AI Paper Atlas

Research map / 3D vision / Depth and stereo

Revealing the Reciprocal Relations Between Self-Supervised Stereo and Monocular Depth Estimation

Zhi Chen, Xiaoqing Ye, Wei Yang, Zhenbo Xu, Xiao Tan, Zhikang Zou, Errui Ding, Xinming Zhang, Liusheng Huang

ICCV 2021 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth · 38 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
use Unet encoding instead of pyramid encoding in StereoNet (ablation)StereoNet · KITTI 2015 training (stereo, after stage 1)Abs Rel: 0.054 -> 0.052Improved
use Unet encoding instead of pyramid encoding in StereoNet (ablation)StereoNet · KITTI 2015 training (stereo, after stage 1)Sq Rel: 0.629 -> 0.558Improved
add occlusion-aware fusion of StereoNet and SingleNetStereoNet · KITTI 2015 training (stereo depth)Abs Rel: 0.052 -> 0.049Improved
distill fused disparity back into StereoNet (StereoNet-D)StereoNet · KITTI 2015 training (stereo depth)Abs Rel: 0.052 -> 0.048Improved
distill from StereoNet with occlusion-aware masking instead of self-supervision (ablation)SingleNet · KITTI Eigen split (monocular depth)Abs Rel: 0.102 -> 0.095Improved
distill from StereoNet instead of SGM proxy labels (ablation)SingleNet · KITTI Eigen split (monocular depth)Abs Rel: 0.100 -> 0.095Improved
set occlusion threshold alpha to 0.01 instead of 1 in distillation (ablation)SingleNet · KITTI (SingleNet, stereo split, alpha ablation)Abs Rel: 0.086 -> 0.083Improved
set occlusion threshold alpha to 0.01 instead of 1 in fusion (ablation)OA Fusion · KITTI 2015 training (fusion, alpha ablation)Abs Rel: 0.052 -> 0.049Improved
add post-processing at test timeSingleNet · KITTI Eigen split (monocular depth)Abs Rel: 0.095 -> 0.094Improved
use StereoNet with Unet encoding instead of UnOS stereo-onlyUnOS (Stereo-only) · KITTI 2015 training (stereo depth)Abs Rel: 0.060 -> 0.052Improved

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