Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Adaptive and Temporally Consistent Gaussian Surfels for Multi-view Dynamic Reconstruction Contributions: • A method for efficiently reconstructing dynamic surfaces from multi-view videos using Gaussian surfels. • A unified and gradient-aware densification strategy for optimizing dynamic 3D Gaussians with fine details. • A temporal consistency approach that ensures stable and... show more

MrNeRF

16,835 subscribers

31,824 views • 1 year ago •via X (Twitter)

Gaming Science & Technology Education

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

GSTAR: Gaussian Surface Tracking and Reconstruction Contributions: • A new framework for tracking and reconstructing dynamic scenes, combining 3D Gaussians and meshes to effectively manage changes in topology. • A method for Gaussian unbinding and surface re-meshing, allowing for the generation of new surfaces as topologies evolve. • A method for handling large or fast deformations of surfaces between frames using scene flow warping. Abstract (excerpt): However, tracking dynamic surfaces with 3D Gaussians remains challenging due to complex topology changes, such as surfaces appearing, disappearing, or splitting. To address these challenges, we propose GSTAR, a novel method that achieves photo-realistic rendering, accurate surface reconstruction, and reliable 3D tracking for general dynamic scenes with changing topology. Given multi-view captures as input, GSTAR binds Gaussians to mesh faces to represent dynamic objects. For surfaces with consistent topology, GSTAR maintains the mesh topology and tracks the meshes using Gaussians.

GSTAR: Gaussian Surface Tracking and Reconstruction Contributions: • A new framework for tracking and reconstructing dynamic scenes, combining 3D Gaussians and meshes to effectively manage changes in topology. • A method for Gaussian unbinding and surface re-meshing, allowing for the generation of new surfaces as topologies evolve. • A method for handling large or fast deformations of surfaces between frames using scene flow warping. Abstract (excerpt): However, tracking dynamic surfaces with 3D Gaussians remains challenging due to complex topology changes, such as surfaces appearing, disappearing, or splitting. To address these challenges, we propose GSTAR, a novel method that achieves photo-realistic rendering, accurate surface reconstruction, and reliable 3D tracking for general dynamic scenes with changing topology. Given multi-view captures as input, GSTAR binds Gaussians to mesh faces to represent dynamic objects. For surfaces with consistent topology, GSTAR maintains the mesh topology and tracks the meshes using Gaussians.

MrNeRF

22,698 views • 1 year ago

MoE-GS: Mixture of Experts for Dynamic Gaussian Splatting Contributions: • MoE-GS: the first dynamic Gaussian splatting framework employing a Mixture-of-Experts architecture, enabling robust and adaptive reconstruction across diverse dynamic scenes. • A novel Volume-aware Pixel Router integrates expert outputs through differentiable weight splatting, achieving spatially and temporally coherent adaptive blending. • Efficiency of MoE-GS is improved through single-pass multi-expert rendering and gate-aware Gaussian pruning. A separate knowledge distillation strategy trains individual experts with pseudo-labels from the MoE model, enhancing quality without modifying the architecture.

MoE-GS: Mixture of Experts for Dynamic Gaussian Splatting Contributions: • MoE-GS: the first dynamic Gaussian splatting framework employing a Mixture-of-Experts architecture, enabling robust and adaptive reconstruction across diverse dynamic scenes. • A novel Volume-aware Pixel Router integrates expert outputs through differentiable weight splatting, achieving spatially and temporally coherent adaptive blending. • Efficiency of MoE-GS is improved through single-pass multi-expert rendering and gate-aware Gaussian pruning. A separate knowledge distillation strategy trains individual experts with pseudo-labels from the MoE model, enhancing quality without modifying the architecture.

MrNeRF

10,408 views • 9 months ago

SplatVoxel: History-Aware Novel View Streaming without Temporal Training Contributions: • We propose a hybrid Splat-Voxel feed-forward reconstruction framework that leverages historical information to enable novel view streaming, without relying on multi-view video datasets for training. • We develop an efficient sparse voxel transformer with a coarse-to-fine voxel representation, outperforming existing feed-forward Gaussian splatting methods. • Experiment results demonstrate that our proposed framework enhances novel view synthesis for streaming scene reconstruction, providing better visual quality and reduced temporal artifacts through history-aware modeling.

SplatVoxel: History-Aware Novel View Streaming without Temporal Training Contributions: • We propose a hybrid Splat-Voxel feed-forward reconstruction framework that leverages historical information to enable novel view streaming, without relying on multi-view video datasets for training. • We develop an efficient sparse voxel transformer with a coarse-to-fine voxel representation, outperforming existing feed-forward Gaussian splatting methods. • Experiment results demonstrate that our proposed framework enhances novel view synthesis for streaming scene reconstruction, providing better visual quality and reduced temporal artifacts through history-aware modeling.

MrNeRF

10,823 views • 1 year ago

DroneSplat: 3D Gaussian Splatting for Robust 3D Reconstruction from In-the-Wild Drone Imagery Abstract: Drones have become essential tools for reconstructing wild scenes due to their outstanding maneuverability. Recent advances in radiance field methods have achieved remarkable rendering quality, providing a new avenue for 3D reconstruction from drone imagery. However, dynamic distractors in wild environments challenge the static scene assumption in radiance fields, while limited view constraints hinder the accurate capture of underlying scene geometry. To address these challenges, we introduce DroneSplat, a novel framework designed for robust 3D reconstruction from in-the-wild drone imagery. Our method adaptively adjusts masking thresholds by integrating local-global segmentation heuristics with statistical approaches, enabling precise identification and elimination of dynamic distractors in static scenes. We enhance 3D Gaussian Splatting with multi-view stereo predictions and a voxel-guided optimization strategy, supporting high-quality rendering under limited view constraints. For comprehensive evaluation, we provide a drone-captured 3D reconstruction dataset encompassing both dynamic and static scenes. Extensive experiments demonstrate that DroneSplat outperforms both 3DGS and NeRF baselines in handling in-the-wild drone imagery.

DroneSplat: 3D Gaussian Splatting for Robust 3D Reconstruction from In-the-Wild Drone Imagery Abstract: Drones have become essential tools for reconstructing wild scenes due to their outstanding maneuverability. Recent advances in radiance field methods have achieved remarkable rendering quality, providing a new avenue for 3D reconstruction from drone imagery. However, dynamic distractors in wild environments challenge the static scene assumption in radiance fields, while limited view constraints hinder the accurate capture of underlying scene geometry. To address these challenges, we introduce DroneSplat, a novel framework designed for robust 3D reconstruction from in-the-wild drone imagery. Our method adaptively adjusts masking thresholds by integrating local-global segmentation heuristics with statistical approaches, enabling precise identification and elimination of dynamic distractors in static scenes. We enhance 3D Gaussian Splatting with multi-view stereo predictions and a voxel-guided optimization strategy, supporting high-quality rendering under limited view constraints. For comprehensive evaluation, we provide a drone-captured 3D reconstruction dataset encompassing both dynamic and static scenes. Extensive experiments demonstrate that DroneSplat outperforms both 3DGS and NeRF baselines in handling in-the-wild drone imagery.

MrNeRF

21,346 views • 1 year ago

Gaussian Head Avatar: Ultra High-fidelity Head Avatar via Dynamic Gaussians paper page: Creating high-fidelity 3D head avatars has always been a research hotspot, but there remains a great challenge under lightweight sparse view setups. In this paper, we propose Gaussian Head Avatar represented by controllable 3D Gaussians for high-fidelity head avatar modeling. We optimize the neutral 3D Gaussians and a fully learned MLP-based deformation field to capture complex expressions. The two parts benefit each other, thereby our method can model fine-grained dynamic details while ensuring expression accuracy. Furthermore, we devise a well-designed geometry-guided initialization strategy based on implicit SDF and Deep Marching Tetrahedra for the stability and convergence of the training procedure. Experiments show our approach outperforms other state-of-the-art sparse-view methods, achieving ultra high-fidelity rendering quality at 2K resolution even under exaggerated expressions.

AK

65,853 views • 2 years ago

PackUV: Packed Gaussian UV Maps for 4D Volumetric Video - PackUV — A new volumetric video representation that packs 3D Gaussian attributes into a sequence of UV atlases for efficient streaming and storage, making it readily compatible with existing video coding infrastructure. - PackUV-GS — An efficient method to fit PackUV directly from multiview videos using optical-flow-based keyframing and Gaussian labeling to handle large motions, disocclusions, and temporal consistency. - PackUV-2B — The largest multi-view 4D dataset with 2B frames, large motions, and disocclusions. It provides 360° coverage from 50+ synchronized cameras.

PackUV: Packed Gaussian UV Maps for 4D Volumetric Video - PackUV — A new volumetric video representation that packs 3D Gaussian attributes into a sequence of UV atlases for efficient streaming and storage, making it readily compatible with existing video coding infrastructure. - PackUV-GS — An efficient method to fit PackUV directly from multiview videos using optical-flow-based keyframing and Gaussian labeling to handle large motions, disocclusions, and temporal consistency. - PackUV-2B — The largest multi-view 4D dataset with 2B frames, large motions, and disocclusions. It provides 360° coverage from 50+ synchronized cameras.

MrNeRF

17,035 views • 5 months ago

[SIGGRAPH ASIA '25] Detail-Enhanced Gaussian Splatting for Large-Scale Volumetric Capture Contributions: - A two-stage approach to performance capture, combining a scene-scale capture rig and a single-actor facial capture rig. - A novel high-quality scene-scale volumetric performance capture rig, incorporating both static and dynamic cameras to track the performance of multiple actors. - A reconstruction pipeline for dynamic performance capture, featuring stable calibration of moving cameras and 4DGS with improved dynamic range and color fidelity. - A detail enhancement Diffusion Model, which supports 4K, RGB, and Alpha, with improved temporal stability.

[SIGGRAPH ASIA '25] Detail-Enhanced Gaussian Splatting for Large-Scale Volumetric Capture Contributions: - A two-stage approach to performance capture, combining a scene-scale capture rig and a single-actor facial capture rig. - A novel high-quality scene-scale volumetric performance capture rig, incorporating both static and dynamic cameras to track the performance of multiple actors. - A reconstruction pipeline for dynamic performance capture, featuring stable calibration of moving cameras and 4DGS with improved dynamic range and color fidelity. - A detail enhancement Diffusion Model, which supports 4K, RGB, and Alpha, with improved temporal stability.

MrNeRF

42,456 views • 9 months ago

WeatherEdit: Controllable Weather Editing with 4D Gaussian Field Contributions: 1. Based on our analysis of weather editing characteristics, we introduce WeatherEdit, a comprehensive and efficient framework for realistic and controllable weather generation. Compared with existing methods that focus on either background editing or static weather effects, a progressive 2D-to-4D transformation process in WeatherEdit enhances adaptability across a wider range of scenarios. 2. We introduce an all-in-one adapter to enable a diffusion model for multi-weather (snowy, rainy, and fog) synthesis, along with a Temporal-View attention to ensure consistent editing across multi-frame and multi-view. 3. We design a 4D Gaussian field for weather particle modeling, enabling plausible simulation of raindrops, snowflakes, and fog with controllable severity. 4. We demonstrate WeatherEdit’s effectiveness in generating realistic, consistent, and controllable weather effects in 3D driving scenes, showcasing its applicability to real-world scenarios.

WeatherEdit: Controllable Weather Editing with 4D Gaussian Field Contributions: 1. Based on our analysis of weather editing characteristics, we introduce WeatherEdit, a comprehensive and efficient framework for realistic and controllable weather generation. Compared with existing methods that focus on either background editing or static weather effects, a progressive 2D-to-4D transformation process in WeatherEdit enhances adaptability across a wider range of scenarios. 2. We introduce an all-in-one adapter to enable a diffusion model for multi-weather (snowy, rainy, and fog) synthesis, along with a Temporal-View attention to ensure consistent editing across multi-frame and multi-view. 3. We design a 4D Gaussian field for weather particle modeling, enabling plausible simulation of raindrops, snowflakes, and fog with controllable severity. 4. We demonstrate WeatherEdit’s effectiveness in generating realistic, consistent, and controllable weather effects in 3D driving scenes, showcasing its applicability to real-world scenarios.

MrNeRF

10,691 views • 1 year ago

Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models Contributions: • We introduce Diffuman4D, a novel diffusion model that generates spatio-temporally consistent and high-resolution (1024p) human videos from sparse-view video inputs. • We propose a sliding iterative denoising mechanism that enhances both the spatial and temporal consistency of generated long-term videos while maintaining efficient inference. • We design a human pose conditioning scheme to enhance the appearance quality and motion accuracy of generated human videos. • We plan to release our processed version of the DNA-Rendering dataset, which we believe will benefit future research in this area.

Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models Contributions: • We introduce Diffuman4D, a novel diffusion model that generates spatio-temporally consistent and high-resolution (1024p) human videos from sparse-view video inputs. • We propose a sliding iterative denoising mechanism that enhances both the spatial and temporal consistency of generated long-term videos while maintaining efficient inference. • We design a human pose conditioning scheme to enhance the appearance quality and motion accuracy of generated human videos. • We plan to release our processed version of the DNA-Rendering dataset, which we believe will benefit future research in this area.

MrNeRF

24,729 views • 1 year ago

F3D-Gaus: Feed-forward 3D-aware Generation on ImageNet with Cycle-Consistent Gaussian Splatting Contributions: • We pioneer 3D-aware generation using generalizable feed-forward Gaussian Splatting representation, achieving significant efficiency and favorable rendering quality on monocular datasets. • We significantly advance the capability of pixel-aligned Gaussian Splatting representations by designing a self-supervised cycle training strategy specifically tailored for monocular datasets. • We further mitigate the artifacts of 3D-aware representations caused by large viewpoint shifts by introducing geometry-aware video priors.

F3D-Gaus: Feed-forward 3D-aware Generation on ImageNet with Cycle-Consistent Gaussian Splatting Contributions: • We pioneer 3D-aware generation using generalizable feed-forward Gaussian Splatting representation, achieving significant efficiency and favorable rendering quality on monocular datasets. • We significantly advance the capability of pixel-aligned Gaussian Splatting representations by designing a self-supervised cycle training strategy specifically tailored for monocular datasets. • We further mitigate the artifacts of 3D-aware representations caused by large viewpoint shifts by introducing geometry-aware video priors.

MrNeRF

14,229 views • 1 year ago

Self-Calibrating Gaussian Splatting for Large Field of View Reconstruction Note: Check below for full video. Abstract (cited): "In this paper, we present a self-calibrating framework that jointly optimizes camera parameters, lens distortion, and 3D Gaussian representations, enabling accurate and efficient scene reconstruction. Our technique is particularly effective for high-quality scene reconstruction from large field-of-view (FOV) imagery taken with wide-angle lenses, allowing the scene to be modeled from a smaller number of images. We introduce a novel method for modeling complex lens distortions using a hybrid network that combines invertible residual networks with explicit grids. This design effectively regularizes the optimization process, achieving greater accuracy than conventional camera models. Additionally, we propose a cubemap-based resampling strategy to support large FOV images without sacrificing resolution or introducing distortion artifacts. Our method is compatible with the fast rasterization of Gaussian Splatting, adaptable to a wide variety of camera lens distortions, and demonstrates state-of-the-art performance on both synthetic and real-world datasets."

Self-Calibrating Gaussian Splatting for Large Field of View Reconstruction Note: Check below for full video. Abstract (cited): "In this paper, we present a self-calibrating framework that jointly optimizes camera parameters, lens distortion, and 3D Gaussian representations, enabling accurate and efficient scene reconstruction. Our technique is particularly effective for high-quality scene reconstruction from large field-of-view (FOV) imagery taken with wide-angle lenses, allowing the scene to be modeled from a smaller number of images. We introduce a novel method for modeling complex lens distortions using a hybrid network that combines invertible residual networks with explicit grids. This design effectively regularizes the optimization process, achieving greater accuracy than conventional camera models. Additionally, we propose a cubemap-based resampling strategy to support large FOV images without sacrificing resolution or introducing distortion artifacts. Our method is compatible with the fast rasterization of Gaussian Splatting, adaptable to a wide variety of camera lens distortions, and demonstrates state-of-the-art performance on both synthetic and real-world datasets."

MrNeRF

17,206 views • 1 year ago

Wonderland: Navigating 3D Scenes from a Single Image Contributions: • First, we introduce a representation for controllable 3D generation by leveraging the generative priors from camera-guided video diffusion models. Unlike image models, video diffusion models are trained on extensive video datasets. This enables them to capture comprehensive spatial relationships within scenes across multiple views and embed a form of "3D awareness" in their latent space, which allows us to maintain 3D consistency in novel view synthesis. • Second, to achieve controllable novel view generation, we empower video models with precise control over specified camera motions. We introduce a novel dual-branch conditioning mechanism that effectively incorporates desired diverse camera trajectories into the video diffusion model. This enables expansion of a single image into a multi-view consistent capture of a 3D scene with precise pose control. • Third, to achieve efficient 3D reconstruction, we directly transform video latents into 3DGS. We propose a novel latent-based large reconstruction model (LaLRM) that lifts video latents to 3D in a feed-forward manner. With this design, during inference, our model directly predicts 3DGS from a single input image, effectively aligning the generation and reconstruction tasks—and bridging image space and 3D space—through the video latent space. Compared with reconstructing scenes from images, the video latent space offers a 256× spatial-temporal reduction while retaining essential and consistent 3D structural details. Such a high degree of compression is crucial, as it allows the LaLRM to handle a wider range of 3D scenes within the reconstruction framework, with the same memory constraints.

Wonderland: Navigating 3D Scenes from a Single Image Contributions: • First, we introduce a representation for controllable 3D generation by leveraging the generative priors from camera-guided video diffusion models. Unlike image models, video diffusion models are trained on extensive video datasets. This enables them to capture comprehensive spatial relationships within scenes across multiple views and embed a form of "3D awareness" in their latent space, which allows us to maintain 3D consistency in novel view synthesis. • Second, to achieve controllable novel view generation, we empower video models with precise control over specified camera motions. We introduce a novel dual-branch conditioning mechanism that effectively incorporates desired diverse camera trajectories into the video diffusion model. This enables expansion of a single image into a multi-view consistent capture of a 3D scene with precise pose control. • Third, to achieve efficient 3D reconstruction, we directly transform video latents into 3DGS. We propose a novel latent-based large reconstruction model (LaLRM) that lifts video latents to 3D in a feed-forward manner. With this design, during inference, our model directly predicts 3DGS from a single input image, effectively aligning the generation and reconstruction tasks—and bridging image space and 3D space—through the video latent space. Compared with reconstructing scenes from images, the video latent space offers a 256× spatial-temporal reduction while retaining essential and consistent 3D structural details. Such a high degree of compression is crucial, as it allows the LaLRM to handle a wider range of 3D scenes within the reconstruction framework, with the same memory constraints.

MrNeRF

52,849 views • 1 year ago

3D Gaussian Splatting for Real-Time Radiance Field Rendering paper page: Radiance Field methods have recently revolutionized novel-view synthesis of scenes captured with multiple photos or videos. However, achieving high visual quality still requires neural networks that are costly to train and render, while recent faster methods inevitably trade off speed for quality. For unbounded and complete scenes (rather than isolated objects) and 1080p resolution rendering, no current method can achieve real-time display rates. We introduce three key elements that allow us to achieve state-of-the-art visual quality while maintaining competitive training times and importantly allow high-quality real-time (>= 30 fps) novel-view synthesis at 1080p resolution. First, starting from sparse points produced during camera calibration, we represent the scene with 3D Gaussians that preserve desirable properties of continuous volumetric radiance fields for scene optimization while avoiding unnecessary computation in empty space; Second, we perform interleaved optimization/density control of the 3D Gaussians, notably optimizing anisotropic covariance to achieve an accurate representation of the scene; Third, we develop a fast visibility-aware rendering algorithm that supports anisotropic splatting and both accelerates training and allows realtime rendering. We demonstrate state-of-the-art visual quality and real-time rendering on several established datasets.

3D Gaussian Splatting for Real-Time Radiance Field Rendering paper page: Radiance Field methods have recently revolutionized novel-view synthesis of scenes captured with multiple photos or videos. However, achieving high visual quality still requires neural networks that are costly to train and render, while recent faster methods inevitably trade off speed for quality. For unbounded and complete scenes (rather than isolated objects) and 1080p resolution rendering, no current method can achieve real-time display rates. We introduce three key elements that allow us to achieve state-of-the-art visual quality while maintaining competitive training times and importantly allow high-quality real-time (>= 30 fps) novel-view synthesis at 1080p resolution. First, starting from sparse points produced during camera calibration, we represent the scene with 3D Gaussians that preserve desirable properties of continuous volumetric radiance fields for scene optimization while avoiding unnecessary computation in empty space; Second, we perform interleaved optimization/density control of the 3D Gaussians, notably optimizing anisotropic covariance to achieve an accurate representation of the scene; Third, we develop a fast visibility-aware rendering algorithm that supports anisotropic splatting and both accelerates training and allows realtime rendering. We demonstrate state-of-the-art visual quality and real-time rendering on several established datasets.

AK

633,674 views • 3 years ago

📢Pix2NPHM: Learning to Regress NPHM Reconstructions From a Single Image📢 We directly regress neural parametric head models (NPHMs) from a single image — fast, stable, and significantly more expressive than classical 3DMMs such as FLAME. Face tracking & 3D reconstruction are often limited by the representational capacity of PCA-based face models. By lifting NPHMs to a first-class reconstruction primitive, we enable more accurate geometry, richer expressions, and finer animation control. Pix2NPHM obtains fast and reliable NPHM reconstructions on real-world data. Inference-time optimization against surface normals and canonical point maps can further increase fidelity. Key to successful and generalized training of our ViT-based network are: (1) large-scale registration of existing 3D head datasets, and (2) self-supervised training on vast in-the-wild 2D video datasets using pseudo ground-truth surface normals. Finally, we show that geometry-aware pretraining on pixel-aligned reconstruction tasks significantly outperforms generic visual pretraining (e.g., DINO-style features) in terms of generalization. 🌍 🎥 Great work by Simon Giebenhain, Tobias Kirschstein, Liam Schoneveld, Davide Davoli, Zhe Chen

📢Pix2NPHM: Learning to Regress NPHM Reconstructions From a Single Image📢 We directly regress neural parametric head models (NPHMs) from a single image — fast, stable, and significantly more expressive than classical 3DMMs such as FLAME. Face tracking & 3D reconstruction are often limited by the representational capacity of PCA-based face models. By lifting NPHMs to a first-class reconstruction primitive, we enable more accurate geometry, richer expressions, and finer animation control. Pix2NPHM obtains fast and reliable NPHM reconstructions on real-world data. Inference-time optimization against surface normals and canonical point maps can further increase fidelity. Key to successful and generalized training of our ViT-based network are: (1) large-scale registration of existing 3D head datasets, and (2) self-supervised training on vast in-the-wild 2D video datasets using pseudo ground-truth surface normals. Finally, we show that geometry-aware pretraining on pixel-aligned reconstruction tasks significantly outperforms generic visual pretraining (e.g., DINO-style features) in terms of generalization. 🌍 🎥 Great work by Simon Giebenhain, Tobias Kirschstein, Liam Schoneveld, Davide Davoli, Zhe Chen

Matthias Niessner

37,850 views • 7 months ago

DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion TL;DR: Create 3/4DGS from Video Diffusion Note: Some first inference code released (not all yet). Contributions (cited): • We present DimensionX, a novel framework for generating photorealistic 3D and 4D scenes from only a single image using controllable video diffusion. • We propose ST-Director, which decouples the spatial and temporal priors in video diffusion models by learning (spatial and temporal) dimension-aware modules with our curated datasets. We further enhance the hybriddimension control with a training-free composition approach according to the essence of video diffusion denoising process. • To bridge the gap between video diffusion and real-world scenes, we design a trajectory-aware mechanism for 3D generation and an identity-preserving denoising approach for 4D generation, enabling more realistic and controllable scene synthesis. • Extensive experiments manifest that our DimensionX delivers superior performance in video, 3D, and 4D generation compared with baseline methods.

DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion TL;DR: Create 3/4DGS from Video Diffusion Note: Some first inference code released (not all yet). Contributions (cited): • We present DimensionX, a novel framework for generating photorealistic 3D and 4D scenes from only a single image using controllable video diffusion. • We propose ST-Director, which decouples the spatial and temporal priors in video diffusion models by learning (spatial and temporal) dimension-aware modules with our curated datasets. We further enhance the hybriddimension control with a training-free composition approach according to the essence of video diffusion denoising process. • To bridge the gap between video diffusion and real-world scenes, we design a trajectory-aware mechanism for 3D generation and an identity-preserving denoising approach for 4D generation, enabling more realistic and controllable scene synthesis. • Extensive experiments manifest that our DimensionX delivers superior performance in video, 3D, and 4D generation compared with baseline methods.

MrNeRF

17,062 views • 1 year ago

Segment Any 3D Gaussians paper page: Interactive 3D segmentation in radiance fields is an appealing task since its importance in 3D scene understanding and manipulation. However, existing methods face challenges in either achieving fine-grained, multi-granularity segmentation or contending with substantial computational overhead, inhibiting real-time interaction. In this paper, we introduce Segment Any 3D GAussians (SAGA), a novel 3D interactive segmentation approach that seamlessly blends a 2D segmentation foundation model with 3D Gaussian Splatting (3DGS), a recent breakthrough of radiance fields. SAGA efficiently embeds multi-granularity 2D segmentation results generated by the segmentation foundation model into 3D Gaussian point features through well-designed contrastive training. Evaluation on existing benchmarks demonstrates that SAGA can achieve competitive performance with state-of-the-art methods. Moreover, SAGA achieves multi-granularity segmentation and accommodates various prompts, including points, scribbles, and 2D masks. Notably, SAGA can finish the 3D segmentation within milliseconds, achieving nearly 1000x acceleration compared to previous SOTA.

Segment Any 3D Gaussians paper page: Interactive 3D segmentation in radiance fields is an appealing task since its importance in 3D scene understanding and manipulation. However, existing methods face challenges in either achieving fine-grained, multi-granularity segmentation or contending with substantial computational overhead, inhibiting real-time interaction. In this paper, we introduce Segment Any 3D GAussians (SAGA), a novel 3D interactive segmentation approach that seamlessly blends a 2D segmentation foundation model with 3D Gaussian Splatting (3DGS), a recent breakthrough of radiance fields. SAGA efficiently embeds multi-granularity 2D segmentation results generated by the segmentation foundation model into 3D Gaussian point features through well-designed contrastive training. Evaluation on existing benchmarks demonstrates that SAGA can achieve competitive performance with state-of-the-art methods. Moreover, SAGA achieves multi-granularity segmentation and accommodates various prompts, including points, scribbles, and 2D masks. Notably, SAGA can finish the 3D segmentation within milliseconds, achieving nearly 1000x acceleration compared to previous SOTA.

AK

69,542 views • 2 years ago

🤖 One predictive backbone, three distinct tasks, consistent gains: a strong signal that investing in reusable world models is the right abstraction for robot learning. Toyota Research Institute (TRI) just ran the same idea three different ways—and it worked each time. Using our NVIDIA Cosmos Predict 2–style world models, they hit SOTA with dynamic view synthesis, teleop data augmentation (even up against MimicGen as an upper bound), and navigation world models. 🙌 📚 dynamic view synthesis 📚 teleop data augmentation (also compare to MimicGen as an upper bound) 📚 navigation world models 📸 from

🤖 One predictive backbone, three distinct tasks, consistent gains: a strong signal that investing in reusable world models is the right abstraction for robot learning. Toyota Research Institute (TRI) just ran the same idea three different ways—and it worked each time. Using our NVIDIA Cosmos Predict 2–style world models, they hit SOTA with dynamic view synthesis, teleop data augmentation (even up against MimicGen as an upper bound), and navigation world models. 🙌 📚 dynamic view synthesis 📚 teleop data augmentation (also compare to MimicGen as an upper bound) 📚 navigation world models 📸 from

NVIDIA AI Developer

38,100 views • 5 months ago

ImmerseGen: Agent-Guided Immersive World Generation with Alpha-Textured Proxies Contributions: 1) We propose ImmerseGen, a novel agent-guided 3D environment generation framework. It uses simplified geometric proxies with alpha-textured meshes to produce compact, photorealistic worlds ready for real-time mobile VR rendering. 2) We propose a novel RGBA texturing paradigm. It first synthesizes 8K terrain textures using a geometry-conditioned panorama generator via user-centric mapping, and then directly generates alpha-textured proxy assets, avoiding fidelity loss typically resulting from mesh decimation. 3) To automate scene creation from user prompts, we introduce VLM-based modeling agents equipped with a novel grid-based semantic analysis. This enables 3D spatial reasoning from 2D observations and ensures accurate asset placement. ImmerseGen further enhances immersion with dynamic effects and ambient audio for a multisensory experience. 4) Experiments on multiple scene-generation scenarios and live mobile VR applications show that ImmerseGen outperforms previous methods in visual quality, realism, spatial coherence, and rendering efficiency for immersive real-time VR experiences.

ImmerseGen: Agent-Guided Immersive World Generation with Alpha-Textured Proxies Contributions: 1) We propose ImmerseGen, a novel agent-guided 3D environment generation framework. It uses simplified geometric proxies with alpha-textured meshes to produce compact, photorealistic worlds ready for real-time mobile VR rendering. 2) We propose a novel RGBA texturing paradigm. It first synthesizes 8K terrain textures using a geometry-conditioned panorama generator via user-centric mapping, and then directly generates alpha-textured proxy assets, avoiding fidelity loss typically resulting from mesh decimation. 3) To automate scene creation from user prompts, we introduce VLM-based modeling agents equipped with a novel grid-based semantic analysis. This enables 3D spatial reasoning from 2D observations and ensures accurate asset placement. ImmerseGen further enhances immersion with dynamic effects and ambient audio for a multisensory experience. 4) Experiments on multiple scene-generation scenarios and live mobile VR applications show that ImmerseGen outperforms previous methods in visual quality, realism, spatial coherence, and rendering efficiency for immersive real-time VR experiences.

MrNeRF

14,225 views • 1 year ago

Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation paper page: Large text-to-image diffusion models have exhibited impressive proficiency in generating high-quality images. However, when applying these models to video domain, ensuring temporal consistency across video frames remains a formidable challenge. This paper proposes a novel zero-shot text-guided video-to-video translation framework to adapt image models to videos. The framework includes two parts: key frame translation and full video translation. The first part uses an adapted diffusion model to generate key frames, with hierarchical cross-frame constraints applied to enforce coherence in shapes, textures and colors. The second part propagates the key frames to other frames with temporal-aware patch matching and frame blending. Our framework achieves global style and local texture temporal consistency at a low cost (without re-training or optimization). The adaptation is compatible with existing image diffusion techniques, allowing our framework to take advantage of them, such as customizing a specific subject with LoRA, and introducing extra spatial guidance with ControlNet. Extensive experimental results demonstrate the effectiveness of our proposed framework over existing methods in rendering high-quality and temporally-coherent videos.

Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation paper page: Large text-to-image diffusion models have exhibited impressive proficiency in generating high-quality images. However, when applying these models to video domain, ensuring temporal consistency across video frames remains a formidable challenge. This paper proposes a novel zero-shot text-guided video-to-video translation framework to adapt image models to videos. The framework includes two parts: key frame translation and full video translation. The first part uses an adapted diffusion model to generate key frames, with hierarchical cross-frame constraints applied to enforce coherence in shapes, textures and colors. The second part propagates the key frames to other frames with temporal-aware patch matching and frame blending. Our framework achieves global style and local texture temporal consistency at a low cost (without re-training or optimization). The adaptation is compatible with existing image diffusion techniques, allowing our framework to take advantage of them, such as customizing a specific subject with LoRA, and introducing extra spatial guidance with ControlNet. Extensive experimental results demonstrate the effectiveness of our proposed framework over existing methods in rendering high-quality and temporally-coherent videos.

AK

375,160 views • 3 years ago