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.

🚀 Speed3R (#CVPR2026): sparse feed-forward 3D reconstruction. 12.4× faster on 1000-view sequences with minimal accuracy loss. Plug-and-play on VGGT, π³, etc. 🔗 📄 💻

Kai Han

1,614 subscribers

11,492 views • 5 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Glob3R: Global Structure-from-Motion With 3D Foundation Models HKUST Spatial Artificial Intelligence Lab · Alibaba Group · Nanjin University · Fudan University Glob3R is a scalable global 3D reconstruction framework built on geometric foundation models. It converts dense feed-forward predictions into reliable multi-view tracks and jointly refines camera poses and scene geometry through motion averaging and bundle adjustment. Glob3R improves reconstruction accuracy and consistency on long sequences, large-scale scenes, and unordered image collections.

Glob3R: Global Structure-from-Motion With 3D Foundation Models HKUST Spatial Artificial Intelligence Lab · Alibaba Group · Nanjin University · Fudan University Glob3R is a scalable global 3D reconstruction framework built on geometric foundation models. It converts dense feed-forward predictions into reliable multi-view tracks and jointly refines camera poses and scene geometry through motion averaging and bundle adjustment. Glob3R improves reconstruction accuracy and consistency on long sequences, large-scale scenes, and unordered image collections.

Ryohei Sasaki@engineer

18,157 views • 3 months ago

Introducing FLARE #CVPR2026 2025 FLARE is a feed-forward model that simultaneously estimates high-quality camera poses, 3D geometry, and appearance from sparse uncalibrated images. 1/4

Introducing FLARE #CVPR2026 2025 FLARE is a feed-forward model that simultaneously estimates high-quality camera poses, 3D geometry, and appearance from sparse uncalibrated images. 1/4

Gordon Wetzstein

29,572 views • 1 year ago

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

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

Jianyuan

784,854 views • 5 months ago

🚀 Our NeurIPS '24 work, Large Spatial Model (LSM), is here! LSM performs semantic 3D reconstruction in just 0.1s, processing unposed data via feed-forward 3D reconstruction. 👉It leverages large-scale 3D datasets with minimal annotations, defining a 3D latent space. We are continuously exploring how this explicit 3D representation can further enhance reasoning and robotic learning. 🔗 Try our online Gradio demo with your own data at #NeurIPS2024 #3DReconstruction

🚀 Our NeurIPS '24 work, Large Spatial Model (LSM), is here! LSM performs semantic 3D reconstruction in just 0.1s, processing unposed data via feed-forward 3D reconstruction. 👉It leverages large-scale 3D datasets with minimal annotations, defining a 3D latent space. We are continuously exploring how this explicit 3D representation can further enhance reasoning and robotic learning. 🔗 Try our online Gradio demo with your own data at #NeurIPS2024 #3DReconstruction

Zhiwen(Aaron) Fan

44,051 views • 2 years ago

Today, we are open-sourcing Hunyuan World 1.1 (WorldMirror), a universal feed-forward 3D reconstruction model. 🚀🚀🚀 While our previously released Hunyuan World 1.0 (open-sourced, lite version deployable on consumer GPUs) focused on generating 3D worlds from text or single-view images, Hunyuan World 1.1 significantly expands the input scope by unlocking video-to-3D and multi-view-to-3D world creation. Highlights: 🔹Any Input, Maximized Flexibility and Fidelity: Flexibly integrates diverse geometric priors (camera poses, intrinsics, depth maps) to resolve structural ambiguities and ensure geometrically consistent 3D outputs. 🔹Any Output, SOTA Results：This elegant architecture simultaneously generates multiple 3D representations: dense point clouds, multi-view depth maps, camera parameters, surface normals, and 3D Gaussian Splattings. 🔹Single-GPU & Fast Inference: As an all-in-one, feed-forward model, Hunyuan World 1.1 runs on a single GPU and delivers all 3D attributes in a single forward pass, within seconds. 🌐Project Page: 🔗Github： 🤗Hugging Face： ✨Demo: 📄Technical Report:

Today, we are open-sourcing Hunyuan World 1.1 (WorldMirror), a universal feed-forward 3D reconstruction model. 🚀🚀🚀 While our previously released Hunyuan World 1.0 (open-sourced, lite version deployable on consumer GPUs) focused on generating 3D worlds from text or single-view images, Hunyuan World 1.1 significantly expands the input scope by unlocking video-to-3D and multi-view-to-3D world creation. Highlights: 🔹Any Input, Maximized Flexibility and Fidelity: Flexibly integrates diverse geometric priors (camera poses, intrinsics, depth maps) to resolve structural ambiguities and ensure geometrically consistent 3D outputs. 🔹Any Output, SOTA Results：This elegant architecture simultaneously generates multiple 3D representations: dense point clouds, multi-view depth maps, camera parameters, surface normals, and 3D Gaussian Splattings. 🔹Single-GPU & Fast Inference: As an all-in-one, feed-forward model, Hunyuan World 1.1 runs on a single GPU and delivers all 3D attributes in a single forward pass, within seconds. 🌐Project Page: 🔗Github： 🤗Hugging Face： ✨Demo: 📄Technical Report:

Tencent Hy

169,023 views • 1 year ago

Feed-forward 3D Gaussians from Visual Geometry Group (VGG) strike again! Flash3D has now been accepted to 3DV 2025: it is a method for feed-forward single-view 3D scene reconstruction. Project page: Code: Arxiv: A 🧵👇

Feed-forward 3D Gaussians from Visual Geometry Group (VGG) strike again! Flash3D has now been accepted to 3DV 2025: it is a method for feed-forward single-view 3D scene reconstruction. Project page: Code: Arxiv: A 🧵👇

Stan Szymanowicz

26,994 views • 1 year ago

How to master multi-robot cooperative mapping? We're excited to release MR.ScaleMaster, which masters the scales to scale - any feed-forward Visual SLAM (MASt3R-SLAM, π³, VGGT-SLAM 2.0, LoGeR, …) - across any robot (legged, wheeled, handheld, …) 🔗

How to master multi-robot cooperative mapping? We're excited to release MR.ScaleMaster, which masters the scales to scale - any feed-forward Visual SLAM (MASt3R-SLAM, π³, VGGT-SLAM 2.0, LoGeR, …) - across any robot (legged, wheeled, handheld, …) 🔗

Giseop Kim

28,905 views • 6 months ago

Scal3R from NVIDIA Accurate online 3D reconstruction on kilometer-scale sequences with only ~1% extra parameters on a frozen backbone, trained in 8 hours on a single GPU.

Scal3R from NVIDIA Accurate online 3D reconstruction on kilometer-scale sequences with only ~1% extra parameters on a frozen backbone, trained in 8 hours on a single GPU.

DailyPapers

15,508 views • 2 months ago

📢 GenRecon Code Release 📢 Few images in → complete, high-fidelity 3D scene out! GenRecon builds a generative prior on full scenes, resulting in unprecedented 3D reconstruction quality. 🔗 🌐 📄

📢 GenRecon Code Release 📢 Few images in → complete, high-fidelity 3D scene out! GenRecon builds a generative prior on full scenes, resulting in unprecedented 3D reconstruction quality. 🔗 🌐 📄

Matthias Niessner

40,580 views • 4 months ago

📢📢GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction📢📢 Reconstructing high-fidelity 3D scenes from sparse RGB input is hard. It needs a strong 3D prior! We reformulate multi-view scene reconstruction as conditional 3D generation over overlapping spatial chunks, lifting posed image features into a generative shape prior via 3D conditioning. As an example prior, we build on Trellis2, and train it such that its reconstruction is pixel aligned and matches from all views. GenRecon achieves unprecedented reconstruction quality from any sparse RGB input sequence, even from a phone capture. The reconstruction also includes PBR materials which facilitates relighting and virtual object insertion. Amazing work by Katharina Schmid, Nicolas von Lützow, Jozef, Angela Dai

📢📢GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction📢📢 Reconstructing high-fidelity 3D scenes from sparse RGB input is hard. It needs a strong 3D prior! We reformulate multi-view scene reconstruction as conditional 3D generation over overlapping spatial chunks, lifting posed image features into a generative shape prior via 3D conditioning. As an example prior, we build on Trellis2, and train it such that its reconstruction is pixel aligned and matches from all views. GenRecon achieves unprecedented reconstruction quality from any sparse RGB input sequence, even from a phone capture. The reconstruction also includes PBR materials which facilitates relighting and virtual object insertion. Amazing work by Katharina Schmid, Nicolas von Lützow, Jozef, Angela Dai

Matthias Niessner

18,482 views • 5 months ago

⚡️ Excited to announce Fast3R: 3D reconstruction of 1000+ images in a single forward pass! Fast3R achieves 251 FPS at its peak. 🔥 Try the demo with your images or video! 🔗 Website: 🎮 Demo: #CVPR2025 #3D AI at Meta

⚡️ Excited to announce Fast3R: 3D reconstruction of 1000+ images in a single forward pass! Fast3R achieves 251 FPS at its peak. 🔥 Try the demo with your images or video! 🔗 Website: 🎮 Demo: #CVPR2025 #3D AI at Meta

Jianing “Jed” Yang

71,881 views • 1 year ago

🚀High-Res 3D Text-to-Texture🚀 🎨#MVPaint delivers high-res 3D textures with minimal UV wrapping dependency and high versatility using synchronized multi-view diffusion 📑 Paper: 🏠 Project Page: 🧑‍💻 Code:

🚀High-Res 3D Text-to-Texture🚀 🎨#MVPaint delivers high-res 3D textures with minimal UV wrapping dependency and high versatility using synchronized multi-view diffusion 📑 Paper: 🏠 Project Page: 🧑‍💻 Code:

Ziwei Liu

28,184 views • 2 years ago

VAST AI releases Triplane Meets Gaussian Splatting on Hugging Face Fast and Generalizable Single-View 3D Reconstruction with Transformers demo: TGS enables fast reconstruction from single-view image. It builds the 3D representation upon a hybrid Triplane-Gaussian representation by evaluating a transformer-based framework, from which 3D Gaussians would be decoded

VAST AI releases Triplane Meets Gaussian Splatting on Hugging Face Fast and Generalizable Single-View 3D Reconstruction with Transformers demo: TGS enables fast reconstruction from single-view image. It builds the 3D representation upon a hybrid Triplane-Gaussian representation by evaluating a transformer-based framework, from which 3D Gaussians would be decoded

AK

113,242 views • 2 years ago

Novel view synthesis has long been a core challenge in 3D vision. But how much 3D inductive bias is truly needed? —Surprisingly, very little! Introducing "LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias"—a fully transformer-based approach that enables scalable, generalizable, and fully data-driven novel view synthesis, from sparse posed inputs. 🧵(1/6) Project Page:

Novel view synthesis has long been a core challenge in 3D vision. But how much 3D inductive bias is truly needed? —Surprisingly, very little! Introducing "LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias"—a fully transformer-based approach that enables scalable, generalizable, and fully data-driven novel view synthesis, from sparse posed inputs. 🧵(1/6) Project Page:

Haian Jin

114,987 views • 2 years ago

Introducing V-DPM, for 4D reconstruction of in-the-wild videos. We build on top of VGGT, using Dynamic Point Maps for jointly representing 3D and motion. Joint work with: Eldar Insafutdinov , Lai Zihang , and Andrea Vedaldi. Visual Geometry Group (VGG). Check out the demo and code 👇

Introducing V-DPM, for 4D reconstruction of in-the-wild videos. We build on top of VGGT, using Dynamic Point Maps for jointly representing 3D and motion. Joint work with: Eldar Insafutdinov , Lai Zihang , and Andrea Vedaldi. Visual Geometry Group (VGG). Check out the demo and code 👇

Edgar Sucar

26,037 views • 9 months ago

Live monocular 3D reconstruction from camera feed, with multi-frame stitching and relative positioning (frame buffer of 4)... running on M3 mac cpu at 24fps... visualised using Rerun next up... realtime semantic navigation in 3d space...

Live monocular 3D reconstruction from camera feed, with multi-frame stitching and relative positioning (frame buffer of 4)... running on M3 mac cpu at 24fps... visualised using Rerun next up... realtime semantic navigation in 3d space...

ud

22,080 views • 10 months ago

🚀Turn Single Image into 3D Human🚀 #GeneMAN is a generalizable single-image 3D human reconstruction framework that turns in-the-wild images into high-quality 3D humans with ease 🔗Project: 📜Paper: 🧑‍💻Code:

🚀Turn Single Image into 3D Human🚀 #GeneMAN is a generalizable single-image 3D human reconstruction framework that turns in-the-wild images into high-quality 3D humans with ease 🔗Project: 📜Paper: 🧑‍💻Code:

Ziwei Liu

26,953 views • 1 year ago

💥 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)

💥 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

27,343 views • 1 year ago

🍺 LagerNVS (CVPR 2026) 🍺 LagerNVS is a generalizable, feed-forward, real-time Novel View Synthesis network which - performs rendering in real time, - generalizes to in-the-wild data, - works with and without known source cameras, - sets a new state-of-the-art among deterministic methods, - can be paired with a diffusion decoder for generative extrapolation. LagerNVS shows that 3D biases are useful for Novel View Synthesis but explicit 3D representations are not required to achieve them. We use 3D biases in (1) architecture design and (2) pre-training: (1) In NVS with explicit 3D representations (3DGS, NeRF) reconstruction is typically difficult and slow, but rendering is much faster and simpler. We mimic this process in the network design: we use a large (1B params) encoder and a small, lightweight decoder (ViT-B). This allows increasing the network capacity while still achieving real-time rendering. (2) The encoder, initialized from VGGT, was pre-trained with 3D reconstruction objectives, making the initial features 3D aware. Both substantially improve performance. Project page: Code: Paper: Models: Work done with Jianyuan Minghao Chen Christian Rupprecht and Andrea Vedaldi

🍺 LagerNVS (CVPR 2026) 🍺 LagerNVS is a generalizable, feed-forward, real-time Novel View Synthesis network which - performs rendering in real time, - generalizes to in-the-wild data, - works with and without known source cameras, - sets a new state-of-the-art among deterministic methods, - can be paired with a diffusion decoder for generative extrapolation. LagerNVS shows that 3D biases are useful for Novel View Synthesis but explicit 3D representations are not required to achieve them. We use 3D biases in (1) architecture design and (2) pre-training: (1) In NVS with explicit 3D representations (3DGS, NeRF) reconstruction is typically difficult and slow, but rendering is much faster and simpler. We mimic this process in the network design: we use a large (1B params) encoder and a small, lightweight decoder (ViT-B). This allows increasing the network capacity while still achieving real-time rendering. (2) The encoder, initialized from VGGT, was pre-trained with 3D reconstruction objectives, making the initial features 3D aware. Both substantially improve performance. Project page: Code: Paper: Models: Work done with Jianyuan Minghao Chen Christian Rupprecht and Andrea Vedaldi

Stan Szymanowicz

33,180 views • 7 months ago