AI Paper Atlas

Research map / 3D vision / Depth and stereo

RigNet: Repetitive Image Guided Network for Depth Completion

Zhiqiang Yan, Kun Wang, Xiang Li, Zhenyu Zhang, Jun Li, Jian Yang

ECCV 2022 · 3D vision › Depth and stereo · approach: Dense depth prediction and completion · 163 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
deepen single image-guidance backbone from ResNet-18 to 26/34/50 (ablation)GuideNet-style baseline · KITTI validationRMSE (mm): 779 -> 777No clear effect
replace ResNet-10 with ResNet-18 backbone (ablation)image guidance branch · KITTI validationRMSE (mm): 822 -> 779Improved
stack hourglass units in tandem (18-2/18-3/18-4) (ablation)image guidance branch · KITTI validationRMSE (mm): 779 -> 816Hurt
use deeper tandem hourglass units (Deeper-More) (ablation)image guidance branch · KITTI validationRMSE (mm): 779 -> 807Hurt
add parallel repetitive hourglass network (RHN 18-3) (ablation)baseline ResNet-18 · KITTI validationRMSE (mm): 779 -> 769Improved
replace raw guided convolution G1 with efficient guidance EG1 (ablation)RigNet · KITTI validationGPU memory (GB): +1.35 -> -10.60Improved
repeat efficient guidance twice (EG1,2) (ablation)RigNet · KITTI validationRMSE (mm): 768.6 -> 762.3Improved
repeat efficient guidance three times (EG1,2,3) (ablation)RigNet · KITTI validationRMSE (mm): 768.6 -> 757.4Improved
add fusion of repeated outputs by addition (ablation)RigNet (d) · KITTI validationRMSE (mm): 757.4 -> 755.8Improved
add adaptive fusion instead of addition or concatenation (ablation)RigNet (d) · KITTI validationRMSE (mm): 757.4 -> 752.1Improved
use efficient guidance instead of common dynamic convolutionguidance module · GPU memory in one fusion stagememory (GB): 42.75 -> 0.037Improved

Later papers that compared with this method

11 later accepted papers report RigNet as a baseline in their results tables; 9 of them report a better number on most of the results they share with it.

3 more not listed.

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