From the 1 of 4 linked papers with an AI index.
4 papers
ViP-Rig: Visual-Prompted Controllable Rigging
Zihan Qin, Mingze Sun, Yifan Mao +6
ViP-Rig is a framework that lets users control 3D rigging by providing 2D visual prompts, enabling both initial skeleton creation and later editing of skeletons and skinning weight…
Velocity-Space 3D Asset Editing
Hao Liu, Yuxuan Lin, Jingfeng Guo +4
Editing a 3D asset locally, modifying a target region while preserving the rest, is a fundamental requirement of native 3D editing. Existing methods enforce locality through mechan…
Mesh-RFT: Enhancing Mesh Generation via Fine-grained Reinforcement Fine-Tuning
Jian Liu, Jing Xu, Song Guo +10
Existing pretrained models for 3D mesh generation often suffer from data biases and produce low-quality results, while global reinforcement learning (RL) methods rely on object-lev…
Auto-Connect: Connectivity-Preserving RigFormer with Direct Preference Optimization
Jingfeng Guo, Jian Liu, Jinnan Chen +9
We introduce Auto-Connect, a novel approach for automatic rigging that explicitly preserves skeletal connectivity through a connectivity-preserving tokenization scheme. Unlike prev…