paper-with-me

홈 › Papers

VLM-Guided Group Preference Alignment for Diffusion-based Human Mesh Recovery

2026-02-22 · Wenhao Shen, Hao Wang, Wanqi Yin, Fayao Liu, Xulei Yang, Chao Liang, Zhongang Cai, Guosheng Lin arxiv

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.

📄 PDF Abstract BibTeX arXiv:2602.19180

Code (0)

등록된 구현이 없습니다.

Tasks

Human Mesh Recovery

Similar Papers 제목 키워드 기반

PC-Diffusion: Aligning Diffusion Models with Human Preferences via Preference Classifier

2025-11-11 · Shaomeng Wang, He Wang, Xiaolu Wei, Longquan Dai 외 arxiv

Diffusion models have achieved remarkable success in conditional image generation, yet their outputs often remain misaligned with human preferences. To address this, recent work has applied Direct Preference Optimization…

Conditional Image Generation

Towards General Preference Alignment: Diffusion Models at Nash Equilibrium

2026-05-06 · Jiaming Hu, Jiamu Bai, Haoyu Wang, Debarghya Mukherjee 외 arxiv

Reinforcement learning from human feedback (RLHF) has been popular for aligning text-to-image (T2I) diffusion models with human preferences. As a mainstream branch of RLHF, Direct Preference Optimization (DPO) offers a c…

Text-to-Image GenerationReinforcement Learning

Enhancing Diffusion-based Unrestricted Adversarial Attacks via Adversary Preferences Alignment

2025-06-02 · Kaixun Jiang, Zhaoyu Chen, Haijing Guo, Jinglun Li 외

Preference alignment in diffusion models has primarily focused on benign human preferences (e.g., aesthetic). In this paper, we propose a novel perspective: framing unrestricted adversarial example generation as a proble…

GEM: Generative Entropy-Guided Preference Modeling for Few-shot Alignment of LLMs

2025-11-17 · Yiyang Zhao, Huiyu Bai, Xuejiao Zhao arxiv

Alignment of large language models (LLMs) with human preferences typically relies on supervised reward models or external judges that demand abundant annotations. However, in fields that rely on professional knowledge, s…

Mathematical ReasoningDecision Making

Instant Preference Alignment for Text-to-Image Diffusion Models

2025-08-25 · Yang Li, Songlin Yang, Xiaoxuan Han, Wei Wang 외 arxiv

Text-to-image (T2I) generation has greatly enhanced creative expression, yet achieving preference-aligned generation in a real-time and training-free manner remains challenging. Previous methods often rely on static, pre…

Image Generation