AI Paper Atlas

Research map / 3D vision / Depth and stereo

T2Net: Synthetic-to-Realistic Translation for Solving Single-Image Depth Estimation Tasks

Chuanxia Zheng, Tat-Jen Cham, Jianfei Cai

ECCV 2018 · 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
add unpaired real images with translation and GAN losses (full T2Net vs synthetic-only)depth network f_T · KITTI Eigen splitAbs Rel: 0.278 -> 0.169Improved
add unpaired real images with translation and GAN losses (full T2Net vs synthetic-only)depth network f_T · NYUDv2Abs Rel: 0.304 -> 0.257Improved
train translation and task networks end-to-end rather than separately (ablation)T2Net · KITTI Eigen splitAbs Rel: 0.234 -> 0.169Improved
add reconstruction loss on real images (ablation)T2Net · KITTI Eigen splitAbs Rel: 0.201 -> 0.169Improved
add the feature-level GAN loss D_feat (ablation)T2Net · KITTI Eigen splitAbs Rel: 0.168 -> 0.169No clear effect
add the feature-level GAN loss D_feat to the image GAN (ablation)T2Net · NYUDv2Abs Rel: 0.274 -> 0.257Improved
add the image GAN loss (ablation)T2Net · KITTI Eigen splitAbs Rel: 0.233 -> 0.169Improved
use image GAN alone instead of feature GAN alone (ablation)T2Net · NYUDv2Abs Rel: 0.320 -> 0.274Improved
use target-domain reconstruction with unidirectional translation instead of separately trained CycleGAN (ablation)T2Net · KITTI Eigen splitAbs Rel: 0.212 -> 0.169Improved
use target-domain reconstruction on real images instead of self-domain reconstruction on synthetic images (ablation)T2Net · KITTI Eigen splitAbs Rel: 0.199 -> 0.169Improved
use the proposed task network instead of a vanilla task network (synthetic only) (ablation)f_T · KITTI Eigen splitAbs Rel: 0.295 -> 0.278Improved
use the proposed task network instead of a vanilla task network (full approach) (ablation)T2Net · KITTI Eigen splitAbs Rel: 0.259 -> 0.169Improved

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