AI Paper Atlas

Research map / 3D vision / Depth and stereo

Estimating Fog Parameters From a Sequence of Stereo Images

Yining Ding, João F. C. Mota, Andrew Michael Wallace, Sen Wang

TPAMI 2025 · 3D vision › Depth and stereo · approach: Learned stereo with specialized sensors · 0 citations (OpenAlex)

Read the paperCheck 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 second optimisation stage (inlier-only square loss) to Huber stage (ablation)Ours · KITTI-CARLAbeta RMSE (abs): 0.0122 -> 0.0116Improved
add second optimisation stage (ablation)Ours · KITTI-CARLAA RMSE (abs): 3.4662 -> 2.5711Improved
add radiance-difference and inlier-count residual weights instead of uniform (ablation)Ours · KITTI-CARLAbeta RMSE (abs): 0.0122 -> 0.0116Improved
add radiance-difference residual weights instead of uniform (ablation)Ours · KITTI-CARLAA RMSE (abs): 2.9282 -> 2.5711Improved
give ground-truth A to Li's methodLi's · KITTI-CARLAbeta RMSE (abs): 0.0499 -> 0.0357Improved
give ground-truth A to Li's modifiedLi's modified · KITTI-CARLAbeta RMSE (abs): 0.0166 -> 0.0109Improved
give ground-truth A to proposed methodOurs · KITTI-CARLAbeta RMSE (abs): 0.0116 -> 0.0099Improved
simultaneous estimation of beta and A instead of sequential (Li's modified)Ours · KITTI-CARLAbeta RMSE (abs): 0.0166 -> 0.0116Improved
simultaneous estimation vs Li's modified on AOurs · VKITTI2A RMSE (abs): 1.5921 -> 2.5495Hurt
simultaneous estimation vs Li's modified on betaOurs · VKITTI2beta RMSE (abs): 0.0113 -> 0.0078Improved
modify Li's method: median dark channel and bounded beta histogramLi's · DRIVINGbeta RMSE (abs): 0.0465 -> 0.0168Improved
modify Li's method: median dark channel and bounded beta histogramLi's · KITTI-CARLAbeta RMSE (abs): 0.0499 -> 0.0166Improved

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