AI Paper Atlas

Research map / 3D vision / Depth and stereo

Semi-Supervised Adversarial Monocular Depth Estimation

Rongrong Ji, Ke Li, Yan Wang, Xiaoshuai Sun, Feng Guo, Xiaowei Guo, Yongjian Wu, Feiyue Huang, Jiebo Luo

TPAMI 2019 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth · 61 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 pair discriminator and depth discriminator together (vs depth discriminator only) (ablation)semi-supervised GAN loss · NYU Depth v2 (500 GT)rel: 0.191 -> 0.183Improved
add semi-supervised GAN loss vs L1 supervised lossHu et al. generator · NYU Depth v2 (500 GT)rel: 0.201 -> 0.183Improved
add semi-supervised framework to Hu et al.Hu et al. · NYU Depth v2 (100 GT)rel: 0.322 -> 0.232Improved
add semi-supervised framework to FCRNFCRN · NYU Depth v2 (500 GT)rel: 0.272 -> 0.254Improved
add semi-supervised framework to UnetUnet · NYU Depth v2 (1000 GT)rel: 0.365 -> 0.369No clear effect
add unlabeled RGB images beyond 10x the labeled pairs (ablation)semi-supervised model · NYU Depth v2 (500 GT)depth accuracy: gain saturates after 10 times more RGB imagesNo clear effect
add unlabeled RGB images within 1/2k to 10k range (ablation)semi-supervised model · NYU Depth v2 (500 GT)depth accuracyImproved
use semi-supervised framework with abundant labeled data (>3.5K pairs)semi-supervised model · NYU Depth v2depth accuracyNo clear effect
add 425 unlabeled RGB images in semi-supervised trainingOurs-GAN · Make3Drel: 0.158 -> 0.153Improved
add 20k Cityscape RGB imagesOurs-GAN · KITTI Eigen splitrel: 0.107 -> 0.093Improved
add 400 unlabeled Make3D RGB images in training (domain adaptation)Ours · KITTI to Make3Drel: 0.555 -> 0.447Improved
use GAN loss with sufficient data (12K) vs Zhang et al.Ours · NYU Depth v2 (12K GT)delta1: 0.824 -> 0.851Mixed

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