AI Paper Atlas

Research map / 3D vision / Depth and stereo

Kick Back & Relax: Learning to Reconstruct the World by Watching SlowTV

Jaime Spencer, Chris Russell, Simon Hadfield, Richard Bowden

ICCV 2023 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth · 19 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
train self-supervised depth on the SlowTV dataset plus Mannequin Challenge and Kitti instead of automotive data onlySS-MDE (ConvNeXt-B) · zero-shot outdoor and indoor datasetsdepth accuracy (AbsRel, delta, F-score)Improved
leave-one-out removal of aspect ratio augmentation, learned intrinsics, random support frames or flexible pose (ablation)full SlowTV model · Kitti, Mannequin Challenge, SYNSdepth accuracyImproved
learn camera intrinsics with the pose network instead of using ground-truth (ablation)full SlowTV model · Kitti (calibrated)depth accuracyNo clear effect
learn camera intrinsics when ground truth intrinsics come from COLMAP (ablation)full SlowTV model · Mannequin Challengedepth accuracyImproved
add minimum reconstruction loss and automasking from Monodepth2 (ablation)monocular depth training · subset of three training datasetsdepth accuracyImproved
median alignment instead of scale-and-shift alignmentevaluation · all datasetsdepth accuracyHurt
self-supervised SlowTV model versus supervised SOTA on indoor datasetsSlowTV model · indoor datasetsdepth accuracyHurt
SlowTV-trained model on Map-free relocalization versus self-supervised baselinesSlowTV model · MapFreeReloc valrelocalization errorsImproved

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