NTIRE 2024 challenge on HR depth from images of specular and transparent surfaces

PZ Ramirez, F Tosi, L Di Stefano… - Proceedings of the …, 2024 - openaccess.thecvf.com
This paper reports on the NTIRE 2024 challenge on HR Depth From images of Specular and
Transparent surfaces held in conjunction with the New Trends in Image Restoration and …

Diffusion Models for Monocular Depth Estimation: Overcoming Challenging Conditions

F Tosi, PZ Ramirez, M Poggi - arXiv preprint arXiv:2407.16698, 2024 - arxiv.org
We present a novel approach designed to address the complexities posed by challenging,
out-of-distribution data in the single-image depth estimation task. Starting with images that …

NimbleD: Enhancing Self-supervised Monocular Depth Estimation with Pseudo-labels and Large-scale Video Pre-training

A Luginov, M Shahzad - arXiv preprint arXiv:2408.14177, 2024 - arxiv.org
We introduce NimbleD, an efficient self-supervised monocular depth estimation learning
framework that incorporates supervision from pseudo-labels generated by a large vision …