AI Paper Atlas

Research map / 3D vision / Depth and stereo

GEDepth: Ground Embedding for Monocular Depth Estimation

Xiaodong Yang, Zhuang Ma, Zhiyu Ji, Zhe Ren

ICCV 2023 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth · 46 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
plug GEDepth-Adaptive into DepthFormer, PixelFormer, BinsFormer, BTSdepth networks · KITTIAbs Rel: 0.052 -> 0.048 (DepthFormer)Improved
use GEDepth-Adaptive instead of Vanilla (model slope) (ablation)GEDepth · KITTI sloping-scene subsetAbs Rel: 0.064 -> 0.057Improved
add GEDepth-Vanilla to PixelFormer on KITTI (ablation)PixelFormer · KITTIRMSE: 2.081 -> 2.071No clear effect
add ground embedding for cross-dataset transfer KITTI to DDADDepthFormer · KITTI to DDADAbs Rel: 0.644 -> 0.261Improved
add ground embedding for cross-dataset transfer DDAD to KITTIDepthFormer · DDAD to KITTIAbs Rel: 0.149 -> 0.104Improved
add ground embedding, evaluate ground vs non-ground (ablation)DepthFormer · KITTIAbs Rel: ground 0.032 -> 0.028; non-ground 0.078 -> 0.074Improved
embed ground depth in the input instead of the encoder (ablation)GEDepth-Adaptive · KITTIAbs Rel: 0.049 -> 0.048Improved
vary ground slope range and binning (ablation)GEDepth-Adaptive · KITTIAbs Rel: 0.048 to 0.049No clear effect
vary classification loss weight lambda_cls (ablation)GEDepth-Adaptive · KITTIAbs Rel: 0.049 -> 0.048 at 0.10No clear effect
add GEDepth to DepthFormer for computeDepthFormer · KITTIinference latency: 179ms -> 185msHurt

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