Media Summary: Project Page: Abstract: Estimating camera pose in dynamic environments is a critical challenge, as most ... This is a presentation video of the paper: "SplineGS: Robust Motion-Adaptive Spline for Real-Time Dynamic 3D Gaussians from ... This is a 5-minute presentation of the work: Semantic Draw ✍️: Towards Real-Time Interactive Content Creation from Image ...

Cvpr 2025 Robopepp - Detailed Analysis & Overview

Project Page: Abstract: Estimating camera pose in dynamic environments is a critical challenge, as most ... This is a presentation video of the paper: "SplineGS: Robust Motion-Adaptive Spline for Real-Time Dynamic 3D Gaussians from ... This is a 5-minute presentation of the work: Semantic Draw ✍️: Towards Real-Time Interactive Content Creation from Image ... Paper Abstract: We present BimArt, a novel generative approach for synthesizing 3D bimanual hand interactions with articulated ... Re-HOLD: Video Hand Object Interaction Reenactment via Adaptive Layout-instructed Diffusion Model. Given a driving video and ...

Photo Gallery

[CVPR 2025] RoboPEPP
CVPR 2025 Highlights: AI, Computer Vision, and What’s Next
[CVPR 2026] WildPose: A Unified Framework for Robust Pose Estimation in the Wild
[CVPR 2025] SplineGS: Robust Motion-Adaptive Spline (...) from Monocular Video
[CVPR 2025] Reloc3r
[CVPR 2025] Semantic Draw Presentation (5 min)
CVPR 2025: Estimating Body and Hand Motion in an Ego-sensed World
[CVPR 2025] Augmented Unseen Region Alignment for Reference-based 360° Unbounded Scene Inpainting
CVPR 2025 Highlight: Parallelized Autoregressive Visual Generation.
[CVPR 2026] PoseGAM: Robust Unseen Object Pose Estimation via Geometry-Aware Multi-View Reasoning
🛹 RollingDepth: Video Depth without Video Models (CVPR 2025)
BimArt. In CVPR, 2025
Sponsored
View Detailed Profile
[CVPR 2025] RoboPEPP

[CVPR 2025] RoboPEPP

Title:

CVPR 2025 Highlights: AI, Computer Vision, and What’s Next

CVPR 2025 Highlights: AI, Computer Vision, and What’s Next

Experience

[CVPR 2026] WildPose: A Unified Framework for Robust Pose Estimation in the Wild

[CVPR 2026] WildPose: A Unified Framework for Robust Pose Estimation in the Wild

Project Page: https://wildpose.github.io/ Abstract: Estimating camera pose in dynamic environments is a critical challenge, as most ...

[CVPR 2025] SplineGS: Robust Motion-Adaptive Spline (...) from Monocular Video

[CVPR 2025] SplineGS: Robust Motion-Adaptive Spline (...) from Monocular Video

This is a presentation video of the paper: "SplineGS: Robust Motion-Adaptive Spline for Real-Time Dynamic 3D Gaussians from ...

[CVPR 2025] Reloc3r

[CVPR 2025] Reloc3r

This is a video presentation for our

Sponsored
[CVPR 2025] Semantic Draw Presentation (5 min)

[CVPR 2025] Semantic Draw Presentation (5 min)

This is a 5-minute presentation of the work: Semantic Draw ✍️: Towards Real-Time Interactive Content Creation from Image ...

CVPR 2025: Estimating Body and Hand Motion in an Ego-sensed World

CVPR 2025: Estimating Body and Hand Motion in an Ego-sensed World

CVPR 2025

[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 Highlight: Parallelized Autoregressive Visual Generation.

CVPR 2025 Highlight: Parallelized Autoregressive Visual Generation.

Project page: https://yuqingwang1029.github.io/PAR-project/, Code: https://github.com/YuqingWang1029/PAR.

[CVPR 2026] PoseGAM: Robust Unseen Object Pose Estimation via Geometry-Aware Multi-View Reasoning

[CVPR 2026] PoseGAM: Robust Unseen Object Pose Estimation via Geometry-Aware Multi-View Reasoning

Presentation for

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

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

[

BimArt. In CVPR, 2025

BimArt. In CVPR, 2025

Paper Abstract: We present BimArt, a novel generative approach for synthesizing 3D bimanual hand interactions with articulated ...

CVPR 2025 Re-HOLD

CVPR 2025 Re-HOLD

Re-HOLD: Video Hand Object Interaction Reenactment via Adaptive Layout-instructed Diffusion Model. Given a driving video and ...