CVAIMar 5

RelaxFlow: Text-Driven Amodal 3D Generation

arXiv:2603.05425v1
Originality Incremental advance
AI Analysis

This work addresses the semantic ambiguity under occlusion in image-to-3D generation, which is a problem for anyone trying to create complete 3D models from partial observations.

This paper tackles the problem of text-driven amodal 3D generation, where text prompts guide the completion of occluded regions while strictly preserving observed parts. They propose RelaxFlow, a training-free dual-branch framework that successfully steers the generation of unseen regions to match the prompt intent without compromising visual fidelity.

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 relaxation is equivalent to applying a low-pass filter on the generative vector field, which suppresses high-frequency instance details to isolate geometric structure that accommodates the observation. To facilitate evaluation, we introduce two diagnostic benchmarks, ExtremeOcc-3D and AmbiSem-3D. Extensive experiments demonstrate that RelaxFlow successfully steers the generation of unseen regions to match the prompt intent without compromising visual fidelity.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes