content. • Computing oriented 3D Gaussian splat brushes for stamp-based painting on 3D surfaces represented as meshes or 3DGS scenes. • Deforming the splats in a brush stamp to ensure a smooth appearance of the painted 3D stroke. • Producing seamless brush strokes despite overlapping brush stamps, using diffusion inpainting. • Efficient modeling and rendering of brush strokes to facilitate 3DGS painting in real time.

MrNeRF

22,958 görüntüleme • 1 yıl önce

Extract accurate depth from your 3D gaussians! Fast, accurate, and easy to use. Code of RaDe-GS is released! project page: code: paper: No need to change your 3D GS representations, we propose a play-and-plug rasterizer to extract accurate depth and normal from 3D gaussians, leading to the possibility of high-quality geometry reconstruction. It's quite efficient and fast, achieving 0.69mm errors on DTU dataset in only 5 minutes. Very easy to adopt the rasterizer in your any 3dgs projects.
0:24

Extract accurate depth from your 3D gaussians! Fast, accurate, and easy to use. Code of RaDe-GS is released! project page: code: paper: No need to change your 3D GS representations, we propose a play-and-plug rasterizer to extract accurate depth and normal from 3D gaussians, leading to the possibility of high-quality geometry reconstruction. It's quite efficient and fast, achieving 0.69mm errors on DTU dataset in only 5 minutes. Very easy to adopt the rasterizer in your any 3dgs projects.

Xiao-Xiao Long

31,290 görüntüleme • 2 yıl önce

Alibaba presents MIMO Controllable Character Video Synthesis with Spatial Decomposed Modeling Character video synthesis aims to produce realistic videos of animatable characters within lifelike scenes. As a fundamental problem in the computer vision and graphics community, 3D works typically require multi-view captures for per-case training, which severely limits their applicability of modeling arbitrary characters in a short time. Recent 2D methods break this limitation via pre-trained diffusion models, but they struggle for pose generality and scene interaction. To this end, we propose MIMO, a novel framework which can not only synthesize character videos with controllable attributes (i.e., character, motion and scene) provided by simple user inputs, but also simultaneously achieve advanced scalability to arbitrary characters, generality to novel 3D motions, and applicability to interactive real-world scenes in a unified framework. The core idea is to encode the 2D video to compact spatial codes, considering the inherent 3D nature of video occurrence. Concretely, we lift the 2D frame pixels into 3D using monocular depth estimators, and decompose the video clip to three spatial components (i.e., main human, underlying scene, and floating occlusion) in hierarchical layers based on the 3D depth. These components are further encoded to canonical identity code, structured motion code and full scene code, which are utilized as control signals of synthesis process. The design of spatial decomposed modeling enables flexible user control, complex motion expression, as well as 3D-aware synthesis for scene interactions. Experimental results demonstrate effectiveness and robustness of the proposed method.
1:29

Alibaba presents MIMO Controllable Character Video Synthesis with Spatial Decomposed Modeling Character video synthesis aims to produce realistic videos of animatable characters within lifelike scenes. As a fundamental problem in the computer vision and graphics community, 3D works typically require multi-view captures for per-case training, which severely limits their applicability of modeling arbitrary characters in a short time. Recent 2D methods break this limitation via pre-trained diffusion models, but they struggle for pose generality and scene interaction. To this end, we propose MIMO, a novel framework which can not only synthesize character videos with controllable attributes (i.e., character, motion and scene) provided by simple user inputs, but also simultaneously achieve advanced scalability to arbitrary characters, generality to novel 3D motions, and applicability to interactive real-world scenes in a unified framework. The core idea is to encode the 2D video to compact spatial codes, considering the inherent 3D nature of video occurrence. Concretely, we lift the 2D frame pixels into 3D using monocular depth estimators, and decompose the video clip to three spatial components (i.e., main human, underlying scene, and floating occlusion) in hierarchical layers based on the 3D depth. These components are further encoded to canonical identity code, structured motion code and full scene code, which are utilized as control signals of synthesis process. The design of spatial decomposed modeling enables flexible user control, complex motion expression, as well as 3D-aware synthesis for scene interactions. Experimental results demonstrate effectiveness and robustness of the proposed method.

AK

148,998 görüntüleme • 1 yıl önce

Excited to share this demo from Over the Reality! Watch our Unitree Go2 robodog navigating our office while reconstructing the 3D space in real-time using the VGGT-based foundation vision model. This is a prime example of machine perception in action, turning raw RGB camera feeds into rich, detailed 3D maps! The robodog's RGB cam generates a dense, textured 3D reconstruction via VGGT from a few photograms, capturing nuances like object shapes and surfaces with impressive fidelity (main view). Compare that to the standard LiDAR system (top right), it's sparser, more point-cloud focused, lacking the visual richness. Vision models are closing the gap fast! What's powering this? VGGT, a cutting-edge foundation model for 3D perception, trained on datasets orders of magnitude smaller than our massive OVER 3D maps dataset. Imagine the leap when we apply OVER's scale to VGGT-like transformer based architectures, denser reconstructions, better generalization, revolutionary for robotics, machine perception & AR! Stay tuned for more breakthroughs at the intersection of AI, robotics, and DePIN. We're building the future of Physical AI and Spatial Computing at Over the Reality 🌐 What do you think, ready for robodogs in your world? Drop your thoughts! 🤖🌐
0:25

Excited to share this demo from Over the Reality! Watch our Unitree Go2 robodog navigating our office while reconstructing the 3D space in real-time using the VGGT-based foundation vision model. This is a prime example of machine perception in action, turning raw RGB camera feeds into rich, detailed 3D maps! The robodog's RGB cam generates a dense, textured 3D reconstruction via VGGT from a few photograms, capturing nuances like object shapes and surfaces with impressive fidelity (main view). Compare that to the standard LiDAR system (top right), it's sparser, more point-cloud focused, lacking the visual richness. Vision models are closing the gap fast! What's powering this? VGGT, a cutting-edge foundation model for 3D perception, trained on datasets orders of magnitude smaller than our massive OVER 3D maps dataset. Imagine the leap when we apply OVER's scale to VGGT-like transformer based architectures, denser reconstructions, better generalization, revolutionary for robotics, machine perception & AR! Stay tuned for more breakthroughs at the intersection of AI, robotics, and DePIN. We're building the future of Physical AI and Spatial Computing at Over the Reality 🌐 What do you think, ready for robodogs in your world? Drop your thoughts! 🤖🌐

Over the Reality 🌐

359,717 görüntüleme • 10 ay önce

PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking paper page: introduce PointOdyssey, a large-scale synthetic dataset, and data generation framework, for the training and evaluation of long-term fine-grained tracking algorithms. Our goal is to advance the state-of-the-art by placing emphasis on long videos with naturalistic motion. Toward the goal of naturalism, we animate deformable characters using real-world motion capture data, we build 3D scenes to match the motion capture environments, and we render camera viewpoints using trajectories mined via structure-from-motion on real videos. We create combinatorial diversity by randomizing character appearance, motion profiles, materials, lighting, 3D assets, and atmospheric effects. Our dataset currently includes 104 videos, averaging 2,000 frames long, with orders of magnitude more correspondence annotations than prior work. We show that existing methods can be trained from scratch in our dataset and outperform the published variants. Finally, we introduce modifications to the PIPs point tracking method, greatly widening its temporal receptive field, which improves its performance on PointOdyssey as well as on two real-world benchmarks.
0:33

PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking paper page: introduce PointOdyssey, a large-scale synthetic dataset, and data generation framework, for the training and evaluation of long-term fine-grained tracking algorithms. Our goal is to advance the state-of-the-art by placing emphasis on long videos with naturalistic motion. Toward the goal of naturalism, we animate deformable characters using real-world motion capture data, we build 3D scenes to match the motion capture environments, and we render camera viewpoints using trajectories mined via structure-from-motion on real videos. We create combinatorial diversity by randomizing character appearance, motion profiles, materials, lighting, 3D assets, and atmospheric effects. Our dataset currently includes 104 videos, averaging 2,000 frames long, with orders of magnitude more correspondence annotations than prior work. We show that existing methods can be trained from scratch in our dataset and outperform the published variants. Finally, we introduce modifications to the PIPs point tracking method, greatly widening its temporal receptive field, which improves its performance on PointOdyssey as well as on two real-world benchmarks.

AK

122,533 görüntüleme • 3 yıl önce

Multi-view Reconstruction via SfM-guided Monocular Depth Estimation Contributions: • We propose a novel approach to inject SfM priors into diffusion-based depth estimation, enabling highly accurate and multi-view consistent depth predictions for each viewpoint. • Based on the proposed depth estimator, we design a new multi-view 3D geometry reconstruction framework and process some synthetic datasets to facilitate training. • We evaluate our method on diverse real-world scene data, including objects, indoor environments, streetscapes, and aerial scenes, demonstrating the superior performance and generalization capability of our approach.
0:30

Multi-view Reconstruction via SfM-guided Monocular Depth Estimation Contributions: • We propose a novel approach to inject SfM priors into diffusion-based depth estimation, enabling highly accurate and multi-view consistent depth predictions for each viewpoint. • Based on the proposed depth estimator, we design a new multi-view 3D geometry reconstruction framework and process some synthetic datasets to facilitate training. • We evaluate our method on diverse real-world scene data, including objects, indoor environments, streetscapes, and aerial scenes, demonstrating the superior performance and generalization capability of our approach.

MrNeRF

25,651 görüntüleme • 1 yıl önce

DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision paper page: We have witnessed significant progress in deep learning-based 3D vision, ranging from neural radiance field (NeRF) based 3D representation learning to applications in novel view synthesis (NVS). However, existing scene-level datasets for deep learning-based 3D vision, limited to either synthetic environments or a narrow selection of real-world scenes, are quite insufficient. This insufficiency not only hinders a comprehensive benchmark of existing methods but also caps what could be explored in deep learning-based 3D analysis. To address this critical gap, we present DL3DV-10K, a large-scale scene dataset, featuring 51.2 million frames from 10,510 videos captured from 65 types of point-of-interest (POI) locations, covering both bounded and unbounded scenes, with different levels of reflection, transparency, and lighting. We conducted a comprehensive benchmark of recent NVS methods on DL3DV-10K, which revealed valuable insights for future research in NVS. In addition, we have obtained encouraging results in a pilot study to learn generalizable NeRF from DL3DV-10K, which manifests the necessity of a large-scale scene-level dataset to forge a path toward a foundation model for learning 3D representation.
0:29

DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision paper page: We have witnessed significant progress in deep learning-based 3D vision, ranging from neural radiance field (NeRF) based 3D representation learning to applications in novel view synthesis (NVS). However, existing scene-level datasets for deep learning-based 3D vision, limited to either synthetic environments or a narrow selection of real-world scenes, are quite insufficient. This insufficiency not only hinders a comprehensive benchmark of existing methods but also caps what could be explored in deep learning-based 3D analysis. To address this critical gap, we present DL3DV-10K, a large-scale scene dataset, featuring 51.2 million frames from 10,510 videos captured from 65 types of point-of-interest (POI) locations, covering both bounded and unbounded scenes, with different levels of reflection, transparency, and lighting. We conducted a comprehensive benchmark of recent NVS methods on DL3DV-10K, which revealed valuable insights for future research in NVS. In addition, we have obtained encouraging results in a pilot study to learn generalizable NeRF from DL3DV-10K, which manifests the necessity of a large-scale scene-level dataset to forge a path toward a foundation model for learning 3D representation.

AK

49,917 görüntüleme • 2 yıl önce

MAGS-SLAM: Monocular Multi-Agent Gaussian Splatting SLAM for Geometrically and Photometrically Consistent Reconstruction TL;DR: The first RGB-only multi-agent 3D Gaussian Splatting SLAM for collaborative photorealistic scene reconstruction. Contributions: (1) We propose the first monocular RGB-only multi-agent 3D Gaussian Splatting SLAM system. It integrates Gaussian front-ends, compact submap summaries, inter-agent verification, Sim(3) submap pose graph, and occupancy-aware fusion into a unified framework, achieving accurate tracking and photorealistic reconstruction without depth sensors. (2) We propose a Pose-Graph Bundle Adjustment (PGBA)-consistent Sim(3) loop closure mechanism for multi-agent systems, which jointly resolves intra- and inter-agent scale drift through a submap-level Sim(3) pose graph coupling geometric and photometric residuals. Robustness is ensured by a spatial-extent gate that rejects degenerate loops and an adaptive edge invalidation scheme consistent with evolving PGBA corrections. (3) We propose an occupancy-aware fusion framework for coherent multi-agent Gaussian maps. It combines occupancy-grid deduplication, decoupled coordinator, and joint pose-Gaussian photometric refinement to eliminate duplicated Gaussians, residual misalignment, and photometric seams across agents. (4) We introduce ReplicaMultiagent Plus dataset. While existing multi-agent datasets are typically limited to 2-3 agents with short trajectories, our dataset scales to 4 agents with long-horizon trajectories. In addition, we provide ground-truth geometry and semantic annotations, supporting the evaluation of monocular, RGB-D, and semantic multi-agent SLAM for collaborative dense reconstruction.
0:29

MAGS-SLAM: Monocular Multi-Agent Gaussian Splatting SLAM for Geometrically and Photometrically Consistent Reconstruction TL;DR: The first RGB-only multi-agent 3D Gaussian Splatting SLAM for collaborative photorealistic scene reconstruction. Contributions: (1) We propose the first monocular RGB-only multi-agent 3D Gaussian Splatting SLAM system. It integrates Gaussian front-ends, compact submap summaries, inter-agent verification, Sim(3) submap pose graph, and occupancy-aware fusion into a unified framework, achieving accurate tracking and photorealistic reconstruction without depth sensors. (2) We propose a Pose-Graph Bundle Adjustment (PGBA)-consistent Sim(3) loop closure mechanism for multi-agent systems, which jointly resolves intra- and inter-agent scale drift through a submap-level Sim(3) pose graph coupling geometric and photometric residuals. Robustness is ensured by a spatial-extent gate that rejects degenerate loops and an adaptive edge invalidation scheme consistent with evolving PGBA corrections. (3) We propose an occupancy-aware fusion framework for coherent multi-agent Gaussian maps. It combines occupancy-grid deduplication, decoupled coordinator, and joint pose-Gaussian photometric refinement to eliminate duplicated Gaussians, residual misalignment, and photometric seams across agents. (4) We introduce ReplicaMultiagent Plus dataset. While existing multi-agent datasets are typically limited to 2-3 agents with short trajectories, our dataset scales to 4 agents with long-horizon trajectories. In addition, we provide ground-truth geometry and semantic annotations, supporting the evaluation of monocular, RGB-D, and semantic multi-agent SLAM for collaborative dense reconstruction.

MrNeRF

19,357 görüntüleme • 2 ay önce

LLaVA-3D A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness Recent advancements in Large Multimodal Models (LMMs) have greatly enhanced their proficiency in 2D visual understanding tasks, enabling them to effectively process and understand images and videos. However, the development of LMMs with 3D-awareness for 3D scene understanding has been hindered by the lack of large-scale 3D vision-language datasets and powerful 3D encoders. In this paper, we introduce a simple yet effective framework called LLaVA-3D. Leveraging the strong 2D understanding priors from LLaVA, our LLaVA-3D efficiently adapts LLaVA for 3D scene understanding without compromising 2D understanding capabilities. To achieve this, we employ a simple yet effective representation, 3D Patch, which connects 2D CLIP patch features with their corresponding positions in 3D space. By integrating the 3D Patches into 2D LMMs and employing joint 2D and 3D vision-language instruction tuning, we establish a unified architecture for both 2D image understanding and 3D scene understanding. Experimental results show that LLaVA-3D converges 3.5x faster than existing 3D LMMs when trained on 3D vision-language datasets. Moreover, LLaVA-3D not only achieves state-of-the-art performance across various 3D tasks but also maintains comparable 2D image understanding and vision-language conversation capabilities with LLaVA.
0:31

LLaVA-3D A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness Recent advancements in Large Multimodal Models (LMMs) have greatly enhanced their proficiency in 2D visual understanding tasks, enabling them to effectively process and understand images and videos. However, the development of LMMs with 3D-awareness for 3D scene understanding has been hindered by the lack of large-scale 3D vision-language datasets and powerful 3D encoders. In this paper, we introduce a simple yet effective framework called LLaVA-3D. Leveraging the strong 2D understanding priors from LLaVA, our LLaVA-3D efficiently adapts LLaVA for 3D scene understanding without compromising 2D understanding capabilities. To achieve this, we employ a simple yet effective representation, 3D Patch, which connects 2D CLIP patch features with their corresponding positions in 3D space. By integrating the 3D Patches into 2D LMMs and employing joint 2D and 3D vision-language instruction tuning, we establish a unified architecture for both 2D image understanding and 3D scene understanding. Experimental results show that LLaVA-3D converges 3.5x faster than existing 3D LMMs when trained on 3D vision-language datasets. Moreover, LLaVA-3D not only achieves state-of-the-art performance across various 3D tasks but also maintains comparable 2D image understanding and vision-language conversation capabilities with LLaVA.

AK

41,736 görüntüleme • 1 yıl önce

Incredible to see the Aria Digital Twin (ADT) dataset leveraged here! 🚀 ADT is a game-changer for AI—it bridges the gap between real-world sensor data and 1:1 3D virtual reconstructions by providing a hyper-accurate "gold-standard" benchmark. Using this data, the RADIO-ViPE team proved that "uncalibrated" predictions can be nearly as accurate as those from expensive, high-end sensor rigs. This is a massive step forward for robots and AI systems understanding 3D spaces in real-time. 👓✨ Paper: Dataset: 💡Nathan Yan
0:30

Incredible to see the Aria Digital Twin (ADT) dataset leveraged here! 🚀 ADT is a game-changer for AI—it bridges the gap between real-world sensor data and 1:1 3D virtual reconstructions by providing a hyper-accurate "gold-standard" benchmark. Using this data, the RADIO-ViPE team proved that "uncalibrated" predictions can be nearly as accurate as those from expensive, high-end sensor rigs. This is a massive step forward for robots and AI systems understanding 3D spaces in real-time. 👓✨ Paper: Dataset: 💡Nathan Yan

Project Aria @Meta

26,780 görüntüleme • 2 ay önce

I was really impressed by the UMI gripper (Cheng Chi et al.), but a key limitation is that **force-related data wasn’t captured**: humans feel haptic feedback through the mechanical springs, but the robot couldn’t leverage that info, limiting the data’s value for fine-grained manipulation tasks. Led by my amazing students Yolanda Zhu and Binghao Huang, we designed a **portable visuo-tactile gripper** by integrating our dense, flexible tactile arrays with the UMI gripper to enable large-scale in-the-wild data collection. 🔗 We demonstrate **cross-modal representation learning** and **downstream policy learning** on tasks requiring in-hand state estimation (e.g., test tube reorientation) and fine-grained force sensing (e.g., pipette fluid transfer). Key takeaways: - Our flexible tactile arrays store the rich haptic information humans perceive as dense tactile signals. - Portability and robustness are key for in-the-wild data collection; our portable gripper is compact, lightweight, and durable. - Touch provides precise, robust measurements of in-hand object pose, invariant to lighting and viewpoint. - Cross-modal pretraining on large-scale in-the-wild data significantly improves policy robustness and sample efficiency (as shown many times before — and verified again here!). Also check out our previous investigations of dense, flexible tactile grids for understanding human-robot-environment interactions: - Dense tactile glove (Nature ’19): - 3D-ViTac (CoRL ’24):
5:35

I was really impressed by the UMI gripper (Cheng Chi et al.), but a key limitation is that **force-related data wasn’t captured**: humans feel haptic feedback through the mechanical springs, but the robot couldn’t leverage that info, limiting the data’s value for fine-grained manipulation tasks. Led by my amazing students Yolanda Zhu and Binghao Huang, we designed a **portable visuo-tactile gripper** by integrating our dense, flexible tactile arrays with the UMI gripper to enable large-scale in-the-wild data collection. 🔗 We demonstrate **cross-modal representation learning** and **downstream policy learning** on tasks requiring in-hand state estimation (e.g., test tube reorientation) and fine-grained force sensing (e.g., pipette fluid transfer). Key takeaways: - Our flexible tactile arrays store the rich haptic information humans perceive as dense tactile signals. - Portability and robustness are key for in-the-wild data collection; our portable gripper is compact, lightweight, and durable. - Touch provides precise, robust measurements of in-hand object pose, invariant to lighting and viewpoint. - Cross-modal pretraining on large-scale in-the-wild data significantly improves policy robustness and sample efficiency (as shown many times before — and verified again here!). Also check out our previous investigations of dense, flexible tactile grids for understanding human-robot-environment interactions: - Dense tactile glove (Nature ’19): - 3D-ViTac (CoRL ’24):

Yunzhu Li

13,188 görüntüleme • 1 yıl önce