English
Related papers

Related papers: A Compromise Principle in Deep Monocular Depth Est…

200 papers

Depth estimation from a single image is an important task that can be applied to various fields in computer vision, and has grown rapidly with the development of convolutional neural networks. In this paper, we propose a novel structure and…

Computer Vision and Pattern Recognition · Computer Science 2022-11-01 Doyeon Kim , Woonghyun Ka , Pyungwhan Ahn , Donggyu Joo , Sehwan Chun , Junmo Kim

Multi-view data containing complementary and consensus information can facilitate representation learning by exploiting the intact integration of multi-view features. Because most objects in real world often have underlying connections,…

Machine Learning · Computer Science 2023-08-15 Zhaoliang Chen , Lele Fu , Shunxin Xiao , Shiping Wang , Claudia Plant , Wenzhong Guo

We present a novel real-time capable learning method that jointly perceives a 3D scene's geometry structure and semantic labels. Recent approaches to real-time 3D scene reconstruction mostly adopt a volumetric scheme, where a Truncated…

Computer Vision and Pattern Recognition · Computer Science 2023-09-12 Ziyang Hong , C. Patrick Yue

Current self-supervised methods for monocular depth estimation are largely based on deeply nested convolutional networks that leverage stereo image pairs or monocular sequences during a training phase. However, they often exhibit inaccurate…

Computer Vision and Pattern Recognition · Computer Science 2021-10-25 Jaehoon Cho , Dongbo Min , Youngjung Kim , Kwanghoon Sohn

Accurate classification of fine-grained images remains a challenge in backbones based on convolutional operations or self-attention mechanisms. This study proposes novel dual-current neural networks (DCNN), which combine the advantages of…

Computer Vision and Pattern Recognition · Computer Science 2024-05-08 Da Fu , Mingfei Rong , Eun-Hu Kim , Hao Huang , Witold Pedrycz

Although deep neural networks have been widely applied to computer vision problems, extending them into multiview depth estimation is non-trivial. In this paper, we present MVDepthNet, a convolutional network to solve the depth estimation…

Robotics · Computer Science 2018-07-24 Kaixuan Wang , Shaojie Shen

This paper addresses the problem of estimating the depth map of a scene given a single RGB image. We propose a fully convolutional architecture, encompassing residual learning, to model the ambiguous mapping between monocular images and…

Computer Vision and Pattern Recognition · Computer Science 2016-09-20 Iro Laina , Christian Rupprecht , Vasileios Belagiannis , Federico Tombari , Nassir Navab

Monocular 3D object detection is a key problem for autonomous vehicles, as it provides a solution with simple configuration compared to typical multi-sensor systems. The main challenge in monocular 3D detection lies in accurately predicting…

Computer Vision and Pattern Recognition · Computer Science 2021-03-25 Cody Reading , Ali Harakeh , Julia Chae , Steven L. Waslander

Designing effective graph neural networks (GNNs) with message passing has two fundamental challenges, i.e., determining optimal message-passing pathways and designing local aggregators. Previous methods of designing optimal pathways are…

Machine Learning · Computer Science 2024-11-01 Junshu Sun , Shuhui Wang , Chenxue Yang , Qingming Huang

Graph neural networks (GNNs) have achieved remarkable advances in graph-oriented tasks. However, real-world graphs invariably contain a certain proportion of heterophilous nodes, challenging the homophily assumption of traditional GNNs and…

Machine Learning · Computer Science 2025-02-04 Jiajun Zhou , Shengbo Gong , Xuanze Chen , Chenxuan Xie , Shanqing Yu , Qi Xuan , Xiaoniu Yang

We propose Shift R-CNN, a hybrid model for monocular 3D object detection, which combines deep learning with the power of geometry. We adapt a Faster R-CNN network for regressing initial 2D and 3D object properties and combine it with a…

Computer Vision and Pattern Recognition · Computer Science 2019-05-27 Andretti Naiden , Vlad Paunescu , Gyeongmo Kim , ByeongMoon Jeon , Marius Leordeanu

Estimating depth from RGB images can facilitate many computer vision tasks, such as indoor localization, height estimation, and simultaneous localization and mapping (SLAM). Recently, monocular depth estimation has obtained great progress…

Computer Vision and Pattern Recognition · Computer Science 2020-11-10 Qing Li , Jiasong Zhu , Jun Liu , Rui Cao , Qingquan Li , Sen Jia , Guoping Qiu

Deep neural networks have recently thrived on single image depth estimation. That being said, current developments on this topic highlight an apparent compromise between accuracy and network size. This work proposes an accurate and…

Computer Vision and Pattern Recognition · Computer Science 2021-08-26 Lam Huynh , Matteo Pedone , Phong Nguyen , Jiri Matas , Esa Rahtu , Janne Heikkila

Deep graph clustering, which aims to reveal the underlying graph structure and divide the nodes into different clusters without human annotations, is a fundamental yet challenging task. However, we observed that the existing methods suffer…

Computer Vision and Pattern Recognition · Computer Science 2022-02-28 Yue Liu , Sihang Zhou , Xinwang Liu , Wenxuan Tu , Xihong Yang

Despite significant progress in monocular depth estimation in the wild, recent state-of-the-art methods cannot be used to recover accurate 3D scene shape due to an unknown depth shift induced by shift-invariant reconstruction losses used in…

Computer Vision and Pattern Recognition · Computer Science 2020-12-18 Wei Yin , Jianming Zhang , Oliver Wang , Simon Niklaus , Long Mai , Simon Chen , Chunhua Shen

While the depth of convolutional neural networks has attracted substantial attention in the deep learning research, the width of these networks has recently received greater interest. The width of networks, defined as the size of the…

Computer Vision and Pattern Recognition · Computer Science 2024-06-25 Peng Liu , Xiaoxiao Zhou , Yangjunyi Li , El Basha Mohammad D , Ruogu Fang

Extracting temporal and representation features efficiently plays a pivotal role in understanding visual sequence information. To deal with this, we propose a new recurrent neural framework that can be stacked deep effectively. There are…

Computer Vision and Pattern Recognition · Computer Science 2019-10-28 Bo Pang , Kaiwen Zha , Hanwen Cao , Chen Shi , Cewu Lu

We present a self-supervised approach to training convolutional neural networks for dense depth estimation from monocular endoscopy data without a priori modeling of anatomy or shading. Our method only requires sequential data from…

Computer Vision and Pattern Recognition · Computer Science 2019-04-02 Xingtong Liu , Ayushi Sinha , Mathias Unberath , Masaru Ishii , Gregory Hager , Russell H. Taylor , Austin Reiter

Self-supervised depth learning from monocular images normally relies on the 2D pixel-wise photometric relation between temporally adjacent image frames. However, they neither fully exploit the 3D point-wise geometric correspondences, nor…

Computer Vision and Pattern Recognition · Computer Science 2022-10-04 Kaichen Zhou , Lanqing Hong , Changhao Chen , Hang Xu , Chaoqiang Ye , Qingyong Hu , Zhenguo Li

Learning-based, single-view depth estimation often generalizes poorly to unseen datasets. While learning-based, two-frame depth estimation solves this problem to some extent by learning to match features across frames, it performs poorly at…

Computer Vision and Pattern Recognition · Computer Science 2018-05-18 Rui Wang , Jan-Michael Frahm , Stephen M. Pizer