AI Paper Atlas

Research map / 3D vision / Depth and stereo

RDFC-GAN: RGB-Depth Fusion CycleGAN for Indoor Depth Completion

Haowen Wang, Zhengping Che, Yufan Yang, Mingyuan Wang, Zhiyuan Xu, Xiuquan Qiao, Mengshi Qi, Feifei Feng, Jian Tang

TPAMI 2024 · 3D vision › Depth and stereo · approach: Dense depth prediction and completion · 16 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 CycleGAN consistency over a plain GAN (ablation)RDFC-GAN · NYU-Depth V2 (Setting A)RMSE: 0.129 -> 0.120Improved
add a GAN branch to the dual encoder-decoder (ablation)RDFC-GAN · NYU-Depth V2 (Setting A)RMSE: 0.176 -> 0.129Improved
fine-tune the pretrained normal generator on NYU-Depth V2 (ablation)MCN branch · NYU-Depth V2 (Setting A)RMSE: 0.147 -> 0.132Improved
add Manhattan constraint losses via segmentation network (MNM) over fine-tuned normal generator (ablation)MCN branch · NYU-Depth V2 (Setting A)RMSE: 0.132 -> 0.120Improved
replace Local Guidance with Manhattan Normal Module (ablation)RDFC-GAN · NYU-Depth V2 (Setting A)RMSE: 0.146 -> 0.120Improved
add segmentation features as extra input to the normal generator (ablation)Manhattan Normal Module · NYU-Depth V2 (Setting A)RMSE: 0.120 -> 0.122Hurt
add wall loss to normal loss (ablation)MCN branch · NYU-Depth V2 (Setting A)RMSE: 0.132 -> 0.123Improved
add floor, ceiling and wall losses together (ablation)MCN branch · NYU-Depth V2 (Setting A)RMSE: 0.132 -> 0.120Improved
use W-AdaIN fusion instead of instance normalization (ablation)RDFC-GAN · NYU-Depth V2 (Setting A)RMSE: 0.126 -> 0.120Improved
use W-AdaIN fusion instead of plain AdaIN (ablation)RDFC-GAN · NYU-Depth V2 (Setting A)RMSE: 0.133 -> 0.120Improved
feed RDFC-GAN completed depth to detector instead of original inputVoteNet · SUN RGB-DmAP@25: 59.07 -> 61.02Improved
feed NLSPN completed depth to detectorH3DNet · SUN RGB-DmAP@25: 60.11 -> 27.10Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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