Loading video...

Video Failed to Load

Go Home

Introducing VGGT-Ω: scaling feed-forward reconstruction across static and dynamic scenes, and studying whether the learned geometric representations transfer beyond reconstruction.

jianyuan_wang's profile picture

Jianyuan

2,718 subscribers

776,970 views • 27 days ago •via X (Twitter)

EducationScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

💥 Think more real data is needed for scene reconstruction? Think again! Meet MegaSynth: scaling up feed-forward 3D scene reconstruction with synthesized scenes. In 3 days, it generates 700K scenes for training—70x larger than real data! ✨ The secret? Reconstruction is mostly non-semantic! No need to rely heavily on real or highly realistic synthetic data. 🌐 Project: (1/4)
0:52

💥 Think more real data is needed for scene reconstruction? Think again! Meet MegaSynth: scaling up feed-forward 3D scene reconstruction with synthesized scenes. In 3 days, it generates 700K scenes for training—70x larger than real data! ✨ The secret? Reconstruction is mostly non-semantic! No need to rely heavily on real or highly realistic synthetic data. 🌐 Project: (1/4)

Hanwen Jiang

26,832 views • 1 year ago

Want high-quality 3D meshes with sharp geometric details? Try our newly released MeshFormer! It only takes 8 GPUs for two days of training, outperforming state-of-the-art models that use over a hundred GPUs! With 3D-native input guidance, representations, supervision, and post-processing, we significantly improve the training efficiency and geometric quality of feed-forward reconstruction models! Project page: Chong Zeng
0:21

Want high-quality 3D meshes with sharp geometric details? Try our newly released MeshFormer! It only takes 8 GPUs for two days of training, outperforming state-of-the-art models that use over a hundred GPUs! With 3D-native input guidance, representations, supervision, and post-processing, we significantly improve the training efficiency and geometric quality of feed-forward reconstruction models! Project page: Chong Zeng

Minghua Liu @ SIGGRAPHASIA25

16,320 views • 1 year ago

Introducing St4RTrack!🖖 Simultaneous 4D Reconstruction and Tracking in the world coordinate feed-forwardly, just by changing the meaning of two pointmaps!
1:57

Introducing St4RTrack!🖖 Simultaneous 4D Reconstruction and Tracking in the world coordinate feed-forwardly, just by changing the meaning of two pointmaps!

Junyi Zhang

52,426 views • 1 year ago

Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes Contributions: • We propose STORM, the first feed-forward, self-supervised method for fast and accurate reconstruction of dynamic 3D scenes from sparse, multi-timestep, posed camera images. • Our bottom-up framework aggregates and transforms per-frame 3D Gaussian Splats into a cohesive scene representation, enabling self-supervised motion estimation. Furthermore, we introduce motion tokens that capture common motion primitives and regularize motion predictions, facilitating dynamic motion group segmentation without explicit motion or correspondence supervision. • We present several enhancements for in-the-wild scenarios, including sky modeling, camera exposure inconsistency handling, large novel-view extrapolation, and fine-grained human motions reconstruction, making STORM well-suited for real-world applications.
0:31

Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes Contributions: • We propose STORM, the first feed-forward, self-supervised method for fast and accurate reconstruction of dynamic 3D scenes from sparse, multi-timestep, posed camera images. • Our bottom-up framework aggregates and transforms per-frame 3D Gaussian Splats into a cohesive scene representation, enabling self-supervised motion estimation. Furthermore, we introduce motion tokens that capture common motion primitives and regularize motion predictions, facilitating dynamic motion group segmentation without explicit motion or correspondence supervision. • We present several enhancements for in-the-wild scenarios, including sky modeling, camera exposure inconsistency handling, large novel-view extrapolation, and fine-grained human motions reconstruction, making STORM well-suited for real-world applications.

MrNeRF

53,292 views • 1 year ago

Excited to share MonST3R! -- a simple way to estimate geometry from unposed video of dynamic scene We achieve competitive results on several downstreams (video depth, camera pose) and believe this is a promising step toward feed-forward 4D reconstruction
1:03

Excited to share MonST3R! -- a simple way to estimate geometry from unposed video of dynamic scene We achieve competitive results on several downstreams (video depth, camera pose) and believe this is a promising step toward feed-forward 4D reconstruction

Junyi Zhang @CVPR

131,523 views • 1 year ago

📢 QuickSplat: Fast 3D Surface Reconstruction via Learned Gaussian Initialization Yueh-Cheng Liu learns 2DGS initialization, densification, and optimization priors from ScanNet++ => fast & accurate reconstruction! Project:
0:24

📢 QuickSplat: Fast 3D Surface Reconstruction via Learned Gaussian Initialization Yueh-Cheng Liu learns 2DGS initialization, densification, and optimization priors from ScanNet++ => fast & accurate reconstruction! Project:

Angela Dai

27,294 views • 1 year ago

V-DPM 4D Video Reconstruction with Dynamic Point Maps
3:26

V-DPM 4D Video Reconstruction with Dynamic Point Maps

AK

19,274 views • 4 months ago

Zhou et al., "PAGE-4D: Disentangled Pose and Geometry Estimation for 4D Perception" VGGT extended to dynamic scenes with a dynamic mask predictor.
0:25

Zhou et al., "PAGE-4D: Disentangled Pose and Geometry Estimation for 4D Perception" VGGT extended to dynamic scenes with a dynamic mask predictor.

Kwang Moo Yi

11,492 views • 7 months ago

Introducing the Digital Twin Catalog: We believe it’s the world’s highest quality dataset for object reconstruction research. It consists of over 2,400 physical objects scanned with state-of-art hardware and hand-tuned to achieve sub-millimeter-level geometric accuracy and photorealism. Project Aria @Meta
1:34

Introducing the Digital Twin Catalog: We believe it’s the world’s highest quality dataset for object reconstruction research. It consists of over 2,400 physical objects scanned with state-of-art hardware and hand-tuned to achieve sub-millimeter-level geometric accuracy and photorealism. Project Aria @Meta

Reality Labs at Meta

27,757 views • 1 year ago

📢Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction📢 -> highly accurate face reconstruction by training powerful VITs via surface normals and UV-coordinates estimation. The geometric cues from our 2D foundation model backbone constrain the 3DMM parameters, which allows us to achieve remarkable reconstruction accuracy - works for both single image and videos! In addition, we introduce a new 3D face reconstruction benchmark that evaluates both neutral and posed face geometry. 🌍 📷 Great work by Simon Giebenhain Tobias Kirschstein Martin Rünz Lourdes Agapito
0:32

📢Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction📢 -> highly accurate face reconstruction by training powerful VITs via surface normals and UV-coordinates estimation. The geometric cues from our 2D foundation model backbone constrain the 3DMM parameters, which allows us to achieve remarkable reconstruction accuracy - works for both single image and videos! In addition, we introduce a new 3D face reconstruction benchmark that evaluates both neutral and posed face geometry. 🌍 📷 Great work by Simon Giebenhain Tobias Kirschstein Martin Rünz Lourdes Agapito

Matthias Niessner

62,069 views • 1 year ago

📢 Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation Got only one or a few images and wondering if recovering the 3D environment is a reconstruction or generation problem? Why not do it with a generative reconstruction model! We show that a camera-conditioned video diffusion model can be transformed into a generative reconstruction model that directly outputs a high-quality 3D Gaussian Splatting representation through self-distillation, without requiring real-world training data. Check out our results in the video (wait for dynamic scenes in the second half!) : Project Page: Code and Models: Paper:
0:50

📢 Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation Got only one or a few images and wondering if recovering the 3D environment is a reconstruction or generation problem? Why not do it with a generative reconstruction model! We show that a camera-conditioned video diffusion model can be transformed into a generative reconstruction model that directly outputs a high-quality 3D Gaussian Splatting representation through self-distillation, without requiring real-world training data. Check out our results in the video (wait for dynamic scenes in the second half!) : Project Page: Code and Models: Paper:

Sherwin Bahmani

66,417 views • 8 months ago

Watch the new exclusive trailer for Sea of Remnants, launching with DLSS 4.5 Super Resolution, Ray Reconstruction, and path tracing. Brave the dynamic seas with #RTXOn →
0:50

Watch the new exclusive trailer for Sea of Remnants, launching with DLSS 4.5 Super Resolution, Ray Reconstruction, and path tracing. Brave the dynamic seas with #RTXOn →

NVIDIA GeForce

51,576 views • 3 months ago

Geometric Context Transformer for Streaming 3D Reconstruction Contributions: • We introduce LingBot-Map, a streaming 3D foundation model built around Geometric Context Attention (GCA), which maintains three complementary context types – anchor, pose-reference window, and trajectory memory – for efficient and consistent long-sequence streaming inference. • We propose an efficient training recipe based on progressive training and context parallelism with a relative loss formulation for stable long-sequence optimization. • We demonstrate that LingBot-Map achieves state-of-the-art performance on multiple benchmarks (Oxford Spires, Tanks and Temples, ETH3D, and 7-Scenes), significantly outperforming existing streaming approaches in reconstruction quality and inference speed.
1:10

Geometric Context Transformer for Streaming 3D Reconstruction Contributions: • We introduce LingBot-Map, a streaming 3D foundation model built around Geometric Context Attention (GCA), which maintains three complementary context types – anchor, pose-reference window, and trajectory memory – for efficient and consistent long-sequence streaming inference. • We propose an efficient training recipe based on progressive training and context parallelism with a relative loss formulation for stable long-sequence optimization. • We demonstrate that LingBot-Map achieves state-of-the-art performance on multiple benchmarks (Oxford Spires, Tanks and Temples, ETH3D, and 7-Scenes), significantly outperforming existing streaming approaches in reconstruction quality and inference speed.

MrNeRF

24,549 views • 1 month ago

💫It's fascinating that a single feed-forward pass through an LLM can replace a complex rendering pipeline, like Blender! Just feed it 3D shapes, xyz positions, and poses as tokens, and it spits out the image token-by-token. The dual, aka scene reconstruction, is also possible! 👇
0:26

💫It's fascinating that a single feed-forward pass through an LLM can replace a complex rendering pipeline, like Blender! Just feed it 3D shapes, xyz positions, and poses as tokens, and it spits out the image token-by-token. The dual, aka scene reconstruction, is also possible! 👇

Georgia Gkioxari

44,553 views • 1 year ago

"DVD: Dynamic Video Depth" TL;DR: Recovers temporally consistent depth from monocular videos using diffusion priors + geometric constraints, handling dynamic scenes and motion robustly.
0:36

"DVD: Dynamic Video Depth" TL;DR: Recovers temporally consistent depth from monocular videos using diffusion priors + geometric constraints, handling dynamic scenes and motion robustly.

Alexandre Morgand

11,804 views • 2 months ago

Spatial reconstruction is a long-context problem: real scenes come with hundreds of images. But O(N²) transformer-based models don’t scale efficiently. Introducing: 🤐ZipMap (CVPR ’26): Linear-Time, Stateful 3D Reconstruction via Test-Time Training (TTT). ZipMap “zips” a large image collection into an implicit TTT scene state in a single linear-time operation. The state will then be decoded into spatial outputs, and can be queried efficiently for novel-view geometry and appearance (~100 FPS) ZipMap is not only much faster (>20× faster than VGGT), but also matches or surpasses the accuracy of all SOTA models.
0:35

Spatial reconstruction is a long-context problem: real scenes come with hundreds of images. But O(N²) transformer-based models don’t scale efficiently. Introducing: 🤐ZipMap (CVPR ’26): Linear-Time, Stateful 3D Reconstruction via Test-Time Training (TTT). ZipMap “zips” a large image collection into an implicit TTT scene state in a single linear-time operation. The state will then be decoded into spatial outputs, and can be queried efficiently for novel-view geometry and appearance (~100 FPS) ZipMap is not only much faster (>20× faster than VGGT), but also matches or surpasses the accuracy of all SOTA models.

Haian Jin

78,090 views • 3 months ago

📢Face Anything: 4D Face Reconstruction from Any Image Sequence Transformer model for 4D face reconstruction and dense tracking: - predict canonical facial coordinates per pixel - tracking as reconstruction in canonical space - geometry + correspondences in one forward pass Key idea: a shared canonical space across frames - correspondences as nearest neighbors - no motion or deformation estimation Stable geometry and tracking, even under large expressions and viewpoint changes - check out our results! 🌐 ▶️ Great work by Umut Kocasarı, Simon Giebenhain, Richard Shaw
0:42

📢Face Anything: 4D Face Reconstruction from Any Image Sequence Transformer model for 4D face reconstruction and dense tracking: - predict canonical facial coordinates per pixel - tracking as reconstruction in canonical space - geometry + correspondences in one forward pass Key idea: a shared canonical space across frames - correspondences as nearest neighbors - no motion or deformation estimation Stable geometry and tracking, even under large expressions and viewpoint changes - check out our results! 🌐 ▶️ Great work by Umut Kocasarı, Simon Giebenhain, Richard Shaw

Matthias Niessner

61,367 views • 1 month ago

Reconstruction the #Third destroyed railway bridge near Qom, Iran, after attacks by the U.S -Israel. Negotiators, militaries, and engineers working together for Iran’s future. #Iran #Reconstruction #Infrastructure
0:21

Reconstruction the #Third destroyed railway bridge near Qom, Iran, after attacks by the U.S -Israel. Negotiators, militaries, and engineers working together for Iran’s future. #Iran #Reconstruction #Infrastructure

Embassy of Iran in Bulgaria

142,808 views • 2 months ago

VIDEO: Third Mainland Bridge requires either maintenance or reconstruction — with maintenance estimated at N3.8trn and reconstruction at N3.6trn, says Umahi
5:00

VIDEO: Third Mainland Bridge requires either maintenance or reconstruction — with maintenance estimated at N3.8trn and reconstruction at N3.6trn, says Umahi

TheCable

15,443 views • 10 months ago

Want to reconstruct very large-scale scenes accurately? Check out our Scal3R (CVPR'26 Highlight) — scaling up VGGT with TTT Layers: Split image sequences into chunks, compute TTT gradients per chunk, and then average gradients across chunks. Code is out:
1:45

Want to reconstruct very large-scale scenes accurately? Check out our Scal3R (CVPR'26 Highlight) — scaling up VGGT with TTT Layers: Split image sequences into chunks, compute TTT gradients per chunk, and then average gradients across chunks. Code is out:

Sida Peng

51,806 views • 2 months ago