English
Related papers

Related papers: Beyond Photometric Loss for Self-Supervised Ego-Mo…

200 papers

Accurate and robust localization is a fundamental need for mobile agents. Visual-inertial odometry (VIO) algorithms exploit the information from camera and inertial sensors to estimate position and translation. Recent deep learning based…

Computer Vision and Pattern Recognition · Computer Science 2022-09-20 Zheming Tu , Changhao Chen , Xianfei Pan , Ruochen Liu , Jiarui Cui , Jun Mao

Photometric differences are widely used as supervision signals to train neural networks for estimating depth and camera pose from unlabeled monocular videos. However, this approach is detrimental for model optimization because occlusions…

Computer Vision and Pattern Recognition · Computer Science 2023-03-06 Fei Wang , Jun Cheng , Penglei Liu

Accurate camera pose estimation result is essential for visual SLAM (VSLAM). This paper presents a novel pose correction method to improve the accuracy of the VSLAM system. Firstly, the relationship between the camera pose estimation error…

Computer Vision and Pattern Recognition · Computer Science 2019-08-27 Zhaobing Kang , Wei Zou , Zheng Zhu

Person re identification is a challenging retrieval task that requires matching a person's acquired image across non overlapping camera views. In this paper we propose an effective approach that incorporates both the fine and coarse pose…

Computer Vision and Pattern Recognition · Computer Science 2018-04-03 M. Saquib Sarfraz , Arne Schumann , Andreas Eberle , Rainer Stiefelhagen

Precise localization is of great importance for autonomous parking task since it provides service for the downstream planning and control modules, which significantly affects the system performance. For parking scenarios, dynamic lighting,…

Robotics · Computer Science 2024-07-09 Xuefeng Jiang , Fangyuan Wang , Rongzhang Zheng , Han Liu , Yixiong Huo , Jinzhang Peng , Lu Tian , Emad Barsoum

Monocular visual odometry is a key technology in various autonomous systems. Traditional feature-based methods suffer from failures due to poor lighting, insufficient texture, and large motions. In contrast, recent learning-based dense SLAM…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Takayuki Kanai , Igor Vasiljevic , Vitor Guizilini , Kazuhiro Shintani

We propose an automatic method for pose and motion estimation against a ground surface for a ground-moving robot-mounted monocular camera. The framework adopts a semi-dense approach that benefits from both a feature-based method and an…

Robotics · Computer Science 2023-03-10 Masahiro Hirano , Taku Senoo , Norimasa Kishi , Masatoshi Ishikawa

Localization is an indispensable component of a robot's autonomy stack that enables it to determine where it is in the environment, essentially making it a precursor for any action execution or planning. Although convolutional neural…

Robotics · Computer Science 2018-03-13 Abhinav Valada , Noha Radwan , Wolfram Burgard

Estimating metric relative camera pose from a pair of images is of great importance for 3D reconstruction and localisation. However, conventional two-view pose estimation methods are not metric, with camera translation known only up to a…

Computer Vision and Pattern Recognition · Computer Science 2025-09-18 Yumin Li , Dylan Campbell

Learning based methods have shown very promising results for the task of depth estimation in single images. However, most existing approaches treat depth prediction as a supervised regression problem and as a result, require vast quantities…

Computer Vision and Pattern Recognition · Computer Science 2017-04-14 Clément Godard , Oisin Mac Aodha , Gabriel J. Brostow

Although existing monocular depth estimation methods have made great progress, predicting an accurate absolute depth map from a single image is still challenging due to the limited modeling capacity of networks and the scale ambiguity…

Computer Vision and Pattern Recognition · Computer Science 2022-10-07 Jie Xiang , Yun Wang , Lifeng An , Haiyang Liu , Zijun Wang , Jian Liu

In this work, we investigate several methods and strategies to learn deep embeddings for face recognition, using joint sample- and set-based optimization. We explain our framework that expands traditional learning with set-based supervision…

Computer Vision and Pattern Recognition · Computer Science 2020-09-09 Baris Gecer , Vassileios Balntas , Tae-Kyun Kim

Recent work has shown that CNN-based depth and ego-motion estimators can be learned using unlabelled monocular videos. However, the performance is limited by unidentified moving objects that violate the underlying static scene assumption in…

Computer Vision and Pattern Recognition · Computer Science 2019-10-04 Jia-Wang Bian , Zhichao Li , Naiyan Wang , Huangying Zhan , Chunhua Shen , Ming-Ming Cheng , Ian Reid

We propose the MAC-VO, a novel learning-based stereo VO that leverages the learned metrics-aware matching uncertainty for dual purposes: selecting keypoint and weighing the residual in pose graph optimization. Compared to traditional…

Robotics · Computer Science 2025-03-13 Yuheng Qiu , Yutian Chen , Zihao Zhang , Wenshan Wang , Sebastian Scherer

Solving the camera-to-robot pose is a fundamental requirement for vision-based robot control, and is a process that takes considerable effort and cares to make accurate. Traditional approaches require modification of the robot via markers,…

Computer Vision and Pattern Recognition · Computer Science 2023-03-22 Jingpei Lu , Florian Richter , Michael C. Yip

Recent work in multi-view stereo (MVS) combines learnable photometric scores and regularization with PatchMatch-based optimization to achieve robust pixelwise estimates of depth, normals, and visibility. However, non-learning based methods…

Computer Vision and Pattern Recognition · Computer Science 2022-10-17 Jae Yong Lee , Chuhang Zou , Derek Hoiem

Homography estimation is often an indispensable step in many computer vision tasks. The existing approaches, however, are not robust to illumination and/or larger viewpoint changes. In this paper, we propose bidirectional implicit…

Computer Vision and Pattern Recognition · Computer Science 2021-04-21 Daniel Koguciuk , Elahe Arani , Bahram Zonooz

Self-supervised monocular depth estimation has emerged as a promising method because it does not require groundtruth depth maps during training. As an alternative for the groundtruth depth map, the photometric loss enables to provide…

Computer Vision and Pattern Recognition · Computer Science 2021-01-01 Jaehoon Choi , Dongki Jung , Donghwan Lee , Changick Kim

We introduce a novel neural volumetric pose feature, termed PoseMap, designed to enhance camera localization by encapsulating the information between images and the associated camera poses. Our framework leverages an Absolute Pose…

Computer Vision and Pattern Recognition · Computer Science 2024-07-15 Jingyu Lin , Jiaqi Gu , Bojian Wu , Lubin Fan , Renjie Chen , Ligang Liu , Jieping Ye

LiDAR odometry is a fundamental task for various areas such as robotics, autonomous driving. This problem is difficult since it requires the systems to be highly robust running in noisy real-world data. Existing methods are mostly local…

Computer Vision and Pattern Recognition · Computer Science 2020-04-10 Zhichao Li , Naiyan Wang