RelaxFlow: Text-Driven Amodal 3D Generation 事件

RelaxFlow: Text-Driven Amodal 3D Generation arXiv:2603.05425v2 Announce Type: replace Abstract: Image-to-3D generation faces inherent semantic ambiguity under occlusion, where partial observation alone is often insufficient to determine object category. In this work, we formalize text-driven amodal 3D generation, where text prompts steer the completion of unseen regions while strictly preserving input observation. Crucially, we identify that these objectives demand distinct control granularitie