中文
相关论文

相关论文: Layered Neural Rendering for Retiming People in Vi…

200 篇论文

Time-lapse image sequences offer visually compelling insights into dynamic processes that are too slow to observe in real time. However, playing a long time-lapse sequence back as a video often results in distracting flicker due to random…

计算机视觉与模式识别 · 计算机科学 2022-07-05 Erik Härkönen , Miika Aittala , Tuomas Kynkäänniemi , Samuli Laine , Timo Aila , Jaakko Lehtinen

Video-based person re-identification (ReID) is a challenging problem, where some video tracks of people across non-overlapping cameras are available for matching. Feature aggregation from a video track is a key step for video-based person…

计算机视觉与模式识别 · 计算机科学 2019-04-30 Xingyu Liao , Lingxiao He , Zhouwang Yang , Chi Zhang

We propose a self-supervised approach for learning representations and robotic behaviors entirely from unlabeled videos recorded from multiple viewpoints, and study how this representation can be used in two robotic imitation settings:…

计算机视觉与模式识别 · 计算机科学 2018-03-21 Pierre Sermanet , Corey Lynch , Yevgen Chebotar , Jasmine Hsu , Eric Jang , Stefan Schaal , Sergey Levine

State-of-the-art video deblurring methods are capable of removing non-uniform blur caused by unwanted camera shake and/or object motion in dynamic scenes. However, most existing methods are based on batch processing and thus need access to…

计算机视觉与模式识别 · 计算机科学 2017-04-12 Tae Hyun Kim , Kyoung Mu Lee , Bernhard Schölkopf , Michael Hirsch

Human video generation remains challenging due to the difficulty of jointly modeling human appearance, motion, and camera viewpoint under limited multi-view data. Existing methods often address these factors separately, resulting in limited…

计算机视觉与模式识别 · 计算机科学 2026-04-22 Zhengwentai Sun , Keru Zheng , Chenghong Li , Hongjie Liao , Xihe Yang , Heyuan Li , Yihao Zhi , Shuliang Ning , Shuguang Cui , Xiaoguang Han

We explore total scene capture -- recording, modeling, and rerendering a scene under varying appearance such as season and time of day. Starting from internet photos of a tourist landmark, we apply traditional 3D reconstruction to register…

计算机视觉与模式识别 · 计算机科学 2019-04-10 Moustafa Meshry , Dan B Goldman , Sameh Khamis , Hugues Hoppe , Rohit Pandey , Noah Snavely , Ricardo Martin-Brualla

Recent years have witnessed tremendous progress in the 3D reconstruction of dynamic humans from a monocular video with the advent of neural rendering techniques. This task has a wide range of applications, including the creation of virtual…

计算机视觉与模式识别 · 计算机科学 2024-09-24 Kanghao Chen , Zeyu Wang , Lin Wang

The appearance of a human in clothing is driven not only by the pose but also by its temporal context, i.e., motion. However, such context has been largely neglected by existing monocular human modeling methods whose neural networks often…

计算机视觉与模式识别 · 计算机科学 2023-12-29 Hansol Lee , Junuk Cha , Yunhoe Ku , Jae Shin Yoon , Seungryul Baek

We present neural radiance fields for rendering and temporal (4D) reconstruction of humans in motion (H-NeRF), as captured by a sparse set of cameras or even from a monocular video. Our approach combines ideas from neural scene…

计算机视觉与模式识别 · 计算机科学 2021-11-03 Hongyi Xu , Thiemo Alldieck , Cristian Sminchisescu

Upsampling videos of human activity is an interesting yet challenging task with many potential applications ranging from gaming to entertainment and sports broadcasting. The main difficulty in synthesizing video frames in this setting stems…

计算机视觉与模式识别 · 计算机科学 2021-11-02 Hsuan-I Ho , Xu Chen , Jie Song , Otmar Hilliges

We present a learning-based method for estimating 4D reflectance field of a person given video footage illuminated under a flat-lit environment of the same subject. For training data, we use one light at a time to illuminate the subject and…

计算机视觉与模式识别 · 计算机科学 2021-04-08 Loc Huynh , Bipin Kishore , Paul Debevec

Creating high-quality controllable 3D human models from multi-view RGB videos poses a significant challenge. Neural radiance fields (NeRFs) have demonstrated remarkable quality in reconstructing and free-viewpoint rendering of static as…

计算机视觉与模式识别 · 计算机科学 2024-03-20 Paul Knoll , Wieland Morgenstern , Anna Hilsmann , Peter Eisert

We develop a technique for generating smooth and accurate 3D human pose and motion estimates from RGB video sequences. Our method, which we call Motion Estimation via Variational Autoencoder (MEVA), decomposes a temporal sequence of human…

计算机视觉与模式识别 · 计算机科学 2020-10-07 Zhengyi Luo , S. Alireza Golestaneh , Kris M. Kitani

We present a method for predicting dense depth in scenarios where both a monocular camera and people in the scene are freely moving. Existing methods for recovering depth for dynamic, non-rigid objects from monocular video impose strong…

计算机视觉与模式识别 · 计算机科学 2019-04-26 Zhengqi Li , Tali Dekel , Forrester Cole , Richard Tucker , Noah Snavely , Ce Liu , William T. Freeman

Seam carving is a state-of-the-art content-aware image resizing technique that effectively preserves the salient areas of an image. However, when applied to video retargeting, not only is it time intensive, but it also creates highly…

计算机视觉与模式识别 · 计算机科学 2019-03-11 Zhu Chuning

In this paper, a novel video classification method is presented that aims to recognize different categories of third-person videos efficiently. Our motivation is to achieve a light model that could be trained with insufficient training…

计算机视觉与模式识别 · 计算机科学 2022-03-29 Ali Javidani , Ahmad Mahmoudi-Aznaveh

Implicit neural representation (INR) embed various signals into neural networks. They have gained attention in recent years because of their versatility in handling diverse signal types. In the context of video, INR achieves video…

计算机视觉与模式识别 · 计算机科学 2024-10-15 Taiga Hayami , Takahiro Shindo , Shunsuke Akamatsu , Hiroshi Watanabe

Volume rendering using neural fields has shown great promise in capturing and synthesizing novel views of 3D scenes. However, this type of approach requires querying the volume network at multiple points along each viewing ray in order to…

计算机视觉与模式识别 · 计算机科学 2021-11-08 Martin Piala , Ronald Clark

Current person re-identification (ReID) methods typically rely on single-frame imagery features, whilst ignoring space-time information from image sequences often available in the practical surveillance scenarios. Single-frame (single-shot)…

计算机视觉与模式识别 · 计算机科学 2016-01-26 Taiqing Wang , Shaogang Gong , Xiatian Zhu , Shengjin Wang

Camera-based physiological signal estimation provides a non-contact and convenient means to monitor Heart Rate (HR). However, the presence of vital signals in facial videos raises significant privacy concerns, as they can reveal sensitive…

计算机视觉与模式识别 · 计算机科学 2026-04-07 Tianwen Zhou , Akshay Paruchuri , Josef Spjut , Kaan Akşit