中文
相关论文

相关论文: ArtHOI: Taming Foundation Models for Monocular 4D …

200 篇论文

Synthesizing physically plausible articulated human-object interactions (HOI) without 3D/4D supervision remains a fundamental challenge. While recent zero-shot approaches leverage video diffusion models to synthesize human-object…

计算机视觉与模式识别 · 计算机科学 2026-03-05 Zihao Huang , Tianqi Liu , Zhaoxi Chen , Shaocong Xu , Saining Zhang , Lixing Xiao , Zhiguo Cao , Wei Li , Hao Zhao , Ziwei Liu

Our work aims to reconstruct hand-object interactions from a single-view image, which is a fundamental but ill-posed task. Unlike methods that reconstruct from videos, multi-view images, or predefined 3D templates, single-view…

计算机视觉与模式识别 · 计算机科学 2025-12-22 Yumeng Liu , Xiaoxiao Long , Zemin Yang , Yuan Liu , Marc Habermann , Christian Theobalt , Yuexin Ma , Wenping Wang

Most RGB-based hand-object reconstruction methods rely on object templates, while template-free methods typically assume full object visibility. This assumption often breaks in real-world settings, where fixed camera viewpoints and static…

计算机视觉与模式识别 · 计算机科学 2025-08-08 Shibo Wang , Haonan He , Maria Parelli , Christoph Gebhardt , Zicong Fan , Jie Song

Recovering 4D human-object interaction (HOI) from monocular video is a key step toward scalable 3D content creation, embodied AI, and simulation-based learning. Recent methods can reconstruct temporally coherent human and object…

计算机视觉与模式识别 · 计算机科学 2026-05-15 Yubo Zhao , Yujin Chai , Yunao Dong , Chengfeng Zhao , Zijiao Zeng , Yuan Liu , Chi-Keung Tang

The ubiquity of monocular videos capturing daily hand-object interactions presents a valuable resource for embodied intelligence. While 3D hand reconstruction from in-the-wild videos has seen significant progress, reconstructing the…

计算机视觉与模式识别 · 计算机科学 2026-02-09 Yuantao Chen , Jiahao Chang , Chongjie Ye , Chaoran Zhang , Zhaojie Fang , Chenghong Li , Xiaoguang Han

Understanding and synthesizing realistic 3D hand-object interactions (HOI) is critical for applications ranging from immersive AR/VR to dexterous robotics. Existing methods struggle with generalization, performing well on closed-set objects…

计算机视觉与模式识别 · 计算机科学 2025-12-23 Zhenhao Zhang , Ye Shi , Lingxiao Yang , Suting Ni , Qi Ye , Jingya Wang

In 3D hand-object interaction (HOI) tasks, estimating precise joint poses of hands and objects from monocular RGB input remains highly challenging due to the inherent geometric ambiguity of RGB images and the severe mutual occlusions that…

计算机视觉与模式识别 · 计算机科学 2025-07-21 Yuechen Xie , Haobo Jiang , Jian Yang , Yigong Zhang , Jin Xie

Generalized robots must learn from diverse, large-scale human-object interactions (HOI) to operate robustly in the real world. Monocular internet videos offer a nearly limitless and readily available source of data, capturing an…

计算机视觉与模式识别 · 计算机科学 2026-03-20 Boran Wen , Ye Lu , Sirui Wang , Keyan Wan , Jiahong Zhou , Junxuan Liang , Xinpeng Liu , Bang Xiao , Ruiyang Liu , Yong-Lu Li

Human-Object Interaction (HOI) video reenactment with realistic motion remains a frontier in expressive digital human creation. Existing approaches primarily handle simple image-plane motion (e.g., in-plane translations), struggling with…

Reconstructing 3D models of dynamic, real-world objects with high-fidelity textures from monocular frame sequences has been a challenging problem in recent years. This difficulty stems from factors such as shadows, indirect illumination,…

计算机视觉与模式识别 · 计算机科学 2025-05-12 Alakh Aggarwal , Ningna Wang , Xiaohu Guo

We ask whether everyday open-world monocular videos can be turned into reusable 4D interaction primitives: articulated hand motion, object shape with 6D pose over time, and the when/where of contact. Such a capability would enable scalable…

计算机视觉与模式识别 · 计算机科学 2026-05-22 Hao Xu , Yilin Liu , Yinqiao Wang , Chi-Wing Fu , Niloy J. Mitra

Hand-Object Interaction (HOI) remains a core challenge in digital human video synthesis, where models must generate physically plausible contact and preserve object identity across frames. Although recent HOI reenactment approaches have…

计算机视觉与模式识别 · 计算机科学 2026-03-09 Xuan Huang , Mochu Xiang , Zhelun Shen , Jinbo Wu , Chenming Wu , Chen Zhao , Kaisiyuan Wang , Hang Zhou , Shanshan Liu , Haocheng Feng , Wei He , Jingdong Wang

Accurately modeling detailed interactions between human/hand and object is an appealing yet challenging task. Current multi-view capture systems are only capable of reconstructing multiple subjects into a single, unified mesh, which fails…

计算机视觉与模式识别 · 计算机科学 2024-03-22 Jiajun Zhang , Yuxiang Zhang , Hongwen Zhang , Xiao Zhou , Boyao Zhou , Ruizhi Shao , Zonghai Hu , Yebin Liu

Reconstructing human-object interactions (HOI) from single images is fundamental in computer vision. Existing methods are primarily trained and tested on indoor scenes due to the lack of 3D data, particularly constrained by the object…

计算机视觉与模式识别 · 计算机科学 2025-03-21 Boran Wen , Dingbang Huang , Zichen Zhang , Jiahong Zhou , Jianbin Deng , Jingyu Gong , Yulong Chen , Lizhuang Ma , Yong-Lu Li

Current digital human studies focusing on lip-syncing and body movement are no longer sufficient to meet the growing industrial demand, while human video generation techniques that support interacting with real-world environments (e.g.,…

计算机视觉与模式识别 · 计算机科学 2025-03-26 Yingying Fan , Quanwei Yang , Kaisiyuan Wang , Hang Zhou , Yingying Li , Haocheng Feng , Errui Ding , Yu Wu , Jingdong Wang

We present DreamHOI, a novel method for zero-shot synthesis of human-object interactions (HOIs), enabling a 3D human model to realistically interact with any given object based on a textual description. This task is complicated by the…

计算机视觉与模式识别 · 计算机科学 2024-09-13 Thomas Hanwen Zhu , Ruining Li , Tomas Jakab

Human-Object Interaction (HOI) modelling captures how humans act upon and relate to objects, typically expressed as <person, action, object> triplets. Existing approaches split into two disjoint families: HOI generation synthesises scenes…

计算机视觉与模式识别 · 计算机科学 2026-04-16 Jiun Tian Hoe , Weipeng Hu , Xudong Jiang , Yap-Peng Tan , Chee Seng Chan

Human-Object Interaction (HOI), as an important problem in computer vision, requires locating the human-object pair and identifying the interactive relationships between them. The HOI instance has a greater span in spatial, scale, and task…

计算机视觉与模式识别 · 计算机科学 2023-01-11 Shuailei Ma , Yuefeng Wang , Shanze Wang , Ying Wei

We introduce D3D-HOI: a dataset of monocular videos with ground truth annotations of 3D object pose, shape and part motion during human-object interactions. Our dataset consists of several common articulated objects captured from diverse…

计算机视觉与模式识别 · 计算机科学 2021-08-20 Xiang Xu , Hanbyul Joo , Greg Mori , Manolis Savva

Monocular 4D human-object interaction (HOI) reconstruction - recovering a moving human and a manipulated object from a single RGB video - remains challenging due to depth ambiguity and frequent occlusions. Existing methods often rely on…

计算机视觉与模式识别 · 计算机科学 2026-03-17 Haoyu Zhang , Wei Zhai , Yuhang Yang , Yang Cao , Zheng-Jun Zha
‹ 上一页 1 2 3 10 下一页 ›