AI Paper Atlas

Research map / 3D vision / Depth and stereo

Adaptive Surface Normal Constraint for Geometric Estimation From Monocular Images

Xiaoxiao Long, Y. Zheng, Yupeng Zheng, Beiwen Tian, Cheng Chung Lin, Lingjie Liu, Hao Zhao, Guyue Zhou, Wenping Wang

TPAMI 2024 · 3D vision › Depth and stereo · approach: Foundation models for monocular geometry · 23 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 surface normal constraint instead of virtual normal (ablation)depth model with L1 (HRNet-18) · NYUD-V2recovered normal mean error: 31.7 -> 22.2Improved
add ASN constraint to L1 depth loss (ablation)HRNet-18 · NYUD-V2recovered normal mean error: 31.3 -> 22.2Improved
use Sobel-like or least-square normal constraint instead of ASN (ablation)depth model with L1 · NYUD-V2depth rel: 0.113 -> 0.118Hurt
add geometric context adaption to area adaption (ablation)ASN · NYUD-V2recovered normal mean error: 22.6 -> 22.2Improved
add area adaption to geometric context adaption (ablation)ASN · NYUD-V2recovered normal mean error: 22.3 -> 22.2Improved
increase local patch size from 3 to 7 (ablation)ASN · NYUD-V2recovered normal mean error: 22.5 -> 22.2No clear effect
replace HRNet-18 with HRNet-48 backbone (ablation)ASN · NYUD-V2depth rel: 0.111 -> 0.101Improved
replace HRNet-48 with DPT backbone (ablation)ASN · NYUD-V2depth delta1: 0.890 -> 0.908Improved
add first-order geometric context guidance to normal branch (ablation)normal estimation (DPT) · NYUD-V2predicted normal mean error: 15.40 -> 15.29No clear effect
add first-order geometric context guidance to normal branch (ablation)normal estimation (DPT) · SEVERSpredicted normal median error: 1.84 -> 1.39Improved
use second-order instead of first-order guidance (ablation)normal estimation (DPT) · NYUD-V2predicted normal mean error: 15.29 -> 15.30No clear effect
add normal prediction layer (ablation)depth model (DPT) · NYUD-V2recovered normal mean error: 19.9 -> 18.2Improved

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