04:00
2026-07-24
arxiv.org
computer-vision
Axolotl3D: a Unified Framework for Faithful 3D Shape Completion
Axolotl3D, a multi-modal and occlusion-aware 3D generation model introduced in arXiv:2607.20660v1, jointly conditions on images, visibility masks, camera parameters, and a partial point cloud to enabl…