English
Related papers

Related papers: VLM-Guided Group Preference Alignment for Diffusio…

200 papers

Multi-person human mesh recovery (HMR) consists in detecting all individuals in a given input image, and predicting the body shape, pose, and 3D location for each detected person. The dominant approaches to this task rely on neural networks…

Computer Vision and Pattern Recognition · Computer Science 2025-06-05 Brégier Romain , Baradel Fabien , Lucas Thomas , Galaaoui Salma , Armando Matthieu , Weinzaepfel Philippe , Rogez Grégory

Preference optimization for diffusion models aims to align them with human preferences for images. Previous methods typically use Vision-Language Models (VLMs) as pixel-level reward models to approximate human preferences. However, when…

Computer Vision and Pattern Recognition · Computer Science 2025-10-03 Tao Zhang , Cheng Da , Kun Ding , Huan Yang , Kun Jin , Yan Li , Tingting Gao , Di Zhang , Shiming Xiang , Chunhong Pan

Common image editing tasks typically adopt powerful generative diffusion models as the leading paradigm for real-world content editing. Meanwhile, although reinforcement learning (RL) methods such as Diffusion-DPO and Flow-GRPO have further…

Computer Vision and Pattern Recognition · Computer Science 2026-04-22 Fan Li , Chonghuinan Wang , Lina Lei , Yuping Qiu , Jiaqi Xu , Jiaxiu Jiang , Xinran Qin , Zhikai Chen , Fenglong Song , Zhixin Wang , Renjing Pei , Wangmeng Zuo

Human Mesh Recovery (HMR) from a single RGB image is a highly ambiguous problem, as an infinite set of 3D interpretations can explain the 2D observation equally well. Nevertheless, most HMR methods overlook this issue and make a single…

Computer Vision and Pattern Recognition · Computer Science 2025-03-19 Guénolé Fiche , Simon Leglaive , Xavier Alameda-Pineda , Francesc Moreno-Noguer

In this work, we address a challenge in video inpainting: reconstructing occluded regions in dynamic, real-world scenarios. Motivated by the need for continuous human motion monitoring in healthcare settings, where facial features are…

Computer Vision and Pattern Recognition · Computer Science 2024-12-02 Zheyan Zhang , Diego Klabjan , Renee CB Manworren

Current mainstream methods of aligning diffusion models with human preferences typically employ VLM-based reward models. However, these reward models, pre-trained for semantic alignment, struggle to capture the essential perceptual…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Jaxon Zhang , Binxin Yang , Hubery Yin , Chen Li , Jing Lyu

RLHF techniques like DPO can significantly improve the generation quality of text-to-image diffusion models. However, these methods optimize for a single reward that aligns model generation with population-level preferences, neglecting the…

Machine Learning · Computer Science 2025-01-14 Meihua Dang , Anikait Singh , Linqi Zhou , Stefano Ermon , Jiaming Song

In this paper, we make the first attempt to align diffusion models for image inpainting with human aesthetic standards via a reinforcement learning framework, significantly improving the quality and visual appeal of inpainted images.…

Computer Vision and Pattern Recognition · Computer Science 2024-11-05 Kendong Liu , Zhiyu Zhu , Chuanhao Li , Hui Liu , Huanqiang Zeng , Junhui Hou

Text-to-image diffusion models are a class of deep generative models that have demonstrated an impressive capacity for high-quality image generation. However, these models are susceptible to implicit biases that arise from web-scale…

Computer Vision and Pattern Recognition · Computer Science 2024-01-24 Yinan Zhang , Eric Tzeng , Yilun Du , Dmitry Kislyuk

Recent years have witnessed a trend of the deep integration of the generation and reconstruction paradigms. In this paper, we extend the ability of controllable generative models for a more comprehensive hand mesh recovery task: direct hand…

Computer Vision and Pattern Recognition · Computer Science 2024-06-04 Mengcheng Li , Hongwen Zhang , Yuxiang Zhang , Ruizhi Shao , Tao Yu , Yebin Liu

In-bed human mesh recovery can be crucial and enabling for several healthcare applications, including sleep pattern monitoring, rehabilitation support, and pressure ulcer prevention. However, it is difficult to collect large real-world…

Computer Vision and Pattern Recognition · Computer Science 2025-04-07 Jing Gao , Ce Zheng , Laszlo A. Jeni , Zackory Erickson

Human mesh recovery (HMR) is crucial in many computer vision applications; from health to arts and entertainment. HMR from monocular images has predominantly been addressed by deterministic methods that output a single prediction for a…

Computer Vision and Pattern Recognition · Computer Science 2024-12-20 Muhammad Usama Saleem , Ekkasit Pinyoanuntapong , Pu Wang , Hongfei Xue , Srijan Das , Chen Chen

This paper studies full-body 3D human motion recovery from head-mounted device signals. Existing diffusion-based methods often rely on global distribution matching, leading to local joint reconstruction errors. We propose MotionGRPO, a…

Computer Vision and Pattern Recognition · Computer Science 2026-05-13 Nanjie Yao , Junlong Ren , Wenhao Shen , Hao Wang

Human preference alignment presents a critical yet underexplored challenge for diffusion models in text-to-3D generation. Existing solutions typically require task-specific fine-tuning, posing significant hurdles in data-scarce 3D domains.…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Jiaqi Leng , Shuyuan Tu , Haidong Cao , Sicheng Xie , Daoguo Dong , Zuxuan Wu , Yu-Gang Jiang

Text-driven person image generation is an emerging and challenging task in cross-modality image generation. Controllable person image generation promotes a wide range of applications such as digital human interaction and virtual try-on.…

Computer Vision and Pattern Recognition · Computer Science 2022-11-14 Kaiduo Zhang , Muyi Sun , Jianxin Sun , Binghao Zhao , Kunbo Zhang , Zhenan Sun , Tieniu Tan

Evaluating text-to-image generation models requires alignment with human perception, yet existing human-centric metrics are constrained by limited data coverage, suboptimal feature extraction, and inefficient loss functions. To address…

Computer Vision and Pattern Recognition · Computer Science 2025-08-25 Yuhang Ma , Yunhao Shui , Xiaoshi Wu , Keqiang Sun , Hongsheng Li

Sequential decision-making is desired to align with human intents and exhibit versatility across various tasks. Previous methods formulate it as a conditional generation process, utilizing return-conditioned diffusion models to directly…

Machine Learning · Computer Science 2024-10-11 Xudong Yu , Chenjia Bai , Haoran He , Changhong Wang , Xuelong Li

We consider the problem of estimating a parametric model of 3D human mesh from a single image. While there has been substantial recent progress in this area with direct regression of model parameters, these methods only implicitly exploit…

Computer Vision and Pattern Recognition · Computer Science 2020-07-15 Georgios Georgakis , Ren Li , Srikrishna Karanam , Terrence Chen , Jana Kosecka , Ziyan Wu

Human mesh recovery (HMR) models 3D human body from monocular videos, with recent works extending it to world-coordinate human trajectory and motion reconstruction. However, most existing methods remain offline, relying on future frames or…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Yiwen Zhao , Ce Zheng , Yufu Wang , Hsueh-Han Daniel Yang , Liting Wen , Laszlo A. Jeni

Conventional approaches to human mesh recovery predominantly employ a region-based strategy. This involves initially cropping out a human-centered region as a preprocessing step, with subsequent modeling focused on this zoomed-in image.…

Computer Vision and Pattern Recognition · Computer Science 2024-02-27 Zeyu Wang , Zhenzhen Weng , Serena Yeung-Levy