Towards Sharper Object Boundaries in Self-Supervised Depth Estimation


Aurélien Cecille (LIRIS), Stefan Duffner (LIRIS), Franck Davoine (LIRIS), Rémi Agier (Visual Behavior), Thibault Neveu (Visual Behavior)
The 35th British Machine Vision Conference
PDFPosterVideo (Right click to download)Supplementary

Abstract

Accurate monocular depth estimation is crucial for 3D scene understanding, but existing methods often blur depth at object boundaries, introducing spurious intermediate 3D points. While achieving sharp edges usually requires very fine-grained supervision, our method produces crisp depth discontinuities using only self-supervision. Specifically, we model per-pixel depth as a mixture distribution, capturing multiple plausible depths and shifting uncertainty from direct regression to the mixture weights. This formulation integrates seamlessly into existing pipelines via variance-aware loss functions and uncertainty propagation. Extensive evaluations on KITTI and VKITTIv2 show that our method achieves up to 35\% higher boundary sharpness and improves point cloud quality compared to state-of-the-art baselines.

Citation

@inproceedings{Cecille_2025_BMVC,
author    = {Aurélien Cecille and Stefan Duffner and Franck Davoine and Rémi Agier and Thibault Neveu},
title     = {Towards Sharper Object Boundaries in Self-Supervised Depth Estimation},
booktitle = {36th British Machine Vision Conference 2025, {BMVC} 2025, Sheffield, UK, November 24-27, 2025},
publisher = {BMVA},
year      = {2025},
url       = {https://bmva-archive.org.uk/bmvc/2025/assets/papers/Paper_1077/paper.pdf}
}


Copyright © 2025 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection