中文
相关论文

相关论文: HumanRefiner: Benchmarking Abnormal Human Generati…

200 篇论文

This report reviews recent advancements in human motion prediction, reconstruction, and generation. Human motion prediction focuses on forecasting future poses and movements from historical data, addressing challenges like nonlinear…

计算机视觉与模式识别 · 计算机科学 2025-02-25 Canxuan Gang , Yiran Wang

Diffusion models have gained significant popularity in the field of image-to-image translation. Previous efforts applying diffusion models to image super-resolution (SR) have demonstrated that iteratively refining pure Gaussian noise using…

计算机视觉与模式识别 · 计算机科学 2023-07-04 Axi Niu , Pham Xuan Trung , Kang Zhang , Jinqiu Sun , Yu Zhu , In So Kweon , Yanning Zhang

Generative modeling is widely regarded as one of the most essential problems in today's AI community, with text-to-image generation having gained unprecedented real-world impacts. Among various approaches, diffusion models have achieved…

计算机视觉与模式识别 · 计算机科学 2026-01-26 Xuyang Guo , Jiayan Huo , Yingyu Liang , Zhenmei Shi , Zhao Song , Jiahao Zhang , Zhen Zhuang

The rapid progress of text-to-image diffusion models raises significant concerns regarding the unauthorized reproduction of trademarked content. While prior work targets general concepts (e.g., styles, celebrities), it fails to address…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Dawid Malarz , Filip Manjak , Maciej Zięba , Przemysław Spurek , Artur Kasymov

Personalized image generation, where reference images of one or more subjects are used to generate their image according to a scene description, has gathered significant interest in the community. However, such generated images suffer from…

计算机视觉与模式识别 · 计算机科学 2025-07-23 Parul Gupta , Abhinav Dhall , Thanh-Toan Do

We present a comprehensive solution to learn and improve text-to-image models from human preference feedback. To begin with, we build ImageReward -- the first general-purpose text-to-image human preference reward model -- to effectively…

计算机视觉与模式识别 · 计算机科学 2023-12-29 Jiazheng Xu , Xiao Liu , Yuchen Wu , Yuxuan Tong , Qinkai Li , Ming Ding , Jie Tang , Yuxiao Dong

This study assesses the ability of Large Vision-Language Models (LVLMs) to differentiate between AI-generated and human-generated images. It introduces a new automated benchmark construction method for this evaluation. The experiment…

计算机视觉与模式识别 · 计算机科学 2025-11-21 Haokun Zhou , Yipeng Hong

Recent advancements in text-to-image (T2I) models enable high-quality image synthesis, yet generating anatomically accurate human figures remains challenging. AI-generated images frequently exhibit distortions such as proliferated limbs,…

计算机视觉与模式识别 · 计算机科学 2025-03-04 Lu Ma , Kaibo Cao , Hao Liang , Jiaxin Lin , Zhuang Li , Yuhong Liu , Jihong Zhang , Wentao Zhang , Bin Cui

Diffusion models for garment-centric human generation from text or image prompts have garnered emerging attention for their great application potential. However, existing methods often face a dilemma: lightweight approaches, such as…

计算机视觉与模式识别 · 计算机科学 2025-01-22 Ente Lin , Xujie Zhang , Fuwei Zhao , Yuxuan Luo , Xin Dong , Long Zeng , Xiaodan Liang

Human image editing includes tasks like changing a person's pose, their clothing, or editing the image according to a text prompt. However, prior work often tackles these tasks separately, overlooking the benefit of mutual reinforcement…

计算机视觉与模式识别 · 计算机科学 2024-04-02 Nannan Li , Qing Liu , Krishna Kumar Singh , Yilin Wang , Jianming Zhang , Bryan A. Plummer , Zhe Lin

Recently, regression-based methods have dominated the field of 3D human pose and shape estimation. Despite their promising results, a common issue is the misalignment between predictions and image observations, often caused by minor joint…

计算机视觉与模式识别 · 计算机科学 2024-03-19 Tom Wehrbein , Bodo Rosenhahn , Iain Matthews , Carsten Stoll

Recently, diffusion models have shown their impressive ability in visual generation tasks. Besides static images, more and more research attentions have been drawn to the generation of realistic videos. The video generation not only has a…

计算机视觉与模式识别 · 计算机科学 2025-11-03 Yucheng Xing , Jinxing Yin , Xiaodong Liu

Medical image segmentation models struggle with rare abnormalities due to scarce annotated pathological data. We propose DiffAug a novel framework that combines textguided diffusion-based generation with automatic segmentation validation to…

计算机视觉与模式识别 · 计算机科学 2025-08-26 Maham Nazir , Muhammad Aqeel , Francesco Setti

This work focuses on the problem of reconstructing a 3D human body mesh from a given 2D image. Despite the inherent ambiguity of the task of human mesh recovery, most existing works have adopted a method of regressing a single output. In…

计算机视觉与模式识别 · 计算机科学 2023-08-21 Hanbyel Cho , Junmo Kim

Existing methods for image-to-3D avatar generation struggle to produce highly detailed, animation-ready avatars suitable for real-world applications. We introduce AdaHuman, a novel framework that generates high-fidelity animatable 3D…

计算机视觉与模式识别 · 计算机科学 2025-06-02 Yangyi Huang , Ye Yuan , Xueting Li , Jan Kautz , Umar Iqbal

We present CosmicMan, a text-to-image foundation model specialized for generating high-fidelity human images. Unlike current general-purpose foundation models that are stuck in the dilemma of inferior quality and text-image misalignment for…

计算机视觉与模式识别 · 计算机科学 2024-04-02 Shikai Li , Jianglin Fu , Kaiyuan Liu , Wentao Wang , Kwan-Yee Lin , Wayne Wu

Evaluating the quality of automatically generated image descriptions is a complex task that requires metrics capturing various dimensions, such as grammaticality, coverage, accuracy, and truthfulness. Although human evaluation provides…

计算机视觉与模式识别 · 计算机科学 2024-11-11 Jia-Hong Huang , Hongyi Zhu , Yixian Shen , Stevan Rudinac , Evangelos Kanoulas

Training object detectors demands extensive, task-specific annotations, yet this requirement becomes impractical in UAV-based human detection due to constantly shifting target distributions and the scarcity of labeled images. As a remedy,…

计算机视觉与模式识别 · 计算机科学 2026-03-25 Wenda Li , Meng Wu , Liangzhao Chen , Sungmin Eum , Heesung Kwon , Qing Qu

The pose-guided person image generation task requires synthesizing photorealistic images of humans in arbitrary poses. The existing approaches use generative adversarial networks that do not necessarily maintain realistic textures or need…

计算机视觉与模式识别 · 计算机科学 2023-03-02 Ankan Kumar Bhunia , Salman Khan , Hisham Cholakkal , Rao Muhammad Anwer , Jorma Laaksonen , Mubarak Shah , Fahad Shahbaz Khan

Human pose estimation is a fundamental yet challenging task in computer vision, which aims at localizing human anatomical keypoints. However, unlike human vision that is robust to various data corruptions such as blur and pixelation,…

计算机视觉与模式识别 · 计算机科学 2021-05-14 Jiahang Wang , Sheng Jin , Wentao Liu , Weizhong Liu , Chen Qian , Ping Luo