English
Related papers

Related papers: Moving Indoor: Unsupervised Video Depth Learning i…

200 papers

Learning with complete or partial supervision is powerful but relies on ever-growing human annotation efforts. As a way to mitigate this serious problem, as well as to serve specific applications, unsupervised learning has emerged as an…

Computer Vision and Pattern Recognition · Computer Science 2019-04-08 Huy V. Vo , Francis Bach , Minsu Cho , Kai Han , Yann LeCun , Patrick Perez , Jean Ponce

The self-supervised learning of depth and pose from monocular sequences provides an attractive solution by using the photometric consistency of nearby frames as it depends much less on the ground-truth data. In this paper, we address the…

Computer Vision and Pattern Recognition · Computer Science 2019-09-20 Tianwei Shen , Lei Zhou , Zixin Luo , Yao Yao , Shiwei Li , Jiahui Zhang , Tian Fang , Long Quan

We propose a general framework for self-supervised learning of transferable visual representations based on Video-Induced Visual Invariances (VIVI). We consider the implicit hierarchy present in the videos and make use of (i) frame-level…

Computer Vision and Pattern Recognition · Computer Science 2020-04-03 Michael Tschannen , Josip Djolonga , Marvin Ritter , Aravindh Mahendran , Xiaohua Zhai , Neil Houlsby , Sylvain Gelly , Mario Lucic

Modeling the dynamic behavior of deformable objects is crucial for creating realistic digital worlds. While conventional simulations produce high-quality motions, their computational costs are often prohibitive. Subspace simulation…

Cutting-edge connected vehicle (CV) technologies have drawn much attention in recent years. The real-time traffic data captured by a CV can be shared with other CVs and data centers so as to open new possibilities for solving diverse…

Computer Vision and Pattern Recognition · Computer Science 2023-06-22 Shaocheng Jia , Wei Yao

We propose a monocular depth estimator SC-Depth, which requires only unlabelled videos for training and enables the scale-consistent prediction at inference time. Our contributions include: (i) we propose a geometry consistency loss, which…

Computer Vision and Pattern Recognition · Computer Science 2021-11-29 Jia-Wang Bian , Huangying Zhan , Naiyan Wang , Zhichao Li , Le Zhang , Chunhua Shen , Ming-Ming Cheng , Ian Reid

Wearable cameras stand out as one of the most promising devices for the upcoming years, and as a consequence, the demand of computer algorithms to automatically understand the videos recorded with them is increasing quickly. An automatic…

Computer Vision and Pattern Recognition · Computer Science 2017-03-29 Alejandro Betancourt , Natalia Díaz-Rodríguez , Emilia Barakova , Lucio Marcenaro , Matthias Rauterberg , Carlo Regazzoni

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…

Computer Vision and Pattern Recognition · Computer Science 2023-10-04 Sheng-Chi Huang , Wei-Chen Chiu

The accuracy of learning-based optical flow estimation models heavily relies on the realism of the training datasets. Current approaches for generating such datasets either employ synthetic data or generate images with limited realism.…

Computer Vision and Pattern Recognition · Computer Science 2023-09-14 Yingping Liang , Jiaming Liu , Debing Zhang , Ying Fu

Understanding visual reality involves acquiring common-sense knowledge about countless regularities in the visual world, e.g., how illumination alters the appearance of objects in a scene, and how motion changes their apparent spatial…

Computer Vision and Pattern Recognition · Computer Science 2016-10-03 Filip Piekniewski , Patryk Laurent , Csaba Petre , Micah Richert , Dimitry Fisher , Todd Hylton

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 a new self-supervised approach to image feature learning from motion cue. This new approach leverages recent advances in deep learning in two directions: 1) the success of training deep neural network in estimating optical flow…

Computer Vision and Pattern Recognition · Computer Science 2019-01-10 Bin Ma , Shubao Liu , Yingxuan Zhi , Qi Song

Recent visual odometry (VO) methods incorporating geometric algorithm into deep-learning architecture have shown outstanding performance on the challenging monocular VO task. Despite encouraging results are shown, previous methods ignore…

Computer Vision and Pattern Recognition · Computer Science 2022-12-22 Yijun Cao , Xianshi Zhang , Fuya Luo , Peng Peng , Yongjie Li

Recently, cross domain transfer has been applied for unsupervised image restoration tasks. However, directly applying existing frameworks would lead to domain-shift problems in translated images due to lack of effective supervision.…

Computer Vision and Pattern Recognition · Computer Science 2020-03-31 Wenchao Du , Hu Chen , Hongyu Yang

This paper presents two unsupervised learning layers (UL layers) for label-free video analysis: one for fully connected layers, and the other for convolutional ones. The proposed UL layers can play two roles: they can be the cost function…

Machine Learning · Computer Science 2017-05-26 Liang Zhao , Yang Wang , Yi Yang , Wei Xu

Unsupervised meta-learning aims to learn feature representations from unsupervised datasets that can transfer to downstream tasks with limited labeled data. In this paper, we propose a novel approach to unsupervised meta-learning that…

Machine Learning · Computer Science 2025-02-11 Anna Vettoruzzo , Lorenzo Braccaioli , Joaquin Vanschoren , Marlena Nowaczyk

The 3D-zoom operation is the positive translation of the camera in the Z-axis, perpendicular to the image plane. In contrast, the optical zoom changes the focal length and the digital zoom is used to enlarge a certain region of an image to…

Image and Video Processing · Electrical Eng. & Systems 2019-10-03 Juan Luis Gonzalez Bello , Munchurl Kim

We present an unsupervised simultaneous learning framework for the task of monocular camera re-localization and depth estimation from unlabeled video sequences. Monocular camera re-localization refers to the task of estimating the absolute…

Computer Vision and Pattern Recognition · Computer Science 2022-03-25 Shun Taguchi , Noriaki Hirose

Self-supervised paradigms for monocular depth estimation are very appealing since they do not require ground truth annotations at all. Despite the astonishing results yielded by such methodologies, learning to reason about the uncertainty…

Computer Vision and Pattern Recognition · Computer Science 2020-05-14 Matteo Poggi , Filippo Aleotti , Fabio Tosi , Stefano Mattoccia

We present SMURF, a method for unsupervised learning of optical flow that improves state of the art on all benchmarks by $36\%$ to $40\%$ (over the prior best method UFlow) and even outperforms several supervised approaches such as PWC-Net…

Computer Vision and Pattern Recognition · Computer Science 2021-05-18 Austin Stone , Daniel Maurer , Alper Ayvaci , Anelia Angelova , Rico Jonschkowski