AI Paper Atlas

Research map / 3D vision / Depth and stereo

Hierarchical Normalization for Robust Monocular Depth Estimation

Chi Zhang, Wei Yin, Billzb Wang, Gang YU, BIN FU, Chunhua Shen

NeurIPS 2022 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth · 8 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
replace instance-level normalization with HDN-DR (ablation)DPT-Hybrid depth model · 5 zero-shot benchmarks (16K train)AbsRel: -22% mean errorImproved
use batch-level instead of instance-level normalization (ablation)DPT-Hybrid depth model · 5 zero-shot benchmarksAbsRel: 15% mean worseHurt
use only finest local normalization (Local-S) (ablation)depth model · KITTIAbsRel: 13.2 -> 19.3Hurt
use only finest local normalization (Local-DP) (ablation)depth model · KITTIAbsRel: 13.2 -> 23.3Hurt
use only local normalization (Local-DR) (ablation)depth model · DIODEAbsRel: 47.1 -> 25.7Improved
use HDN-S instead of instance normalization (ablation)depth model · DIODEAbsRel: 47.1 -> 36.4Improved
use HDN-DP instead of instance normalization (ablation)depth model · KITTIAbsRel: 13.2 -> 13.2No clear effect
remove random crop from training (ablation)instance-level normalization baseline · 16K ablationoverall AbsRelHurt
use aggressive random crop (1/8, 1/4) with instance normalization (ablation)instance-level baseline · 16K ablationoverall AbsRelHurt
add more fine-grained normalization levels (ablation)HDN · 16K ablationAbsRelMixed
add HDN auxiliary loss to L1regression model · NYU V2 fully supervisedAbsRel: 14.7 -> 13.3Improved
add SSI loss to L1regression model · NYU V2 fully supervisedAbsRel: 14.7 -> 14.6No clear effect

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