atlas

Research map / 3D vision / Depth and stereo

Deep Depth Estimation From Thermal Image

CVPR 2023 · 3D vision › Depth and stereo · approach: Depth from light field and defocus · 66 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use the unified model in stereo rather than monocular modeOurs · MS2 evaluation set (Avg, monocular depth)AbsRel: 0.123 -> 0.120Helped
Use the unified model in stereo rather than monocular modeOurs · MS2 evaluation set (Avg, monocular depth)SqRel: 1.103 -> 1.057Helped
Use the unified model in stereo rather than monocular modeOurs · MS2 evaluation set (Avg, disparity)EPE-all(px): 1.066 -> 0.976Helped
Use the unified model in stereo rather than monocular modeOurs · MS2 evaluation set (Avg, disparity)> 1px(%): 23.1 -> 22.7Hurt
Use a 3D correlation cost volume instead of the 4D cost-volume aggregation used by ACVNetOurs (Stereo) · MS2 evaluation set (Avg, disparity)EPE-all(px): 0.962 -> 0.976Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy