AI Paper Atlas

Research map / Image generation / Image restoration

Image Reassembly Combining Deep Learning and Shortest Path Problem

Marie-Morgane Paumard, David Picard, Hedi Tabia

ECCV 2018 · Image generation › Image restoration · approach: Inverse imaging with learned priors · 35 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
fuse fragment features with Kronecker product instead of concatenation (ablation)relative position CNN · ImageNet val (8-class position)accuracy (%): 64.6% -> 66.4%Improved
fuse with Kronecker product instead of Hadamard low-rank approximation (ablation)relative position CNN · ImageNet val (8-class position)accuracy (%): 59.2% -> 66.4%Improved
use bilinear/Kronecker fusion network instead of Doersch et al. reproductionrelative position CNN · ImageNet val (8-class position)accuracy (%): 57.0% -> 66.4%Improved
solve the 9-class joint problem instead of the sequential 2-class then 8-class approachposition classifier · ImageNet valaccuracy (%): 66.4% -> 64.2%No clear effect
use Dijkstra shortest path instead of greedy assignment (ablation)reassembly, central known, complete puzzle · MET reassemblyreconstruction accuracy (%): 41.0 -> 44.4Improved
use Dijkstra instead of greedy when central fragment unknown (ablation)reassembly, central unknown · MET reassemblyreconstruction accuracy (%): 36.2 -> 39.2Improved
use Dijkstra instead of greedy with incomplete puzzle (ablation)reassembly, incomplete · MET reassemblyreconstruction accuracy (%): 26.5 -> 29.5Improved
use Dijkstra instead of greedy for position accuracy, central known (ablation)reassembly · MET reassemblyposition accuracy (%): 87.7 -> 89.9Improved
solve global assignment instead of per-fragment classifier outputreassembly · MET reassemblyposition accuracy (%): 66.4% -> around 90%Improved
make the central fragment unknownDijkstra reassembly · MET reassemblyreconstruction accuracy (%): 44.4 -> 39.2Hurt
add one outsider fragment to the puzzleDijkstra reassembly · MET reassemblyreassembly accuracy (%): 44.4% -> 26.3%Hurt
add two outsider fragments to the puzzleDijkstra reassembly · MET reassemblyreassembly accuracy (%): 44.4% -> 14.3%Hurt

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