AI Paper Atlas

Research map / 3D vision / Depth and stereo

Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance

Marvin Klingner, Jan-Aike Termhlen, Jonas Mikolajczyk, Tim Fingscheidt

ECCV 2020 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth · 399 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 multi-task training of depth and segmentation (summed losses) (ablation)SGDepth · KITTI splitAbs Rel: 0.108 -> 0.105Improved
add gradient scaling at the encoder (ablation)SGDepth multi-task · KITTI splitAbs Rel: 0.105 -> 0.102Improved
add semantic masking of all DC objects (ablation)SGDepth multi-task + scaled gradients · KITTI splitAbs Rel: 0.102 -> 0.106Hurt
add threshold to learn from non-moving DC objects (ablation)SGDepth with semantic mask · KITTI splitAbs Rel: 0.106 -> 0.099Improved
add scheduling of fraction epsilon for unmasked images (ablation)SGDepth add threshold · KITTI splitAbs Rel: 0.099 -> 0.097Improved
add depth training to segmentation (joint training) (ablation)SGDepth segmentation · KITTI splitmIoU on KITTI: 43.1 -> 51.6Improved
add depth training to segmentation (joint training) (ablation)SGDepth segmentation · Cityscapes validationmIoU: 63.3 -> 68.2Improved
add semantic guidance (SGDepth full vs only depth) (ablation)SGDepth · KITTI Eigen split (640x192)Abs Rel: 0.117 -> 0.113Improved
add semantic guidance (SGDepth full vs only depth) (ablation)SGDepth · KITTI Eigen split (1280x384)Abs Rel: 0.113 -> 0.107Improved
add semantic guidance (SGDepth full vs only depth) (ablation)SGDepth · KITTI Eigen split (416x128)Abs Rel: 0.128 -> 0.121Improved
replace ResNet18 encoder with ResNet50SGDepth full · KITTI splitmIoU on KITTI: 50.1 -> 54.2Improved
add semantic-guided joint training (full vs only depth) on pose estimation (ablation)SGDepth · KITTI odometry sequence 9ATE: 0.017 -> 0.019Hurt

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