AI Paper Atlas

Research map / 3D vision / Depth and stereo

GraphCSPN: Geometry-Aware Depth Completion via Dynamic GCNs

Xin Liu, Xiaofei Shao, Bo Wang, Yali Li, Shengjin Wang

ECCV 2022 · 3D vision › Depth and stereo · approach: Dense depth prediction and completion · 45 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 edge attention (ablation)GraphCSPN · NYU-Depth-v2 (500 samples)RMSE: 0.101 -> 0.090Improved
add geometry-aware neighborhood estimation (ablation)GraphCSPN · NYU-Depth-v2 (500 samples)RMSE: 0.113 -> 0.090Improved
add dynamic graph construction (ablation)GraphCSPN · NYU-Depth-v2 (500 samples)RMSE: 0.108 -> 0.090Improved
use L1 instead of smooth L1 loss (ablation)GraphCSPN · NYU-Depth-v2 (500 samples)RMSE: 0.102 -> 0.094Improved
use L1 instead of L2 loss (ablation)GraphCSPN · NYU-Depth-v2 (500 samples)RMSE: 0.104 -> 0.094Improved
add auxiliary loss on intermediate propagation outputs (ablation)GraphCSPN · NYU-Depth-v2 (500 samples)RMSE: 0.094 -> 0.090Improved
propagate from learned initial depth instead of raw input (ablation)GraphCSPN · NYU-Depth-v2 (500 samples)RMSE: 0.134 -> 0.090Improved
increase sparse input samples from 200 to 500 (ablation)GraphCSPN · NYU-Depth-v2 (500 samples)RMSE: 0.119 -> 0.090Improved
increase sparse input samples from 500 to 800 (ablation)GraphCSPN · NYU-Depth-v2 (500 samples)RMSE: 0.090 -> 0.082Improved
use 3 graph steps vs NLSPN 3 stepsGraphCSPN vs NLSPN · NYU-Depth-v2 (500 samples)RMSE: 0.119 -> 0.090Improved
use 3 graph steps vs NLSPN 3 stepsGraphCSPN vs NLSPN · KITTI (Eigen split, 3200 test images)RMSE: 2.697 -> 2.267Improved
compare GraphCSPN with NLSPN on test serverGraphCSPN · KITTI Depth Completion testRMSE: 741.68 -> 738.41No clear effect

Later papers that compared with this method

1 later accepted paper reports GraphCSPN as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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