English
Related papers

Related papers: Towards Better Generalization: Joint Depth-Pose Le…

200 papers

In classical computer vision, rectification is an integral part of multi-view depth estimation. It typically includes epipolar rectification and lens distortion correction. This process simplifies the depth estimation significantly, and…

Computer Vision and Pattern Recognition · Computer Science 2023-06-07 Varun Ravi Kumar , Senthil Yogamani , Markus Bach , Christian Witt , Stefan Milz , Patrick Mader

General Bayesian updating replaces the likelihood with a loss scaled by a learning rate, but posterior uncertainty can depend sharply on that scale. We propose a simple post-processing that aligns generalized posterior draws with their…

Methodology · Statistics 2025-12-12 Shu Tamano , Yui Tomo

Multimodal alignment is critical for bridging the semantic gap in information retrieval. However, traditional pairwise strategies introduce a geometric blind spot: while they align anchor modalities (e.g., text) with others, they lack…

Information Retrieval · Computer Science 2026-05-28 Arijit Ghosh , Aritra Bandyopadhyay , Chiranjeev Bindra , Jingfen Qiao

We address the problem of reconstructing 3D surfaces from depth and surface normal maps acquired by a sensor system based on a single perspective camera. Depth and normal maps can be obtained through techniques such as structured-light…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 Ondrej Hlinka , Georg Kaniak , Christian Kapeller

We present a novel unsupervised learning framework for single view depth estimation using monocular videos. It is well known in 3D vision that enlarging the baseline can increase the depth estimation accuracy, and jointly optimizing a set…

Computer Vision and Pattern Recognition · Computer Science 2018-12-11 Lipu Zhou , Jiamin Ye , Montiel Abello , Shengze Wang , Michael Kaess

Self-supervised monocular depth estimation (MDE) has gained popularity for obtaining depth predictions directly from videos. However, these methods often produce scale invariant results, unless additional training signals are provided.…

Computer Vision and Pattern Recognition · Computer Science 2025-12-05 Gasser Elazab , Torben Gräber , Michael Unterreiner , Olaf Hellwich

Scene depth estimation from stereo and monocular imagery is critical for extracting 3D information for downstream tasks such as scene understanding. Recently, learning-based methods for depth estimation have received much attention due to…

Computer Vision and Pattern Recognition · Computer Science 2021-10-12 Zhaoshuo Li , Nathan Drenkow , Hao Ding , Andy S. Ding , Alexander Lu , Francis X. Creighton , Russell H. Taylor , Mathias Unberath

6D pose estimation in space poses unique challenges that are not commonly encountered in the terrestrial setting. One of the most striking differences is the lack of atmospheric scattering, allowing objects to be visible from a great…

Computer Vision and Pattern Recognition · Computer Science 2021-04-02 Yinlin Hu , Sebastien Speierer , Wenzel Jakob , Pascal Fua , Mathieu Salzmann

Monocular depth estimation is a challenging task in complex compositions depicting multiple objects of diverse scales. Albeit the recent great progress thanks to the deep convolutional neural networks (CNNs), the state-of-the-art monocular…

Computer Vision and Pattern Recognition · Computer Science 2017-08-09 Bo Li , Yuchao Dai , Mingyi He

Many real-world applications require the estimation of human body joints for higher-level tasks as, for example, human behaviour understanding. In recent years, depth sensors have become a popular approach to obtain three-dimensional…

Computer Vision and Pattern Recognition · Computer Science 2018-07-17 Manuel J. Marin-Jimenez , Francisco J. Romero-Ramirez , Rafael Muñoz-Salinas , Rafael Medina-Carnicer

We present a lightweight solution to recover 3D pose from multi-view images captured with spatially calibrated cameras. Building upon recent advances in interpretable representation learning, we exploit 3D geometry to fuse input images into…

Computer Vision and Pattern Recognition · Computer Science 2020-06-23 Edoardo Remelli , Shangchen Han , Sina Honari , Pascal Fua , Robert Wang

This paper proposes a novel approach for extending monocular visual odometry to a stereo camera system. The proposed method uses an additional camera to accurately estimate and optimize the scale of the monocular visual odometry, rather…

Computer Vision and Pattern Recognition · Computer Science 2019-09-18 Jiawei Mo , Junaed Sattar

Category-level 6D object pose and size estimation is to predict full pose configurations of rotation, translation, and size for object instances observed in single, arbitrary views of cluttered scenes. In this paper, we propose a new method…

Computer Vision and Pattern Recognition · Computer Science 2021-08-17 Jiehong Lin , Zewei Wei , Zhihao Li , Songcen Xu , Kui Jia , Yuanqing Li

Monocular visual SLAM enables 3D reconstruction from internet video and autonomous navigation on resource-constrained platforms, yet suffers from scale drift, i.e., the gradual divergence of estimated scale over long sequences. Existing…

Computer Vision and Pattern Recognition · Computer Science 2026-01-15 Yuchen Wu , Jiahe Li , Xiaohan Yu , Lina Yu , Jin Zheng , Xiao Bai

Dense scene reconstruction for photo-realistic view synthesis has various applications, such as VR/AR, autonomous vehicles. However, most existing methods have difficulties in large-scale scenes due to three core challenges: \textit{(a)…

Computer Vision and Pattern Recognition · Computer Science 2025-12-24 Tianchen Deng , Nailin Wang , Chongdi Wang , Shenghai Yuan , Jingchuan Wang , Hesheng Wang , Danwei Wang , Weidong Chen

Recovering structure and motion parameters given a image pair or a sequence of images is a well studied problem in computer vision. This is often achieved by employing Structure from Motion (SfM) or Simultaneous Localization and Mapping…

Computer Vision and Pattern Recognition · Computer Science 2018-11-07 Thanuja Dharmasiri , Andrew Spek , Tom Drummond

Depth estimation from monocular images is a challenging problem in computer vision. In this paper, we tackle this problem using a novel network architecture using multi scale feature fusion. Our network uses two different blocks, first…

Computer Vision and Pattern Recognition · Computer Science 2020-09-22 Abhinav Sagar

Previous work has shown that adversarial learning can be used for unsupervised monocular depth and visual odometry (VO) estimation, in which the adversarial loss and the geometric image reconstruction loss are utilized as the mainly…

Computer Vision and Pattern Recognition · Computer Science 2021-04-14 Chaoqiang Zhao , Gary G. Yen , Qiyu Sun , Chongzhen Zhang , Yang Tang

Reconstructing 3D scenes from sparse viewpoints is a long-standing challenge with wide applications. Recent advances in feed-forward 3D Gaussian sparse-view reconstruction methods provide an efficient solution for real-time novel view…

Computer Vision and Pattern Recognition · Computer Science 2025-06-05 Yang Xiao , Guoan Xu , Qiang Wu , Wenjing Jia

The 3D depth estimation and relative pose estimation problem within a decentralized architecture is a challenging problem that arises in missions that require coordination among multiple vision-controlled robots. The depth estimation…

Robotics · Computer Science 2019-08-02 Romulo T. Rodrigues , Pedro Miraldo , Dimos V. Dimarogonas , A. Pedro Aguiar