Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

"Spann3R: 3D Reconstruction with Spatial Memory" In a nutshell: DUSt3R strikes again! Paper: Project: Method ⬇️

janusch_patas's profile picture

MrNeRF

16,613 subscribers

52,560 Aufrufe • vor 1 Jahr •via X (Twitter)

Wissenschaft & TechnologieBildung
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

I always thought camera pose estimation is necessary for 3D reconstruction, until Zequn and Stephen proved me wrong! Introducing PreF3R, purely feed-forward 3D Gaussian Splatting without any intermediate pose estimation and COLMAP initialization. Video in, 3D Gaussians and novel view rendering out. Key technique: spatial memory network from Spann3R and Gaussian head supervised by pointmap loss plus photometric loss. See more at:
0:19

I always thought camera pose estimation is necessary for 3D reconstruction, until Zequn and Stephen proved me wrong! Introducing PreF3R, purely feed-forward 3D Gaussian Splatting without any intermediate pose estimation and COLMAP initialization. Video in, 3D Gaussians and novel view rendering out. Key technique: spatial memory network from Spann3R and Gaussian head supervised by pointmap loss plus photometric loss. See more at:

Heng Yang

20,160 Aufrufe • vor 1 Jahr

WildGaussians: 3D Gaussian Splatting in the Wild Project: Code: Method ⬇️ 1 I 2
0:18

WildGaussians: 3D Gaussian Splatting in the Wild Project: Code: Method ⬇️ 1 I 2

MrNeRF

21,175 Aufrufe • vor 1 Jahr

This is completely nuts. Can't wait until the paper is released! "SuperGaussian: Repurposing Video Models for 3D Super Resolution" Project: Paper video ⬇️ 1 I 2
0:12

This is completely nuts. Can't wait until the paper is released! "SuperGaussian: Repurposing Video Models for 3D Super Resolution" Project: Paper video ⬇️ 1 I 2

MrNeRF

78,214 Aufrufe • vor 2 Jahren

Using vDISCO tissue clearing, and a new ultrabright chemical labeling strategy, this Neuron paper introduces LINCS, a powerful method for rapid 3D connectivity mapping in large tissue samples, from whole brains to whole bodies. A very nice advance for scalable circuit mapping, especially by combining strong, uniform labeling with sparse single-neuron reconstruction. Outstanding work by the Rui Lin lab. Full paper: #TissueClearing #LightSheetMicroscopy #Neuroscience #BrainMapping #Connectomics #3DImaging
0:18

Using vDISCO tissue clearing, and a new ultrabright chemical labeling strategy, this Neuron paper introduces LINCS, a powerful method for rapid 3D connectivity mapping in large tissue samples, from whole brains to whole bodies. A very nice advance for scalable circuit mapping, especially by combining strong, uniform labeling with sparse single-neuron reconstruction. Outstanding work by the Rui Lin lab. Full paper: #TissueClearing #LightSheetMicroscopy #Neuroscience #BrainMapping #Connectomics #3DImaging

Ali Max Erturk

13,883 Aufrufe • vor 2 Monaten

Lightplane Highly-Scalable Components for Neural 3D Fields Contemporary 3D research, particularly in reconstruction and generation, heavily relies on 2D images for inputs or supervision. However, current designs for these 2D-3D mapping are memory-intensive, posing a
0:12

Lightplane Highly-Scalable Components for Neural 3D Fields Contemporary 3D research, particularly in reconstruction and generation, heavily relies on 2D images for inputs or supervision. However, current designs for these 2D-3D mapping are memory-intensive, posing a

AK

18,896 Aufrufe • vor 2 Jahren

Human Hair Reconstruction with Strand-Aligned 3D Gaussians Contributions (cited): – We propose a new 3D line lifting scheme that uses a modified 3DGS reconstruction technique to lift 2D orientation maps into a 3D field while also providing refinement of the camera parameters; – We introduce a dual representation of hair strand polylines and 3D Gaussians to achieve differentiable rasterization of hair strands and leverage photometric constraints for strand-based hair reconstruction; – Based on these components, we propose a coarse-to-fine optimization method for prior-guided hair reconstruction that leverages both latent and explicit representations of the hairstyle.
0:13

Human Hair Reconstruction with Strand-Aligned 3D Gaussians Contributions (cited): – We propose a new 3D line lifting scheme that uses a modified 3DGS reconstruction technique to lift 2D orientation maps into a 3D field while also providing refinement of the camera parameters; – We introduce a dual representation of hair strand polylines and 3D Gaussians to achieve differentiable rasterization of hair strands and leverage photometric constraints for strand-based hair reconstruction; – Based on these components, we propose a coarse-to-fine optimization method for prior-guided hair reconstruction that leverages both latent and explicit representations of the hairstyle.

MrNeRF

106,497 Aufrufe • vor 1 Jahr

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.
0:12

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

52,801 Aufrufe • vor 1 Jahr

Yu et al., "MosaicMem: Hybrid Spatial Memory for Controllable Video World Models" A patch-based spatial memory that you raster into views + glues to make things work.
0:10

Yu et al., "MosaicMem: Hybrid Spatial Memory for Controllable Video World Models" A patch-based spatial memory that you raster into views + glues to make things work.

Kwang Moo Yi

11,170 Aufrufe • vor 2 Monaten

Direct3D‑S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention
0:12

Direct3D‑S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention

Dreaming Tulpa 🥓👑

27,799 Aufrufe • vor 1 Jahr

Oh wow! I just tested Splatt3R with my own data on my computer, which creates 3D Gaussian Splats at 4 FPS on uncalibrated 512x512 2D images! It's by far the fastest 3D reconstruction method, powered by MASt3R. Check out the video!
0:17

Oh wow! I just tested Splatt3R with my own data on my computer, which creates 3D Gaussian Splats at 4 FPS on uncalibrated 512x512 2D images! It's by far the fastest 3D reconstruction method, powered by MASt3R. Check out the video!

MrNeRF

67,464 Aufrufe • vor 1 Jahr

SAM 3D Body is a CVPR 2026 award candidate paper from AI at Meta model recovers a full 3D human body mesh from a single RGB image you can run it automatically, or guide the reconstruction with masks and 2D keypoints thx to Niels Rogge for awesome demo idea
0:13

SAM 3D Body is a CVPR 2026 award candidate paper from AI at Meta model recovers a full 3D human body mesh from a single RGB image you can run it automatically, or guide the reconstruction with masks and 2D keypoints thx to Niels Rogge for awesome demo idea

SkalskiP

71,147 Aufrufe • vor 10 Tagen

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.
0:19

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

21,340 Aufrufe • vor 1 Jahr

🚀New paper out - We present Video-MSG (Multimodal Sketch Guidance), a novel planning-based training-free guidance method for T2V models, improving control of spatial layout and object trajectories. 🔧 Key idea: • Generate a Video Sketch — a spatio-temporal plan with background, foreground, and motion in the pixel space. • Encode this structure directly into the latent space of the diffusion model during generation, which does not require fine-tuning or additional memory during inference. 🧵
0:12

🚀New paper out - We present Video-MSG (Multimodal Sketch Guidance), a novel planning-based training-free guidance method for T2V models, improving control of spatial layout and object trajectories. 🔧 Key idea: • Generate a Video Sketch — a spatio-temporal plan with background, foreground, and motion in the pixel space. • Encode this structure directly into the latent space of the diffusion model during generation, which does not require fine-tuning or additional memory during inference. 🧵

Jialu Li

35,060 Aufrufe • vor 1 Jahr

Large venues change daily, but most teams rely on outdated maps. With Scaniverse, scan, capture & reconstruct venues into high-fidelity, georeferenced 3D models. 🏟 Plan venue operations 🦺 Improve safety readiness 🛠 Manage assets over time Turn any venue into a continuously updated live spatial model. Download and try: #NianticSpatial #Scaniverse #GeospatialAI #PhysicalAI #AI #3D #DigitalTwins #Reconstruction
0:13

Large venues change daily, but most teams rely on outdated maps. With Scaniverse, scan, capture & reconstruct venues into high-fidelity, georeferenced 3D models. 🏟 Plan venue operations 🦺 Improve safety readiness 🛠 Manage assets over time Turn any venue into a continuously updated live spatial model. Download and try: #NianticSpatial #Scaniverse #GeospatialAI #PhysicalAI #AI #3D #DigitalTwins #Reconstruction

Niantic Spatial 🌎

11,842 Aufrufe • vor 1 Monat

Wow with new #iPhone15 Pro we’ll be able to record 3d spatial videos! #AppleEvent
0:10

Wow with new #iPhone15 Pro we’ll be able to record 3d spatial videos! #AppleEvent

iJustine

226,330 Aufrufe • vor 2 Jahren

Spatial Vacuuming Never miss a spot again!
0:17

Spatial Vacuuming Never miss a spot again!

Daniel Beauchamp

20,531,064 Aufrufe • vor 2 Jahren

CVPR Highlight #1 VGGT: Visual Geometry Grounded Transformer (best paper award) 🚀 Super-fast 3D scene reconstruction 🤗 Model and demo on Hugging Face The result is a GLB point cloud 👇
0:15

CVPR Highlight #1 VGGT: Visual Geometry Grounded Transformer (best paper award) 🚀 Super-fast 3D scene reconstruction 🤗 Model and demo on Hugging Face The result is a GLB point cloud 👇

dylan

19,325 Aufrufe • vor 1 Jahr

Robots struggle with strict action rules…memory and symbols help them learn fast. [Project + Full video link ⬇️] Robots struggle when tasks require specific steps in a fixed order. What if memory helped them think symbolically and learn faster? Solving tasks like unlocking a door then opening it is hard for deep RL. But by learning constraint relationships and storing them in memory, robots can solve these tasks much faster; with fewer trials and less training. Why it works ✅ Learns symbolic rules about action constraints ✅ Uses memory to transfer what it learned across tasks ✅ Handles real-world exploration with just 30 minutes of data ✅ Needs 10x fewer episodes than deep RL approaches This memory-based method shows a promising path forward for robots learning structured, real-world tasks. Full video: Paper: Thank you, Mrinal Verghese for sharing this amazing work! 🙏
0:18

Robots struggle with strict action rules…memory and symbols help them learn fast. [Project + Full video link ⬇️] Robots struggle when tasks require specific steps in a fixed order. What if memory helped them think symbolically and learn faster? Solving tasks like unlocking a door then opening it is hard for deep RL. But by learning constraint relationships and storing them in memory, robots can solve these tasks much faster; with fewer trials and less training. Why it works ✅ Learns symbolic rules about action constraints ✅ Uses memory to transfer what it learned across tasks ✅ Handles real-world exploration with just 30 minutes of data ✅ Needs 10x fewer episodes than deep RL approaches This memory-based method shows a promising path forward for robots learning structured, real-world tasks. Full video: Paper: Thank you, Mrinal Verghese for sharing this amazing work! 🙏

Ilir Aliu - eu/acc

10,241 Aufrufe • vor 1 Jahr