AI Paper Atlas

Research map / 3D vision / Depth and stereo

Adaptive Surface Normal Constraint for Depth Estimation

Xiaoxiao Long, Cheng Lin, Lingjie Liu, Wei Li, Christian Theobalt, Ruigang Yang, Wenping Wang

ICCV 2021 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth · 81 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 L1-only training with L1 plus ASN constraint (ablation)depth network (HRNet-18) · NYUD-V2recovered normal mean angle error: 31.3 -> 22.2Improved
use ASN instead of Sobel-like normal constraint (ablation)depth network (HRNet-18) · NYUD-V2rel: 0.118 -> 0.111Improved
use ASN instead of least-square normal constraint (ablation)depth network (HRNet-18) · NYUD-V2rel: 0.119 -> 0.111Improved
add Sobel-like normal constraint to L1 loss (ablation)depth network (HRNet-18) · NYUD-V2rel: 0.113 -> 0.118Hurt
add least-square normal constraint to L1 loss (ablation)depth network (HRNet-18) · NYUD-V2rel: 0.113 -> 0.119Hurt
add virtual normal constraint to L1 loss (ablation)depth network (HRNet-18) · NYUD-V2recovered normal mean angle error: 31.3 -> 31.7No clear effect
use ASN instead of virtual normal (ablation)depth network (HRNet-18) · NYUD-V2recovered normal mean angle error: 31.7 -> 22.2Improved
add geometric context adaption to area adaption (ablation)ASN · NYUD-V2recovered normal mean angle error: 22.6 -> 22.2Improved
add area adaption to geometric context adaption (ablation)ASN · NYUD-V2recovered normal mean angle error: 22.3 -> 22.2Improved
increase local patch size from 3 to 7 (ablation)ASN · NYUD-V2recovered normal mean angle error: 22.5 -> 22.2No clear effect
increase number of sampled triplets (ablation)ASN · NYUD-V2recovered normal accuracyImproved
use area weighting instead of simple average of candidates (ablation)ASN · synthetic noisy semi-spheremean angle errorImproved

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