AI Paper Atlas

Research map / 3D vision / Depth and stereo

Indoor Depth Recovery Based on Deep Unfolding with Non-Local Prior

Yuhui Dai, Junkang Zhang, Faming Fang, Guixu Zhang

ICCV 2023 · 3D vision › Depth and stereo · approach: Dense depth prediction and completion · 3 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 the non-local auto-regressive (NLAR) module (ablation)DC-NLAR · NYU-Depth V2RMSE: 0.108 -> 0.102Improved
add diagonal gradient loss Lgrad (ablation)DC-NLAR · NYU-Depth V2RMSE: 0.103 -> 0.102Improved
use learned convolutional DC module instead of explicit 0/1 fidelity term (ablation)DC-NLAR · NYU-Depth V2RMSE: 0.103 -> 0.102Improved
add NLAR, Lgrad and DC on top of the recovery module (ablation)Recovery module baseline · NYU-Depth V2RMSE: 0.115 -> 0.102Improved
vary NLAR patch size (7, 9, 11) (ablation)DC-NLAR · NYU-Depth V2RMSE: 0.102 / 0.102 / 0.103No clear effect
increase unrolling stages from 4 to 6 (ablation)DC-NLAR · NYU-Depth V2RMSE: 0.102 -> 0.109Hurt
reduce unrolling stages from 4 to 2 (ablation)DC-NLAR · NYU-Depth V2RMSE: 0.102 -> 0.107Hurt
DC-NLAR versus best prior method NLSPNNYU-Depth V2 comparison · NYU-Depth V2RMSE: 0.092 -> 0.102Hurt

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