中文
相关论文

相关论文: PKU-DyMVHumans: A Multi-View Video Benchmark for H…

200 篇论文

We present EgoHumans, a new multi-view multi-human video benchmark to advance the state-of-the-art of egocentric human 3D pose estimation and tracking. Existing egocentric benchmarks either capture single subject or indoor-only scenarios,…

计算机视觉与模式识别 · 计算机科学 2023-08-22 Rawal Khirodkar , Aayush Bansal , Lingni Ma , Richard Newcombe , Minh Vo , Kris Kitani

Photorealistic 3D full-body human reconstruction from a single image is a critical yet challenging task for applications in films and video games due to inherent ambiguities and severe self-occlusions. While recent approaches leverage SMPL…

计算机视觉与模式识别 · 计算机科学 2025-10-14 Wenyue Chen , Peng Li , Wangguandong Zheng , Chengfeng Zhao , Mengfei Li , Yaolong Zhu , Zhiyang Dou , Ronggang Wang , Yuan Liu

Recent advances in world models have demonstrated strong capabilities in simulating physical reality, making them an increasingly important foundation for embodied intelligence. For UAV agents in particular, accurate prediction of complex…

计算机视觉与模式识别 · 计算机科学 2026-04-10 Zile Guo , Zhan Chen , Enze Zhu , Kan Wei , Yongkang Zou , Xiaoxuan Liu , Lei Wang

Multiple cameras can provide comprehensive multi-view video coverage of a person. Fusing this multi-view data is crucial for tasks like behavioral analysis, although it traditionally requires camera calibration, a process that is often…

计算机视觉与模式识别 · 计算机科学 2024-08-27 Yitao Zhu , Sheng Wang , Mengjie Xu , Zixu Zhuang , Zhixin Wang , Kaidong Wang , Han Zhang , Qian Wang

Human image animation involves generating videos from a character photo, allowing user control and unlocking the potential for video and movie production. While recent approaches yield impressive results using high-quality training data,…

计算机视觉与模式识别 · 计算机科学 2024-11-22 Zhenzhi Wang , Yixuan Li , Yanhong Zeng , Youqing Fang , Yuwei Guo , Wenran Liu , Jing Tan , Kai Chen , Tianfan Xue , Bo Dai , Dahua Lin

Remarkable strides have been made in reconstructing static scenes or human bodies from monocular videos. Yet, the two problems have largely been approached independently, without much synergy. Most visual SLAM methods can only reconstruct…

计算机视觉与模式识别 · 计算机科学 2024-05-24 Yizhou Zhao , Tuanfeng Y. Wang , Bhiksha Raj , Min Xu , Jimei Yang , Chun-Hao Paul Huang

Indoor scene understanding is central to applications such as robot navigation and human companion assistance. Over the last years, data-driven deep neural networks have outperformed many traditional approaches thanks to their…

计算机视觉与模式识别 · 计算机科学 2017-07-04 Yinda Zhang , Shuran Song , Ersin Yumer , Manolis Savva , Joon-Young Lee , Hailin Jin , Thomas Funkhouser

Multi-face deepfake videos are becoming increasingly prevalent, often appearing in natural social settings that challenge existing detection methods. Most current approaches excel at single-face detection but struggle in multi-face…

计算机视觉与模式识别 · 计算机科学 2025-07-22 Juan Hu , Shaojing Fan , Terence Sim

Multi-focus image fusion, a technique to generate an all-in-focus image from two or more partially-focused source images, can benefit many computer vision tasks. However, currently there is no large and realistic dataset to perform…

计算机视觉与模式识别 · 计算机科学 2020-08-31 Juncheng Zhang , Qingmin Liao , Shaojun Liu , Haoyu Ma , Wenming Yang , Jing-Hao Xue

Recent breakthroughs in video generation, powered by large-scale datasets and diffusion techniques, have shown that video diffusion models can function as implicit 4D novel view synthesizers. Nevertheless, current methods primarily…

计算机视觉与模式识别 · 计算机科学 2025-10-09 Yihao Zhi , Chenghong Li , Hongjie Liao , Xihe Yang , Zhengwentai Sun , Jiahao Chang , Xiaodong Cun , Wensen Feng , Xiaoguang Han

Rendering scenes with a high-quality human face from arbitrary viewpoints is a practical and useful technique for many real-world applications. Recently, Neural Radiance Fields (NeRF), a rendering technique that uses neural networks to…

计算机视觉与模式识别 · 计算机科学 2022-06-01 Satoshi Tsutsui , Weijia Mao , Sijing Lin , Yunyi Zhu , Murong Ma , Mike Zheng Shou

Image-to-video (I2V) generation seeks to produce realistic motion sequences from a single reference image. Although recent methods exhibit strong temporal consistency, they often struggle when dealing with complex, non-repetitive human…

计算机视觉与模式识别 · 计算机科学 2025-07-01 Ashkan Taghipour , Morteza Ghahremani , Mohammed Bennamoun , Farid Boussaid , Aref Miri Rekavandi , Zinuo Li , Qiuhong Ke , Hamid Laga

This paper addresses the challenging task of reconstructing the poses of multiple individuals engaged in close interactions, captured by multiple calibrated cameras. The difficulty arises from the noisy or false 2D keypoint detections due…

计算机视觉与模式识别 · 计算机科学 2024-01-30 Qing Shuai , Zhiyuan Yu , Zhize Zhou , Lixin Fan , Haijun Yang , Can Yang , Xiaowei Zhou

3D human pose estimation captures the human joint points in three-dimensional space while keeping the depth information and physical structure. That is essential for applications that require precise pose information, such as human-computer…

计算机视觉与模式识别 · 计算机科学 2024-03-26 Jianbin Jiao , Xina Cheng , Weijie Chen , Xiaoting Yin , Hao Shi , Kailun Yang

Distilling knowledge from human demonstrations is a promising way for robots to learn and act. Existing methods, which often rely on coarsely-aligned video pairs, are typically constrained to learning global or task-level features. As a…

机器人学 · 计算机科学 2025-11-18 Sicheng Xie , Haidong Cao , Zejia Weng , Zhen Xing , Haoran Chen , Shiwei Shen , Jiaqi Leng , Zuxuan Wu , Yu-Gang Jiang

Human motion modelling is crucial in many areas such as computer graphics, vision and virtual reality. Acquiring high-quality skeletal motions is difficult due to the need for specialized equipment and laborious manual post-posting, which…

计算机视觉与模式识别 · 计算机科学 2020-09-14 Wenheng Chen , He Wang , Yi Yuan , Tianjia Shao , Kun Zhou

Face recognition technology has advanced significantly in recent years due largely to the availability of large and increasingly complex training datasets for use in deep learning models. These datasets, however, typically comprise images…

Recent advancements in neural surface reconstruction have significantly enhanced 3D reconstruction. However, current real world datasets mainly focus on benchmarking multiview stereo (MVS) based on RGB inputs. Multiview photometric stereo…

计算机视觉与模式识别 · 计算机科学 2026-03-05 Zaiyan Yang , Jieji Ren , Xiangyi Wang , zonglin li , Xu Cao , Heng Guo , Zhanyu Ma , Boxin Shi

High-quality 4D reconstruction of human performance with complex interactions to various objects is essential in real-world scenarios, which enables numerous immersive VR/AR applications. However, recent advances still fail to provide…

计算机视觉与模式识别 · 计算机科学 2021-05-03 Zhuo Su , Lan Xu , Dawei Zhong , Zhong Li , Fan Deng , Shuxue Quan , Lu Fang

We present Multi-HMR, a strong sigle-shot model for multi-person 3D human mesh recovery from a single RGB image. Predictions encompass the whole body, i.e., including hands and facial expressions, using the SMPL-X parametric model and 3D…

计算机视觉与模式识别 · 计算机科学 2024-07-25 Fabien Baradel , Matthieu Armando , Salma Galaaoui , Romain Brégier , Philippe Weinzaepfel , Grégory Rogez , Thomas Lucas