AI Paper Atlas

Research map / 3D vision / Depth and stereo

AGG-Net: Attention Guided Gated-Convolutional Network for Depth Image Completion

Dongyue Chen, Tingxuan Huang, Zhimin Song, Shizhuo Deng, Tong Jia

ICCV 2023 · 3D vision › Depth and stereo · approach: Dense depth prediction and completion · 18 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 color features via concatenation to depth-only baseline (ablation)UNet-like depth completion · NYU-Depth V2RMSE: 0.136 -> 0.122Improved
replace vanilla convolution with gated convolution and De-GConv (ablation)concat-fusion UNet · NYU-Depth V2RMSE: 0.122 -> 0.115Improved
replace GConv with AG-GConv (contextual attention from depth and color) (ablation)AGG-Net · NYU-Depth V2RMSE: 0.115 -> 0.105Improved
add AG-SC module on color skip connection (ablation)GConv concat model · NYU-Depth V2RMSE: 0.115 -> 0.103Improved
add AG-SC on top of AG-GConv (ablation)AGG-Net · NYU-Depth V2RMSE: 0.105 -> 0.092Improved
add pre-filling network (ablation)AGG-Net · NYU-Depth V2RMSE: 0.105 -> 0.092Improved
replace MSE with Huber loss (ablation)AGG-Net · NYU-Depth V2RMSE: 0.104 -> 0.100Improved
add edge persistence loss to Huber loss (ablation)AGG-Net · NYU-Depth V2RMSE: 0.100 -> 0.092Improved
increase encoder layers beyond m=4AGG-Net · NYU-Depth V2RMSENo clear effect
use kernel size larger than 3AGG-Net · NYU-Depth V2RMSEHurt
increase CA hidden ratio beyond r=4AGG-Net · NYU-Depth V2RMSENo clear effect

Later papers that compared with this method

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

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