AI Paper Atlas

Research map / 3D vision / Depth and stereo

Self-Supervised Learning With Geometric Constraints in Monocular Video: Connecting Flow, Depth, and Camera

Yuhua Chen, Cordelia Schmid, Cristian Sminchisescu

ICCV 2019 · 3D vision › Depth and stereo · approach: Foundation models for monocular geometry · 270 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 adaptive photometric loss (ablation)standard photometric baseline · KITTI Eigen depthAbs Rel: 0.156 -> 0.144Improved
add multi-view structure consistency loss (ablation)L_apc · KITTI Eigen depthAbs Rel: 0.144 -> 0.138Improved
add epipolar constraint loss (ablation)L_apc + L_mvs · KITTI Eigen depthAbs Rel: 0.138 -> 0.135Improved
add online refinement (ablation)L_apc + L_mvs + L_e · KITTI Eigen depthAbs Rel: 0.135 -> 0.099Improved
add online refinement (ablation)L_apc + L_mvs · KITTI Eigen depthAbs Rel: 0.138 -> 0.103Improved
add output-space regularizer to finetuning (ablation)standard parameter finetuning · KITTI Eigen depth (refinement)Abs RelImproved
use output finetuning instead of parameter finetuning (ablation)online refinement · KITTI Eigen depth (refinement)speed: 2 seconds vs 40 seconds for 50 iterationsNo clear effect
combine PFT and OFT (ablation)PFT alone · KITTI Eigen depth (refinement)Abs RelImproved
add epipolar constraint loss to flow training (ablation)L_apc + L_mvs · KITTI 2015 flow (train set)EPE All: 12.20 -> 8.95Improved
add adaptive photometric and multi-view losses (ablation)flow baseline · KITTI 2015 flow (train set)EPE All: 12.28 -> 12.20No clear effect
add online refinement (ablation)flow with all losses · KITTI 2015 flow (train set)EPE All: 8.95 -> 8.35Improved
predict intrinsics instead of using ground-truth calibration (ablation)GLNet depth (KITTI-trained) · KITTI Eigen depthAbs Rel: 0.099 -> 0.100No clear effect

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