Monocular Depth Estimation
Monocular depth estimation aims to reconstruct three-dimensional scene depth from a single image, a challenging inverse problem due to the inherent loss of depth information during image formation. Current research focuses on improving accuracy and robustness, particularly in challenging scenarios like low-texture regions, viewpoint changes, and non-Lambertian surfaces, often employing deep learning models such as transformers and diffusion networks, along with techniques like multi-view rendering and radar fusion. These advancements have significant implications for various applications, including autonomous driving, robotics, and augmented reality, by enabling more accurate and reliable 3D scene understanding from readily available monocular vision data.
Papers
The Second Monocular Depth Estimation Challenge
Jaime Spencer, C. Stella Qian, Michaela Trescakova, Chris Russell, Simon Hadfield, Erich W. Graf, Wendy J. Adams, Andrew J. Schofield, James Elder, Richard Bowden, Ali Anwar, Hao Chen, Xiaozhi Chen, Kai Cheng, Yuchao Dai, Huynh Thai Hoa, Sadat Hossain, Jianmian Huang, Mohan Jing, Bo Li, Chao Li, Baojun Li, Zhiwen Liu, Stefano Mattoccia, Siegfried Mercelis, Myungwoo Nam, Matteo Poggi, Xiaohua Qi, Jiahui Ren, Yang Tang, Fabio Tosi, Linh Trinh, S. M. Nadim Uddin, Khan Muhammad Umair, Kaixuan Wang, Yufei Wang, Yixing Wang, Mochu Xiang, Guangkai Xu, Wei Yin, Jun Yu, Qi Zhang, Chaoqiang Zhao
Self-Supervised Learning based Depth Estimation from Monocular Images
Mayank Poddar, Akash Mishra, Mohit Kewlani, Haoyang Pei
Learning 3D Photography Videos via Self-supervised Diffusion on Single Images
Xiaodong Wang, Chenfei Wu, Shengming Yin, Minheng Ni, Jianfeng Wang, Linjie Li, Zhengyuan Yang, Fan Yang, Lijuan Wang, Zicheng Liu, Yuejian Fang, Nan Duan
Depth Estimation and Image Restoration by Deep Learning from Defocused Images
Saqib Nazir, Lorenzo Vaquero, Manuel Mucientes, Víctor M. Brea, Daniela Coltuc