Media Summary: Paper Abstract: 3D reconstruction of highly deformable surfaces (e.g. cloths) from monocular RGB videos is a challenging ... Single-image human mesh recovery is a challenging task due to the ill-posed nature of simultaneous body shape, pose, and ... N, Kairanda, M, Habermann, S, Naik, C. Theobalt and V. Golyanik.

Cvpr 2025 Thin Shell Sft - Detailed Analysis & Overview

Paper Abstract: 3D reconstruction of highly deformable surfaces (e.g. cloths) from monocular RGB videos is a challenging ... Single-image human mesh recovery is a challenging task due to the ill-posed nature of simultaneous body shape, pose, and ... N, Kairanda, M, Habermann, S, Naik, C. Theobalt and V. Golyanik. In this video, we present our work, SAT-HMR: Real-Time Multi-Person 3D Mesh Estimation via Scale-Adaptive Tokens. Project ... Abstract: We present WildGS-SLAM, a robust and efficient monocular RGB SLAM system designed to handle dynamic ... "Scaling up Autonomous Driving via Large Foundation Models" Talk given at the

N. Kairanda, E. Tretschk, E. Elgharib, C. Theobalt and V. Golyanik. φ- 00:00 Session Introduction Friday, November 28 2:30 PM ~ 4:00 PM Main Arena Moderator(s): Hyo-Soo Kim, Satoru Otsuji ...

Photo Gallery

Thin-Shell-SfT.  In CVPR, 2025
(CVPR 2025) BLADE: Single-view Body Mesh Estimation through Accurate Depth Estimation
[CVPR 2025] Thin-Shell-SfT: Fine-Grained Monocular Non-rigid 3D Surface Tracking with NDFs
[CVPR 2025] SAT-HMR: Real-Time Multi-Person 3D Mesh Estimation via Scale-Adaptive Tokens
[CVPR 2025] Augmented Unseen Region Alignment for Reference-based 360° Unbounded Scene Inpainting
[CVPR 2025] WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments
[CVPR'25] Keynote - Xianming Liu, XPeng
[CVPR 2022] φ-SfT: Shape-from-Template with a Physics-Based Deformation Model
[COMPLEX PCI 2025] Live Case 4: CTO
🛹 RollingDepth: Video Depth without Video Models (CVPR 2025)
CVPR 2025 presentation-3D Student Splatting and Scooping (Best Paper Honorable Mention)
CVPR 2026 Best Papers Explained: 3D AI, Video Reasoning, Agents & Open Vision Models
View Detailed Profile
Thin-Shell-SfT.  In CVPR, 2025

Thin-Shell-SfT. In CVPR, 2025

Paper Abstract: 3D reconstruction of highly deformable surfaces (e.g. cloths) from monocular RGB videos is a challenging ...

(CVPR 2025) BLADE: Single-view Body Mesh Estimation through Accurate Depth Estimation

(CVPR 2025) BLADE: Single-view Body Mesh Estimation through Accurate Depth Estimation

Single-image human mesh recovery is a challenging task due to the ill-posed nature of simultaneous body shape, pose, and ...

[CVPR 2025] Thin-Shell-SfT: Fine-Grained Monocular Non-rigid 3D Surface Tracking with NDFs

[CVPR 2025] Thin-Shell-SfT: Fine-Grained Monocular Non-rigid 3D Surface Tracking with NDFs

N, Kairanda, M, Habermann, S, Naik, C. Theobalt and V. Golyanik.

[CVPR 2025] SAT-HMR: Real-Time Multi-Person 3D Mesh Estimation via Scale-Adaptive Tokens

[CVPR 2025] SAT-HMR: Real-Time Multi-Person 3D Mesh Estimation via Scale-Adaptive Tokens

In this video, we present our work, SAT-HMR: Real-Time Multi-Person 3D Mesh Estimation via Scale-Adaptive Tokens. Project ...

[CVPR 2025] Augmented Unseen Region Alignment for Reference-based 360° Unbounded Scene Inpainting

[CVPR 2025] Augmented Unseen Region Alignment for Reference-based 360° Unbounded Scene Inpainting

Project Page: https://kkennethwu.github.io/aurafusion360 Paper: https://arxiv.org/abs/2502.05176 Code: ...

[CVPR 2025] WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments

[CVPR 2025] WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments

Abstract: We present WildGS-SLAM, a robust and efficient monocular RGB SLAM system designed to handle dynamic ...

[CVPR'25] Keynote - Xianming Liu, XPeng

[CVPR'25] Keynote - Xianming Liu, XPeng

"Scaling up Autonomous Driving via Large Foundation Models" Talk given at the

[CVPR 2022] φ-SfT: Shape-from-Template with a Physics-Based Deformation Model

[CVPR 2022] φ-SfT: Shape-from-Template with a Physics-Based Deformation Model

N. Kairanda, E. Tretschk, E. Elgharib, C. Theobalt and V. Golyanik. φ-

[COMPLEX PCI 2025] Live Case 4: CTO

[COMPLEX PCI 2025] Live Case 4: CTO

00:00 Session Introduction Friday, November 28 2:30 PM ~ 4:00 PM Main Arena Moderator(s): Hyo-Soo Kim, Satoru Otsuji ...

🛹 RollingDepth: Video Depth without Video Models (CVPR 2025)

🛹 RollingDepth: Video Depth without Video Models (CVPR 2025)

[

CVPR 2025 presentation-3D Student Splatting and Scooping (Best Paper Honorable Mention)

CVPR 2025 presentation-3D Student Splatting and Scooping (Best Paper Honorable Mention)

Our

CVPR 2026 Best Papers Explained: 3D AI, Video Reasoning, Agents & Open Vision Models

CVPR 2026 Best Papers Explained: 3D AI, Video Reasoning, Agents & Open Vision Models

A visual tour of 19

[CVPR 2025] 🍳 PanSplat (Full video)

[CVPR 2025] 🍳 PanSplat (Full video)

CVPR 2025