中文
相关论文

相关论文: Learning Independent Object Motion from Unlabelled…

200 篇论文

We present a self-supervised learning framework to estimate the individual object motion and monocular depth from video. We model the object motion as a 6 degree-of-freedom rigid-body transformation. The instance segmentation mask is…

计算机视觉与模式识别 · 计算机科学 2020-05-14 Qi Dai , Vaishakh Patil , Simon Hecker , Dengxin Dai , Luc Van Gool , Konrad Schindler

We present a method for decomposing the 3D scene flow observed from a moving stereo rig into stationary scene elements and dynamic object motion. Our unsupervised learning framework jointly reasons about the camera motion, optical flow, and…

计算机视觉与模式识别 · 计算机科学 2019-09-17 Seokju Lee , Sunghoon Im , Stephen Lin , In So Kweon

As we move through the world, the pattern of light projected on our eyes is complex and dynamic, yet we are still able to distinguish between moving and stationary objects. We propose that humans accomplish this by exploiting constraints…

神经元与认知 · 定量生物学 2025-05-14 Hope Lutwak , Bas Rokers , Eero P. Simoncelli

Learning to estimate 3D geometry in a single image by watching unlabeled videos via deep convolutional network has made significant process recently. Current state-of-the-art (SOTA) methods, are based on the learning framework of rigid…

计算机视觉与模式识别 · 计算机科学 2018-08-17 Zhenheng Yang , Peng Wang , Yang Wang , Wei Xu , Ram Nevatia

We present an end-to-end joint training framework that explicitly models 6-DoF motion of multiple dynamic objects, ego-motion and depth in a monocular camera setup without supervision. Our technical contributions are three-fold. First, we…

计算机视觉与模式识别 · 计算机科学 2020-04-09 Seokju Lee , Sunghoon Im , Stephen Lin , In So Kweon

We present a method to reconstruct the three-dimensional trajectory of a moving instance of a known object category using stereo video data. We track the two-dimensional shape of objects on pixel level exploiting instance-aware semantic…

计算机视觉与模式识别 · 计算机科学 2018-08-29 Sebastian Bullinger , Christoph Bodensteiner , Michael Arens , Rainer Stiefelhagen

Although considerable advancements have been attained in self-supervised depth estimation from monocular videos, most existing methods often treat all objects in a video as static entities, which however violates the dynamic nature of…

计算机视觉与模式识别 · 计算机科学 2024-03-12 Xiuzhe Wu , Xiaoyang Lyu , Qihao Huang , Yong Liu , Yang Wu , Ying Shan , Xiaojuan Qi

Recently, much attention has been drawn to learning the underlying 3D structures of a scene from monocular videos in a fully self-supervised fashion. One of the most challenging aspects of this task is handling the independently moving…

计算机视觉与模式识别 · 计算机科学 2022-05-19 Juan Luis Gonzalez Bello , Jaeho Moon , Munchurl Kim

Monocular depth estimation has been actively studied in fields such as robot vision, autonomous driving, and 3D scene understanding. Given a sequence of color images, unsupervised learning methods based on the framework of…

计算机视觉与模式识别 · 计算机科学 2022-12-06 Songlin Wei , Guodong Chen , Wenzheng Chi , Zhenhua Wang , Lining Sun

Videos acquired in low-light conditions often exhibit motion blur, which depends on the motion of the objects relative to the camera. This is not only visually unpleasing, but can hamper further processing. With this paper we are the first…

计算机视觉与模式识别 · 计算机科学 2016-07-29 Anita Sellent , Carsten Rother , Stefan Roth

In moving camera videos, motion segmentation is commonly performed using the image plane motion of pixels, or optical flow. However, objects that are at different depths from the camera can exhibit different optical flows even if they share…

计算机视觉与模式识别 · 计算机科学 2015-11-06 Manjunath Narayana , Allen Hanson , Erik Learned-Miller

We present an end-to-end joint training framework that explicitly models 6-DoF motion of multiple dynamic objects, ego-motion and depth in a monocular camera setup without supervision. Our technical contributions are three-fold. First, we…

计算机视觉与模式识别 · 计算机科学 2021-02-05 Seokju Lee , Sunghoon Im , Stephen Lin , In So Kweon

Perceiving 3D objects from monocular inputs is crucial for robotic systems, given its economy compared to multi-sensor settings. It is notably difficult as a single image can not provide any clues for predicting absolute depth values.…

计算机视觉与模式识别 · 计算机科学 2023-03-02 Tai Wang , Jiangmiao Pang , Dahua Lin

To reach human performance on complex tasks, a key ability for artificial systems is to understand physical interactions between objects, and predict future outcomes of a situation. This ability, often referred to as intuitive physics, has…

计算机视觉与模式识别 · 计算机科学 2020-05-04 Ronan Riochet , Josef Sivic , Ivan Laptev , Emmanuel Dupoux

The problem of determining whether an object is in motion, irrespective of camera motion, is far from being solved. We address this challenging task by learning motion patterns in videos. The core of our approach is a fully convolutional…

计算机视觉与模式识别 · 计算机科学 2017-04-11 Pavel Tokmakov , Karteek Alahari , Cordelia Schmid

Learning to understand dynamic 3D scenes from imagery is crucial for applications ranging from robotics to scene reconstruction. Yet, unlike other problems where large-scale supervised training has enabled rapid progress, directly…

计算机视觉与模式识别 · 计算机科学 2025-05-01 Linyi Jin , Richard Tucker , Zhengqi Li , David Fouhey , Noah Snavely , Aleksander Holynski

We introduce a way to learn to estimate a scene representation from a single image by predicting a low-dimensional subspace of optical flow for each training example, which encompasses the variety of possible camera and object movement.…

计算机视觉与模式识别 · 计算机科学 2022-10-28 Richard Strong Bowen , Richard Tucker , Ramin Zabih , Noah Snavely

We study the problem of segmenting moving objects in unconstrained videos. Given a video, the task is to segment all the objects that exhibit independent motion in at least one frame. We formulate this as a learning problem and design our…

计算机视觉与模式识别 · 计算机科学 2017-12-05 Pavel Tokmakov , Cordelia Schmid , Karteek Alahari

In this thesis we address two related aspects of visual object recognition: the use of motion information, and the use of internal supervision, to help unsupervised learning. These two aspects are inter-related in the current study, since…

计算机视觉与模式识别 · 计算机科学 2018-12-14 Daniel Harari

Learning depth and optical flow via deep neural networks by watching videos has made significant progress recently. In this paper, we jointly solve the two tasks by exploiting the underlying geometric rules within stereo videos.…

计算机视觉与模式识别 · 计算机科学 2018-10-10 Yang Wang , Zhenheng Yang , Peng Wang , Yi Yang , Chenxu Luo , Wei Xu
‹ 上一页 1 2 3 10 下一页 ›