AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

DeepMatching: Hierarchical Deformable Dense Matching

Jérôme Revaud, Philippe Weinzaepfel, Zaïd Harchaoui, Cordelia Schmid

IJCV 2016 · Probabilistic and scientific modeling › Molecules and proteins · approach: Flow matching generative modeling · 280 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 the new scoring (sum of correlations along backtracking path) (ablation)DeepMatching R=1/2 · Mikolajczyk (viewpoint sequences)accuracy@10: 0.848 -> 0.864Improved
add new backtracking entry points (all top-level positions) (ablation)DeepMatching R=1/2 with new scoring · Mikolajczyk (viewpoint sequences)accuracy@10: 0.864 -> 0.878Improved
add the new scoring (sum of correlations along backtracking path) (ablation)DeepMatching R=1/2 · MPI-Sintel final (train)accuracy@10: 0.880 -> 0.890Improved
add new backtracking entry points (all top-level positions) (ablation)DeepMatching R=1/2 with new scoring · MPI-Sintel final (train)accuracy@10: 0.890 -> 0.892Improved
add the new scoring (sum of correlations along backtracking path) (ablation)DeepMatching R=1/2 · Kitti (train)accuracy@10: 0.841 -> 0.855Improved
add new backtracking entry points (all top-level positions) (ablation)DeepMatching R=1/2 with new scoring · Kitti (train)accuracy@10: 0.855 -> 0.856Improved
increase input resolution from 1/4 to 1/2DeepMatching (preliminary) · Mikolajczyk (viewpoint sequences)accuracy@10: 0.620 -> 0.848Improved
increase input resolution from 1/4 to 1/2DeepMatching (preliminary) · MPI-Sintel final (train)accuracy@10: 0.822 -> 0.880Improved
use new backtracking entry points to cut cost (ablation)DeepMatching R=1/2 with new scoring · Mikolajczyk (viewpoint sequences)memory usage: 5.5 GB -> 4.4 GBImproved
compress atomic patches with a 1024-prototype dictionaryDeepMatching R=1/2 · MPI-Sintel final (train)accuracy@10: 0.892 -> 0.869Hurt
compress atomic patches with a 1024-prototype dictionaryDeepMatching R=1/2 · Kitti (train)accuracy@10: 0.856 -> 0.812Hurt
compress atomic patches with a 1024-prototype dictionaryDeepMatching R=1/2 · Mikolajczyk (viewpoint sequences)accuracy@10: 0.878 -> 0.820Hurt

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