On the Uncertainty of Self-Supervised Monocular Depth Estimation
By Matteo Poggi, Filippo Aleotti, Fabio Tosi, Stefano Mattoccia. Computer Vision and Pattern Recognition, 2020
327 citations recorded by the source corpus.
Self-supervised paradigms for monocular depth estimation are very appealing since they do not require ground truth annotations at all. Despite the astonishing results yielded by such methodologies, learning to reason about the uncertainty of the estimated depth maps is of paramount importance for practical applications, yet uncharted in the literature. Purposely, we explore for the first time how to estimate the uncertainty for this task and how this affects depth accuracy, proposing a novel peculiar technique specifically designed for self-supervised approaches. On the standard KITTI dataset, we exhaustively assess the performance of each method with different self-supervised paradigms. Such evaluation highlights that our proposal i) always improves depth accuracy significantly and ii) yields state-of-the-art results concerning uncertainty estimation when training on sequences and competitive results uniquely deploying stereo pairs.
View Paper: https://www.semanticscholar.org/paper/631caae176a966470b488c4368d7aed36b01c04f
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Ning Zhang
- Justin Johnson
- Nilesh Kulkarni
- Francesco Nex
- David F. Fouhey
- Abhinav Kumar Gupta
- George Vosselman
- X. Wang
Citations in the corpus
- A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges (2020, unknown): “[366] (Self-Teaching), Cui et al.”
- MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformer (2022, background): “Several frameworks have advanced this line of research by incorporating additional losses and constraints such as those based on direct visual odometry [49], adversarial learning[68], ICP [31], normal consistency [63, 62], semantic segmentation [23, 19] and uncertainty [35, 60].”
- What's Behind the Couch? Directed Ray Distance Functions (DRDF) for 3D Scene Reconstruction (2021, background): “1, 2 [39] Matteo Poggi, Filippo Aleotti, Fabio Tosi, and Stefano Mattoccia.”
- Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimation (2022, methodology): “To model dynamic scenes other works introduced multi-task learning, such as optical flow estimation [41] and semantic segmentation [5,20], or introduced additional constraints, such as uncertainty estimation [30, 40].”