English
Related papers

Related papers: Self-Supervised Joint Learning Framework of Depth …

200 papers

Predicting accurate depth with monocular images is important for low-cost robotic applications and autonomous driving. This study proposes a comprehensive self-supervised framework for accurate scale-aware depth prediction on autonomous…

Computer Vision and Pattern Recognition · Computer Science 2023-04-24 Yuxuan Liu , Zhenhua Xu , Huaiyang Huang , Lujia Wang , Ming Liu

Video Instance Segmentation (VIS) fundamentally struggles with pervasive challenges including object occlusions, motion blur, and appearance variations during temporal association. To overcome these limitations, this work introduces…

Computer Vision and Pattern Recognition · Computer Science 2025-07-15 Quanzhu Niu , Yikang Zhou , Shihao Chen , Tao Zhang , Shunping Ji

In this paper, we propose a novel method for monocular depth estimation in dynamic scenes. We first explore the arbitrariness of object's movement trajectory in dynamic scenes theoretically. To overcome the arbitrariness, we use assume that…

Computer Vision and Pattern Recognition · Computer Science 2024-11-08 Kebin Peng , John Quarles , Kevin Desai

Photometric consistency loss is one of the representative objective functions commonly used for self-supervised monocular depth estimation. However, this loss often causes unstable depth predictions in textureless or occluded regions due to…

Computer Vision and Pattern Recognition · Computer Science 2021-11-09 Byeongjun Park , Taekyung Kim , Hyojun Go , Changick Kim

While monocular depth estimation (MDE) is an important problem in computer vision, it is difficult due to the ambiguity that results from the compression of a 3D scene into only 2 dimensions. It is common practice in the field to treat it…

Computer Vision and Pattern Recognition · Computer Science 2022-12-01 Dylan Auty , Krystian Mikolajczyk

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

Autonomous vehicles and robots need to operate over a wide variety of scenarios in order to complete tasks efficiently and safely. Multi-camera self-supervised monocular depth estimation from videos is a promising way to reason about the…

Computer Vision and Pattern Recognition · Computer Science 2023-08-08 Takayuki Kanai , Igor Vasiljevic , Vitor Guizilini , Adrien Gaidon , Rares Ambrus

Monocular depth estimation aims at predicting depth from a single image or video. Recently, self-supervised methods draw much attention since they are free of depth annotations and achieve impressive performance on several daytime…

Computer Vision and Pattern Recognition · Computer Science 2021-08-16 Kun Wang , Zhenyu Zhang , Zhiqiang Yan , Xiang Li , Baobei Xu , Jun Li , Jian Yang

Obtaining accurate depth measurements out of a single image represents a fascinating solution to 3D sensing. CNNs led to considerable improvements in this field, and recent trends replaced the need for ground-truth labels with…

Computer Vision and Pattern Recognition · Computer Science 2018-08-07 Matteo Poggi , Fabio Tosi , Stefano Mattoccia

Depth estimation from a single image is a challenging problem in computer vision because binocular disparity or motion information is absent. Whereas impressive performances have been reported in this area recently using end-to-end trained…

Computer Vision and Pattern Recognition · Computer Science 2023-11-17 Yihong Wu , Yuwen Heng , Mahesan Niranjan , Hansung 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

As an agent moves through the world, the apparent motion of scene elements is (usually) inversely proportional to their depth. It is natural for a learning agent to associate image patterns with the magnitude of their displacement over…

Computer Vision and Pattern Recognition · Computer Science 2018-04-03 Huaizu Jiang , Erik Learned-Miller , Gustav Larsson , Michael Maire , Greg Shakhnarovich

Monocular depth estimation (MDE) aims to transform an RGB image of a scene into a pixelwise depth map from the same camera view. It is fundamentally ill-posed due to missing information: any single image can have been taken from many…

Computer Vision and Pattern Recognition · Computer Science 2022-05-13 Dylan Auty , Krystian Mikolajczyk

Learning to predict scene depth and camera motion from RGB inputs only is a challenging task. Most existing learning based methods deal with this task in a supervised manner which require ground-truth data that is expensive to acquire. More…

Computer Vision and Pattern Recognition · Computer Science 2019-10-01 Yunxiao Shi , Jing Zhu , Yi Fang , Kuochin Lien , Junli Gu

The dense depth estimation of a 3D scene has numerous applications, mainly in robotics and surveillance. LiDAR and radar sensors are the hardware solution for real-time depth estimation, but these sensors produce sparse depth maps and are…

Computer Vision and Pattern Recognition · Computer Science 2021-03-02 Alwyn Mathew , Aditya Prakash Patra , Jimson Mathew

Depth estimation from images serves as the fundamental step of 3D perception for autonomous driving and is an economical alternative to expensive depth sensors like LiDAR. The temporal photometric constraints enables self-supervised depth…

Computer Vision and Pattern Recognition · Computer Science 2022-09-21 Yi Wei , Linqing Zhao , Wenzhao Zheng , Zheng Zhu , Yongming Rao , Guan Huang , Jiwen Lu , Jie Zhou

We consider the problem of next frame prediction from video input. A recurrent convolutional neural network is trained to predict depth from monocular video input, which, along with the current video image and the camera trajectory, can…

Machine Learning · Computer Science 2017-06-14 Reza Mahjourian , Martin Wicke , Anelia Angelova

Single view depth estimation models can be trained from video footage using a self-supervised end-to-end approach with view synthesis as the supervisory signal. This is achieved with a framework that predicts depth and camera motion, with a…

Computer Vision and Pattern Recognition · Computer Science 2019-08-30 Maarten Schellevis

We propose MAMo, a novel memory and attention frame-work for monocular video depth estimation. MAMo can augment and improve any single-image depth estimation networks into video depth estimation models, enabling them to take advantage of…

Computer Vision and Pattern Recognition · Computer Science 2025-01-17 Rajeev Yasarla , Hong Cai , Jisoo Jeong , Yunxiao Shi , Risheek Garrepalli , Fatih Porikli

Self-supervised monocular depth estimation has been widely investigated to estimate depth images and relative poses from RGB images. This framework is attractive for researchers because the depth and pose networks can be trained from just…

Computer Vision and Pattern Recognition · Computer Science 2022-02-21 Noriaki Hirose , Kosuke Tahara