中文
相关论文

相关论文: Occlusion resistant learning of intuitive physics …

200 篇论文

Anticipating actions and objects before they start or appear is a difficult problem in computer vision with several real-world applications. This task is challenging partly because it requires leveraging extensive knowledge of the world…

计算机视觉与模式识别 · 计算机科学 2016-12-01 Carl Vondrick , Hamed Pirsiavash , Antonio Torralba

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

The ability of predicting the future is important for intelligent systems, e.g. autonomous vehicles and robots to plan early and make decisions accordingly. Future scene parsing and optical flow estimation are two key tasks that help agents…

计算机视觉与模式识别 · 计算机科学 2017-11-10 Xiaojie Jin , Huaxin Xiao , Xiaohui Shen , Jimei Yang , Zhe Lin , Yunpeng Chen , Zequn Jie , Jiashi Feng , Shuicheng Yan

A major element of depth perception and 3D understanding is the ability to predict the 3D layout of a scene and its contained objects for a novel pose. Indoor environments are particularly suitable for novel view prediction, since the set…

计算机视觉与模式识别 · 计算机科学 2018-08-13 Pulak Purkait , Ujwal Bonde , Christopher Zach

For augmented reality (AR), it is important that virtual assets appear to `sit among' real world objects. The virtual element should variously occlude and be occluded by real matter, based on a plausible depth ordering. This occlusion…

计算机视觉与模式识别 · 计算机科学 2023-05-12 Jamie Watson , Mohamed Sayed , Zawar Qureshi , Gabriel J. Brostow , Sara Vicente , Oisin Mac Aodha , Michael Firman

Discovering 3D arrangements of objects from single indoor images is important given its many applications including interior design, content creation, etc. Although heavily researched in the recent years, existing approaches break down…

计算机视觉与模式识别 · 计算机科学 2017-12-05 Moos Hueting , Pradyumna Reddy , Vladimir Kim , Ersin Yumer , Nathan Carr , Niloy Mitra

We propose a novel framework for the task of object-centric video prediction, i.e., extracting the compositional structure of a video sequence, as well as modeling objects dynamics and interactions from visual observations in order to…

计算机视觉与模式识别 · 计算机科学 2023-08-01 Angel Villar-Corrales , Ismail Wahdan , Sven Behnke

Recent time-contrastive learning approaches manage to learn invariant object representations without supervision. This is achieved by mapping successive views of an object onto close-by internal representations. When considering this…

机器学习 · 计算机科学 2022-05-13 Arthur Aubret , Céline Teulière , Jochen Triesch

Single-view 3D shape retrieval is a challenging task that is increasingly important with the growth of available 3D data. Prior work that has studied this task has not focused on evaluating how realistic occlusions impact performance, and…

计算机视觉与模式识别 · 计算机科学 2024-01-02 Qirui Wu , Daniel Ritchie , Manolis Savva , Angel X. Chang

Implicit functions represented as deep learning approximations are powerful for reconstructing 3D surfaces. However, they can only produce static surfaces that are not controllable, which provides limited ability to modify the resulting…

计算机视觉与模式识别 · 计算机科学 2021-11-29 Bharat Lal Bhatnagar , Cristian Sminchisescu , Christian Theobalt , Gerard Pons-Moll

Human perception involves decomposing complex multi-object scenes into time-static object appearance (i.e., size, shape, color) and time-varying object motion (i.e., position, velocity, acceleration). For machines to achieve human-like…

计算机视觉与模式识别 · 计算机科学 2025-07-22 Yeon-Ji Song , Jaein Kim , Suhyung Choi , Jin-Hwa Kim , Byoung-Tak Zhang

We propose an architecture and training scheme to predict video frames by explicitly modeling dis-occlusions and capturing the evolution of semantically consistent regions in the video. The scene layout (semantic map) and motion (optical…

计算机视觉与模式识别 · 计算机科学 2021-04-21 Xinzhu Bei , Yanchao Yang , Stefano Soatto

Accurately modeling local surface properties of objects is crucial to many robotic applications, from grasping to material recognition. Surface properties like friction are however difficult to estimate, as visual observation of the object…

机器人学 · 计算机科学 2025-01-09 Tran Nguyen Le , Francesco Verdoja , Fares J. Abu-Dakka , Ville Kyrki

Intuitive physics understanding in video diffusion models plays an essential role in building general-purpose physically plausible world simulators, yet accurately evaluating such capacity remains a challenging task due to the difficulty in…

计算机视觉与模式识别 · 计算机科学 2026-03-09 Jianhao Yuan , Fabio Pizzati , Francesco Pinto , Lars Kunze , Ivan Laptev , Paul Newman , Philip Torr , Daniele De Martini

Humans are adept at learning new tasks by watching a few instructional videos. On the other hand, robots that learn new actions either require a lot of effort through trial and error, or use expert demonstrations that are challenging to…

机器人学 · 计算机科学 2020-11-16 Vladimír Petrík , Makarand Tapaswi , Ivan Laptev , Josef Sivic

Accurate 6D object pose estimation is vital for robotics, augmented reality, and scene understanding. For seen objects, high accuracy is often attainable via per-object fine-tuning but generalizing to unseen objects remains a challenge. To…

计算机视觉与模式识别 · 计算机科学 2025-11-21 Sajjad Pakdamansavoji , Yintao Ma , Amir Rasouli , Tongtong Cao

Reconstructing simulation-ready deformable objects is important for vision, graphics, and robotics. Existing physics-driven methods can recover physical digital twins from videos, but they suffer from two fundamental limitations: they…

计算机视觉与模式识别 · 计算机科学 2026-05-20 Yang Yang , Yiyan Wang , Zheming Liu , Naoya Iwamoto

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

Estimating the pose and shape of hands and objects under interaction finds numerous applications including augmented and virtual reality. Existing approaches for hand and object reconstruction require explicitly defined physical constraints…

计算机视觉与模式识别 · 计算机科学 2022-04-28 Tze Ho Elden Tse , Kwang In Kim , Ales Leonardis , Hyung Jin Chang

Understanding physical phenomena is a key competence that enables humans and animals to act and interact under uncertain perception in previously unseen environments containing novel object and their configurations. Developmental psychology…

计算机视觉与模式识别 · 计算机科学 2016-04-04 Wenbin Li , Seyedmajid Azimi , Aleš Leonardis , Mario Fritz