中文
相关论文

相关论文: UFD-PRiME: Unsupervised Joint Learning of Optical …

200 篇论文

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

In this paper, we propose a unified method to jointly learn optical flow and stereo matching. Our first intuition is stereo matching can be modeled as a special case of optical flow, and we can leverage 3D geometry behind stereoscopic…

计算机视觉与模式识别 · 计算机科学 2020-04-07 Pengpeng Liu , Irwin King , Michael Lyu , Jia Xu

We present an unsupervised learning framework for simultaneously training single-view depth prediction and optical flow estimation models using unlabeled video sequences. Existing unsupervised methods often exploit brightness constancy and…

计算机视觉与模式识别 · 计算机科学 2018-09-06 Yuliang Zou , Zelun Luo , Jia-Bin Huang

Significant attention has been attracted to deep learning-based depth estimates. Dynamic objects become the most hard problems in inter-frame-supervised depth estimates due to the uncertainty in adjacent frames. Thus, integrating optical…

计算机视觉与模式识别 · 计算机科学 2023-10-04 Zhengyang Lu , Ying Chen

We address the problem of joint optical flow and camera motion estimation in rigid scenes by incorporating geometric constraints into an unsupervised deep learning framework. Unlike existing approaches which rely on brightness constancy and…

计算机视觉与模式识别 · 计算机科学 2020-02-28 Shihao Jiang , Dylan Campbell , Miaomiao Liu , Stephen Gould , Richard Hartley

Unsupervised optical flow methods typically lack reliable uncertainty estimation, limiting their robustness and interpretability. We propose U$^{2}$Flow, the first recurrent unsupervised framework that jointly estimates optical flow and…

计算机视觉与模式识别 · 计算机科学 2026-04-14 Xunpei Sun , Wenwei Lin , Yi Chang , Gang Chen

Stereo matching and flow estimation are two essential tasks for scene understanding, spatially in 3D and temporally in motion. Existing approaches have been focused on the unsupervised setting due to the limited resource to obtain the…

计算机视觉与模式识别 · 计算机科学 2019-05-23 Hsueh-Ying Lai , Yi-Hsuan Tsai , Wei-Chen Chiu

Event cameras rely on motion to obtain information about scene appearance. This means that appearance and motion are inherently linked: either both are present and recorded in the event data, or neither is captured. Previous works treat the…

计算机视觉与模式识别 · 计算机科学 2025-07-23 Shuang Guo , Friedhelm Hamann , Guillermo Gallego

We present an unsupervised learning approach for optical flow estimation by improving the upsampling and learning of pyramid network. We design a self-guided upsample module to tackle the interpolation blur problem caused by bilinear…

计算机视觉与模式识别 · 计算机科学 2021-06-03 Kunming Luo , Chuan Wang , Shuaicheng Liu , Haoqiang Fan , Jue Wang , Jian Sun

Optical flow estimation is a fundamental problem in computer vision, yet the reliance on expensive ground-truth annotations limits the scalability of supervised approaches. Although unsupervised and semi-supervised methods alleviate this…

计算机视觉与模式识别 · 计算机科学 2026-03-24 Yixuan Luo , Feng Qiao , Zhexiao Xiong , Yanjing Li , Nathan Jacobs

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

For visual estimation of optical flow, a crucial function for many vision tasks, unsupervised learning, using the supervision of view synthesis has emerged as a promising alternative to supervised methods, since ground-truth flow is not…

计算机视觉与模式识别 · 计算机科学 2023-04-17 Zitang Sun , Shin'ya Nishida , Zhengbo Luo

In autonomous driving, monocular sequences contain lots of information. Monocular depth estimation, camera ego-motion estimation and optical flow estimation in consecutive frames are high-profile concerns recently. By analyzing tasks above,…

计算机视觉与模式识别 · 计算机科学 2020-08-21 Guangming Wang , Chi Zhang , Hesheng Wang , Jingchuan Wang , Yong Wang , Xinlei Wang

Estimating geometric elements such as depth, camera motion, and optical flow from images is an important part of the robot's visual perception. We use a joint self-supervised method to estimate the three geometric elements. Depth network,…

计算机视觉与模式识别 · 计算机科学 2021-06-01 Jianfeng Li , Junqiao Zhao , Shuangfu Song , Tiantian Feng

In this paper we propose USegScene, a framework for semantically guided unsupervised learning of depth, optical flow and ego-motion estimation for stereo camera images using convolutional neural networks. Our framework leverages semantic…

计算机视觉与模式识别 · 计算机科学 2022-07-18 Johan Vertens , Wolfram Burgard

We propose a novel method for learning convolutional neural image representations without manual supervision. We use motion cues in the form of optical flow, to supervise representations of static images. The obvious approach of training a…

计算机视觉与模式识别 · 计算机科学 2018-07-17 Aravindh Mahendran , James Thewlis , Andrea Vedaldi

Scene flow represents the motion of points in the 3D space, which is the counterpart of the optical flow that represents the motion of pixels in the 2D image. However, it is difficult to obtain the ground truth of scene flow in the real…

计算机视觉与模式识别 · 计算机科学 2022-06-09 Guangming Wang , Xiaoyu Tian , Ruiqi Ding , Hesheng Wang

In this work, we propose a method that combines unsupervised deep learning predictions for optical flow and monocular disparity with a model based optimization procedure for instantaneous camera pose. Given the flow and disparity…

计算机视觉与模式识别 · 计算机科学 2019-02-14 Alex Zihao Zhu , Wenxin Liu , Ziyun Wang , Vijay Kumar , Kostas Daniilidis

Optical flow estimation is crucial for various applications in vision and robotics. As the difficulty of collecting ground truth optical flow in real-world scenarios, most of the existing methods of learning optical flow still adopt…

计算机视觉与模式识别 · 计算机科学 2023-10-04 Sheng-Chi Huang , Wei-Chen Chiu

This paper studies optical flow estimation, a critical task in motion analysis with applications in autonomous navigation, action recognition, and film production. Traditional optical flow methods require consecutive frames, which are often…

计算机视觉与模式识别 · 计算机科学 2025-06-12 Mo Zhou , Jianwei Wang , Xuanmeng Zhang , Dylan Campbell , Kai Wang , Long Yuan , Wenjie Zhang , Xuemin Lin
‹ 上一页 1 2 3 10 下一页 ›