AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

DeFeat-Net: General Monocular Depth via Simultaneous Unsupervised Representation Learning

Jaime Spencer, Richard Bowden, Simon Hadfield

CVPR 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 100 citations (OpenAlex)

Check 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 jointly learned dense features to depth estimation (ablation)DeFeat · RobotCar NightAbs-Rel: 0.748 -> 0.335Improved
Add jointly learned dense features to depth estimation (ablation)DeFeat · RobotCar NightSq-Rel: 13.502 -> 4.339Improved
Add jointly learned dense features to depth estimation (ablation)DeFeat · RobotCar DayAbs-Rel: 0.274 -> 0.265Mixed
Add jointly learned dense features to depth estimation (ablation)DeFeat · KITTIAbs-Rel: 0.123 -> 0.126No clear effect
Train depth estimation with jointly learned featuresDeFeat · RobotCar NightAbs-Rel: 0.367 -> 0.335Improved
Train depth estimation with jointly learned featuresDeFeat · KITTIAbs-Rel: 0.123 -> 0.126Hurt

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