AI Paper Atlas

Research map / 3D vision / Depth and stereo

MODE: Multi-View Omnidirectional Depth Estimation with 360° Cameras

Ming Li, Xueqian Jin, Xuejiao Hu, Jingzhao Dai, Sidan Du, Yang Li

ECCV 2022 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth

Read the paper

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
train on full panoramas without random image cropping (ablation)MODE stereo network · Deep360 stereo matchingMAE: 0.3220 -> 0.2109Improved
train on full panoramas without random image cropping (ablation)MODE stereo network · Deep360 stereo matchingPx1 (%): 3.9787 -> 2.6509Improved
add spherical convolution in the feature extractor (ablation)MODE stereo network · Deep360 stereo matchingMAE: 0.2109 -> 0.2073Improved
add spherical convolution in the feature extractor (ablation)MODE stereo network · Deep360 stereo matchingPx1 (%): 2.6509 -> 2.6010Improved
add the multi-view depth fusion stage (ablation)MODE · Deep360 (Soiled)MAE: 15.2145 -> 4.4652Improved
add the multi-view depth fusion stage (ablation)MODE · Deep360 (Soiled)AbsRel: 0.1230 -> 0.0495Improved
replace stacked 2D conv baseline with encoder-decoder and skip connections (ablation)depth fusion network · Deep360 (Soiled)MAE: 6.8699 -> 6.2548Improved
add reference panoramas as fusion input (ablation)depth fusion network · Deep360 (Soiled)MAE: 6.2548 -> 4.2071Improved
add reference panoramas as fusion input (ablation)depth fusion network · Deep360 (Soiled)AbsRel: 0.0516 -> 0.0710Hurt
add confidence maps as fusion input (ablation)depth fusion network · Deep360 (Soiled)MAE: 4.2071 -> 4.4652Hurt
add confidence maps as fusion input (ablation)depth fusion network · Deep360 (Soiled)AbsRel: 0.0710 -> 0.0495Improved

Later papers that compared with this method

1 later accepted paper reports MODE as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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