AI Paper Atlas

Research map / 3D vision / Depth and stereo

FoggyStereo: Stereo Matching With Fog Volume Representation

Chengtang Yao, Lidong Yu

CVPR 2022 · 3D vision › Depth and stereo · approach: Learned stereo with specialized sensors · 10 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (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
Add a fog volume built from images rendered with disparity candidates, then fuse it with the cost volumeDeepPruner · SceneFlow foggyEPE: 2.68 -> 1.04Improved
Add a fog volume built from images rendered with disparity candidates, then fuse it with the cost volumeDeepPruner · SceneFlow clearEPE: 0.98 -> 0.81Improved
Add a fog volume built from images rendered with disparity candidates, then fuse it with the cost volumeDeepPruner · KITTI 2015 foggyEPE: 0.88 -> 0.51Improved
Add a fog volume built from images rendered with disparity candidates, then fuse it with the cost volumeDeepPruner · KITTI 2012 foggyEPE: 0.94 -> 0.77Improved
Add a fog volume built from images rendered with disparity candidates, then fuse it with the cost volumeDeepPruner · KITTI 2015 clearEPE: 0.49 -> 0.47Improved
Add a fog volume built from images rendered with disparity candidates, then fuse it with the cost volumeDeepPruner · PixelAccurateDepth foggyRMSE: 2.61 -> 2.55Improved
Finetune with clear PixelAccurateDepth dataFoggyStereo · PixelAccurateDepth foggyRMSE: 2.55 -> 1.74Improved
Use reversed atmospheric scattering render quality as depth evidence and fuse the resulting fog volume with the cost volumeFoggyStereo · Foggy scenes, including SceneFlow, KITTI, and PixelAccurateDepthdisparity errorImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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