RelaxFlow: Text-Driven Amodal 3D Generation
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 granularities: rigid control for the observation versus relaxed structural control for the prompt. To this end, we propose RelaxFlow, a training-free dual-branch framework that decouples control granularity via a Multi-Prior Consensus Module and a Relaxation Mechanism. Theoretically, we prove that our rel...
| Authors | Jiayin Zhu, Guoji Fu, Xiaolu Liu et al. |
|---|---|
| Primary category | cs.CV |
| Published | 5 March 2026 |
| Last updated at source | 27 May 2026 |
Models and datasets referencing this paper
- KayZhu/ExtremeOcc-3DDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.