Alert button
Picture for Vincent Sitzmann

Vincent Sitzmann

Alert button

MIT EECS

DittoGym: Learning to Control Soft Shape-Shifting Robots

Jan 29, 2024
Suning Huang, Boyuan Chen, Huazhe Xu, Vincent Sitzmann

Viaarxiv icon

pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction

Dec 21, 2023
David Charatan, Sizhe Li, Andrea Tagliasacchi, Vincent Sitzmann

Viaarxiv icon

Intrinsic Image Diffusion for Single-view Material Estimation

Dec 19, 2023
Peter Kocsis, Vincent Sitzmann, Matthias Nießner

Viaarxiv icon

Variational Barycentric Coordinates

Oct 05, 2023
Ana Dodik, Oded Stein, Vincent Sitzmann, Justin Solomon

Viaarxiv icon

Approaching human 3D shape perception with neurally mappable models

Sep 07, 2023
Thomas P. O'Connell, Tyler Bonnen, Yoni Friedman, Ayush Tewari, Josh B. Tenenbaum, Vincent Sitzmann, Nancy Kanwisher

Figure 1 for Approaching human 3D shape perception with neurally mappable models
Figure 2 for Approaching human 3D shape perception with neurally mappable models
Figure 3 for Approaching human 3D shape perception with neurally mappable models
Figure 4 for Approaching human 3D shape perception with neurally mappable models
Viaarxiv icon

Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervision

Jun 20, 2023
Ayush Tewari, Tianwei Yin, George Cazenavette, Semon Rezchikov, Joshua B. Tenenbaum, Frédo Durand, William T. Freeman, Vincent Sitzmann

Figure 1 for Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervision
Figure 2 for Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervision
Figure 3 for Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervision
Figure 4 for Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervision
Viaarxiv icon

FlowCam: Training Generalizable 3D Radiance Fields without Camera Poses via Pixel-Aligned Scene Flow

May 31, 2023
Cameron Smith, Yilun Du, Ayush Tewari, Vincent Sitzmann

Figure 1 for FlowCam: Training Generalizable 3D Radiance Fields without Camera Poses via Pixel-Aligned Scene Flow
Figure 2 for FlowCam: Training Generalizable 3D Radiance Fields without Camera Poses via Pixel-Aligned Scene Flow
Figure 3 for FlowCam: Training Generalizable 3D Radiance Fields without Camera Poses via Pixel-Aligned Scene Flow
Figure 4 for FlowCam: Training Generalizable 3D Radiance Fields without Camera Poses via Pixel-Aligned Scene Flow
Viaarxiv icon

Learning to Render Novel Views from Wide-Baseline Stereo Pairs

Apr 17, 2023
Yilun Du, Cameron Smith, Ayush Tewari, Vincent Sitzmann

Figure 1 for Learning to Render Novel Views from Wide-Baseline Stereo Pairs
Figure 2 for Learning to Render Novel Views from Wide-Baseline Stereo Pairs
Figure 3 for Learning to Render Novel Views from Wide-Baseline Stereo Pairs
Figure 4 for Learning to Render Novel Views from Wide-Baseline Stereo Pairs
Viaarxiv icon

DeLiRa: Self-Supervised Depth, Light, and Radiance Fields

Apr 06, 2023
Vitor Guizilini, Igor Vasiljevic, Jiading Fang, Rares Ambrus, Sergey Zakharov, Vincent Sitzmann, Adrien Gaidon

Figure 1 for DeLiRa: Self-Supervised Depth, Light, and Radiance Fields
Figure 2 for DeLiRa: Self-Supervised Depth, Light, and Radiance Fields
Figure 3 for DeLiRa: Self-Supervised Depth, Light, and Radiance Fields
Figure 4 for DeLiRa: Self-Supervised Depth, Light, and Radiance Fields
Viaarxiv icon