VLM-Guided Group Preference Alignment for Diffusion-based Human Mesh Recovery
This work addresses the problem of inaccurate and implausible mesh predictions in human mesh recovery for applications in computer vision, though it is incremental as it builds on existing diffusion-based methods.
The paper tackles the ambiguity in human mesh recovery from single RGB images by introducing a group preference alignment framework that uses a critique agent to score predicted meshes for physical plausibility and image consistency, resulting in superior performance compared to state-of-the-art methods.
Human mesh recovery (HMR) from a single RGB image is inherently ambiguous, as multiple 3D poses can correspond to the same 2D observation. Recent diffusion-based methods tackle this by generating various hypotheses, but often sacrifice accuracy. They yield predictions that are either physically implausible or drift from the input image, especially under occlusion or in cluttered, in-the-wild scenes. To address this, we introduce a dual-memory augmented HMR critique agent with self-reflection to produce context-aware quality scores for predicted meshes. These scores distill fine-grained cues about 3D human motion structure, physical feasibility, and alignment with the input image. We use these scores to build a group-wise HMR preference dataset. Leveraging this dataset, we propose a group preference alignment framework for finetuning diffusion-based HMR models. This process injects the rich preference signals into the model, guiding it to generate more physically plausible and image-consistent human meshes. Extensive experiments demonstrate that our method achieves superior performance compared to state-of-the-art approaches.