Media Summary: Abstract: Multi-modal 3D object understanding has gained significant attention, yet current approaches often rely on rigid ... DTGBrepGen is a novel framework that sequentially generates topologically valid and geometrically high-quality B-rep models. This is an oral presentation for the paper "Hierarchical Point-Patch Fusion with Adaptive Patch Codebook for 3D Shape Anomaly ...

Cvpr 2025 Partgen Part Level - Detailed Analysis & Overview

Abstract: Multi-modal 3D object understanding has gained significant attention, yet current approaches often rely on rigid ... DTGBrepGen is a novel framework that sequentially generates topologically valid and geometrically high-quality B-rep models. This is an oral presentation for the paper "Hierarchical Point-Patch Fusion with Adaptive Patch Codebook for 3D Shape Anomaly ...

Photo Gallery

[CVPR 2025] PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Models
[CVPR 2025, Highlight] CrossOver: 3D Scene Cross-Modal Alignment
[CVPR 2025] Reloc3r
CVPR 2026: Spectral Scalpel for Skeleton-Based Action Segmentation
CVPR 2025: WonderWorld: Interactive 3D Scene Generation from a Single Image
CVPR 2026 paper of PL-Stitch
DTGBrepGen (CVPR 2025)
[CVPR 2025] Augmented Unseen Region Alignment for Reference-based 360° Unbounded Scene Inpainting
[CVPR 2025] 🍳 PanSplat (Full video)
[CVPR 2026 Highlight] UniPart: Part-Level 3D Generation with Unified 3D Geom-Seg Latents
CVPR 2025: GAF: Gaussian Avatar Reconstruction from Monocular Videos via Multi-view Diffusion
CVPR 2025 Enhancing 3D Gaze Estimation in the Wild using Weak Supervision with Gaze Following Labels
View Detailed Profile
[CVPR 2025] PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Models

[CVPR 2025] PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Models

In this work, we introduce

[CVPR 2025, Highlight] CrossOver: 3D Scene Cross-Modal Alignment

[CVPR 2025, Highlight] CrossOver: 3D Scene Cross-Modal Alignment

Abstract: Multi-modal 3D object understanding has gained significant attention, yet current approaches often rely on rigid ...

[CVPR 2025] Reloc3r

[CVPR 2025] Reloc3r

This is a video presentation for our

CVPR 2026: Spectral Scalpel for Skeleton-Based Action Segmentation

CVPR 2026: Spectral Scalpel for Skeleton-Based Action Segmentation

This video is an explanation of

CVPR 2025: WonderWorld: Interactive 3D Scene Generation from a Single Image

CVPR 2025: WonderWorld: Interactive 3D Scene Generation from a Single Image

CVPR 2025

CVPR 2026 paper of PL-Stitch

CVPR 2026 paper of PL-Stitch

CVPR

DTGBrepGen (CVPR 2025)

DTGBrepGen (CVPR 2025)

DTGBrepGen is a novel framework that sequentially generates topologically valid and geometrically high-quality B-rep models.

[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] 🍳 PanSplat (Full video)

[CVPR 2025] 🍳 PanSplat (Full video)

CVPR 2025

[CVPR 2026 Highlight] UniPart: Part-Level 3D Generation with Unified 3D Geom-Seg Latents

[CVPR 2026 Highlight] UniPart: Part-Level 3D Generation with Unified 3D Geom-Seg Latents

Demo for UniPart:

CVPR 2025: GAF: Gaussian Avatar Reconstruction from Monocular Videos via Multi-view Diffusion

CVPR 2025: GAF: Gaussian Avatar Reconstruction from Monocular Videos via Multi-view Diffusion

CVPR 2025

CVPR 2025 Enhancing 3D Gaze Estimation in the Wild using Weak Supervision with Gaze Following Labels

CVPR 2025 Enhancing 3D Gaze Estimation in the Wild using Weak Supervision with Gaze Following Labels

CVPR 2025

CVPR2026 Hierarchical Point-Patch Fusion with Adaptive Patch Codebook for 3D Shape Anomaly Detection

CVPR2026 Hierarchical Point-Patch Fusion with Adaptive Patch Codebook for 3D Shape Anomaly Detection

This is an oral presentation for the paper "Hierarchical Point-Patch Fusion with Adaptive Patch Codebook for 3D Shape Anomaly ...