AI Paper Atlas

Research map / 3D vision / Depth and stereo

Warp Consistency for Unsupervised Learning of Dense Correspondences

Prune Truong, Martin Danelljan, Fisher Yu, Luc Van Gool

ICCV 2021 · 3D vision › Depth and stereo · approach: Dense feature matching for correspondence · 50 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 warp-supervision term to W-bipath loss (ablation)W-bipath GLU-Net · MegaDepthPCK-1: 29.55 -> 39.66Improved
stop gradients through the flow used for warping (ablation)W-bipath GLU-Net · MegaDepthPCK-1: 20.06 -> 29.55Improved
add adaptive loss balancing instead of lambda=1 (ablation)WarpC GLU-Net · MegaDepthPCK-1: 39.66 -> 43.47Mixed
add visibility mask in second stage (ablation)WarpC GLU-Net · MegaDepthPCK-1: 43.47 -> 48.86Improved
sample harder warps with elastic transforms (ablation)WarpC GLU-Net · MegaDepthPCK-1: 48.86 -> 50.61Improved
use W-bipath instead of warp-supervision alone (ablation)GLU-Net · MegaDepthPCK-5: 57.21 -> 67.70Improved
combine W-bipath with warp-supervision (ablation)GLU-Net · MegaDepthPCK-5: 67.70 -> 69.90Improved
use I'J-bipath constraint as loss (ablation)GLU-Net · MegaDepthPCK-5: 0.05Hurt
use WarpC instead of SSIM loss (ablation)GLU-Net · MegaDepthPCK-5: 69.58 -> 78.61Improved
use WarpC unsupervised instead of sparse ground-truth supervision (ablation)GLU-Net · MegaDepthPCK-5: 72.42 -> 78.61Improved
fine-tune WarpC with sparse annotations (ablation)WarpC GLU-Net · MegaDepth vs RobotCarPCK-5: 78.61 -> 81.33 (MegaDepth); 35.92 -> 34.67 (RobotCar)Mixed
add SSIM photometric loss to WarpC (ablation)WarpC GLU-Net · MegaDepthPCK-1: 50.61 -> 54.92Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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