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 ... In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2026. Authors: Yunxiang Peng, Mengmeng ... Reinforcement Learning (RL) has achieved remarkable success in various domains, yet it often relies on carefully designed ... [CVPR 2026] VGent: Visual Grounding via Modular Design for Disentangling Reasoning and Prediction