AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Unsupervised Monocular Depth Estimation for Night-time Images using Adversarial Domain Feature Adaptation

Madhu Vankadari, Sourav Garg, Anima Majumder, Swagat Kumar, Ardhendu Behera

ECCV 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 68 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
apply ADFA to a day-trained Monodepth2 instead of training Monodepth2 on night imagesMonodepth2 · Oxford RobotCar night-time (60m)Abs Rel: 0.3990 -> 0.2327Improved
apply ADFA instead of Cycle-GAN image translationday-time depth network · Oxford RobotCar night-time (60m)Abs Rel: 0.7587 -> 0.2327Improved
apply ADFA instead of a day-trained Monodepth2 tested at nightMonodepth2 · Oxford RobotCar night-time (60m)RMSE: 14.253 -> 10.089Improved
pretrain the day model on Oxford instead of KITTI (ablation)ADFA · Oxford RobotCar night-time (60m)Abs Rel: 0.3589 -> 0.2327Improved
pretrain the day model on Oxford instead of KITTI (ablation)ADFA · Oxford RobotCar night-time (40m)delta<1.25: 0.495 -> 0.735Improved
skip the first conv layer's day-encoder features in adversarial learning (ablation)ADFA · Oxford RobotCar night-time (40m)Abs Rel: 0.2071 -> 0.2038Improved
skip the first two conv layers' day-encoder features (ablation)ADFA · Oxford RobotCar night-time (40m)Abs Rel: 0.2071 -> 0.2005Improved
skip the first three conv layers' day-encoder features (ablation)ADFA · Oxford RobotCar night-time (40m)Abs Rel: 0.2005 -> 0.2260Hurt
skip the first three instead of two conv layers' features (ablation)ADFA · Oxford RobotCar night-time (40m)Sq Rel: 2.575 -> 2.574No clear effect
use Cycle-GAN translation instead of training Monodepth2 on night imagesMonodepth2 · Oxford RobotCar night-time (60m)Abs Rel: 0.3990 -> 0.7587Hurt

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