English
Related papers

Related papers: Scene Motion Decomposition for Learnable Visual Od…

200 papers

State-of-the-art neural network models estimate large displacement optical flow in multi-resolution and use warping to propagate the estimation between two resolutions. Despite their impressive results, it is known that there are two…

Computer Vision and Pattern Recognition · Computer Science 2019-03-05 Yao Lu , Jack Valmadre , Heng Wang , Juho Kannala , Mehrtash Harandi , Philip H. S. Torr

Motion, measured via optical flow, provides a powerful cue to discover and learn objects in images and videos. However, compared to using appearance, it has some blind spots, such as the fact that objects become invisible if they do not…

Computer Vision and Pattern Recognition · Computer Science 2022-10-17 Subhabrata Choudhury , Laurynas Karazija , Iro Laina , Andrea Vedaldi , Christian Rupprecht

We propose SF2SE3, a novel approach to estimate scene dynamics in form of a segmentation into independently moving rigid objects and their SE(3)-motions. SF2SE3 operates on two consecutive stereo or RGB-D images. First, noisy scene flow is…

Computer Vision and Pattern Recognition · Computer Science 2022-09-28 Leonhard Sommer , Philipp Schröppel , Thomas Brox

Automatic Video Object Segmentation (AVOS) refers to the task of autonomously segmenting target objects in video sequences without relying on human-provided annotations in the first frames. In AVOS, the use of motion information is crucial,…

Computer Vision and Pattern Recognition · Computer Science 2025-03-13 Sota Kawamura , Hirotada Honda , Shugo Nakamura , Takashi Sano

We present a self-supervised approach to estimate flow in camera image and top-view grid map sequences using fully convolutional neural networks in the domain of automated driving. We extend existing approaches for self-supervised optical…

Computer Vision and Pattern Recognition · Computer Science 2019-04-30 Sascha Wirges , Johannes Gräter , Qiuhao Zhang , Christoph Stiller

Existing optical flow methods make generic, spatially homogeneous, assumptions about the spatial structure of the flow. In reality, optical flow varies across an image depending on object class. Simply put, different objects move…

Computer Vision and Pattern Recognition · Computer Science 2016-04-12 Laura Sevilla-Lara , Deqing Sun , Varun Jampani , Michael J. Black

Object pose tracking is one of the pivotal technologies in multimedia, attracting ever-growing attention in recent years. Existing methods employing traditional cameras encounter numerous challenges such as motion blur, sensor noise,…

Computer Vision and Pattern Recognition · Computer Science 2025-12-25 Zibin Liu , Banglei Guan , Yang Shang , Shunkun Liang , Zhenbao Yu , Qifeng Yu

In this paper, we deal with the problem to predict the future 3D motions of 3D object scans from previous two consecutive frames. Previous methods mostly focus on sparse motion prediction in the form of skeletons. While in this paper we…

Computer Vision and Pattern Recognition · Computer Science 2020-06-25 Shuaihang Yuan , Xiang Li , Anthony Tzes , Yi Fang

Optical flow techniques are becoming increasingly performant and robust when estimating motion in a scene, but their performance has yet to be proven in the area of facial expression recognition. In this work, a variety of optical flow…

Computer Vision and Pattern Recognition · Computer Science 2024-03-19 Benjamin Allaert , Isaac Ronald Ward , Ioan Marius Bilasco , Chaabane Djeraba , Mohammed Bennamoun

In this paper we formulate structure from motion as a learning problem. We train a convolutional network end-to-end to compute depth and camera motion from successive, unconstrained image pairs. The architecture is composed of multiple…

Computer Vision and Pattern Recognition · Computer Science 2018-01-18 Benjamin Ummenhofer , Huizhong Zhou , Jonas Uhrig , Nikolaus Mayer , Eddy Ilg , Alexey Dosovitskiy , Thomas Brox

We present a generative method to estimate 3D human motion and body shape from monocular video. Under the assumption that starting from an initial pose optical flow constrains subsequent human motion, we exploit flow to find temporally…

Computer Vision and Pattern Recognition · Computer Science 2017-03-22 Thiemo Alldieck , Marc Kassubeck , Marcus Magnor

Both optical flow and stereo disparities are image matches and can therefore benefit from joint training. Depth and 3D motion provide geometric rather than photometric information and can further improve optical flow. Accordingly, we design…

Computer Vision and Pattern Recognition · Computer Science 2023-10-10 Shuai Yuan , Carlo Tomasi

Gathering data and identifying events in various traffic situations remains an essential challenge for the systematic evaluation of a perception system's performance. Analyzing large-scale, typically unstructured, multi-modal, time series…

Computer Vision and Pattern Recognition · Computer Science 2024-08-05 Tayssir Bouraffa , Elias Kjellberg Carlson , Erik Wessman , Ali Nouri , Pierre Lamart , Christian Berger

In this paper, we propose a novel self-supervised learning model for estimating continuous ego-motion from video. Our model learns to estimate camera motion by watching RGBD or RGB video streams and determining translational and rotation…

Computational Geometry · Computer Science 2018-06-28 Minhaeng Lee , Charless C. Fowlkes

Using a layered representation for motion estimation has the advantage of being able to cope with discontinuities and occlusions. In this paper, we learn to estimate optical flow by combining a layered motion representation with deep…

Computer Vision and Pattern Recognition · Computer Science 2018-05-10 Xi Zhang , Di Ma , Xu Ouyang , Shanshan Jiang , Lin Gan , Gady Agam

Recent advances in deep learning for edge detection and segmentation opens up a new path for semantic-edge-based ego-motion estimation. In this work, we propose a robust monocular visual odometry (VO) framework using category-aware semantic…

Computer Vision and Pattern Recognition · Computer Science 2019-04-02 Xiaolong Wu , Assia Benbihi , Antoine Richard , Cedric Pradalier

Self-supervised multi-frame methods have currently achieved promising results in depth estimation. However, these methods often suffer from mismatch problems due to the moving objects, which break the static assumption. Additionally,…

Computer Vision and Pattern Recognition · Computer Science 2024-03-29 Yiyang Sun , Zhiyuan Xu , Xiaonian Wang , Jing Yao

We propose a learning-based method that solves monocular stereo and can be extended to fuse depth information from multiple target frames. Given two unconstrained images from a monocular camera with known intrinsic calibration, our network…

Computer Vision and Pattern Recognition · Computer Science 2019-09-13 Kaixuan Wang , Shaojie Shen

Motion is an important signal for agents in dynamic environments, but learning to represent motion from unlabeled video is a difficult and underconstrained problem. We propose a model of motion based on elementary group properties of…

Computer Vision and Pattern Recognition · Computer Science 2018-02-27 Andrew Jaegle , Stephen Phillips , Daphne Ippolito , Kostas Daniilidis

This paper presents a novel architecture for simultaneous estimation of highly accurate optical flows and rigid scene transformations for difficult scenarios where the brightness assumption is violated by strong shading changes. In the case…

Computer Vision and Pattern Recognition · Computer Science 2022-09-15 Torben Fetzer , Gerd Reis , Didier Stricker