AI Paper Atlas

Research map / Image generation / Super-resolution

CARA: Collision-Aware Resolution Adaptation for Multiresolution Hash Encoding Based Image Fitting

Linfeng Ye, Zhixiang Chi, Shayan Mohajer Hamidi, En-Hui Yang, Konstantinos Plataniotis

ECCV 2026 · Image generation › Super-resolution · approach: Perceptual and real-world SR · 0 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 collision factor w_hash to the resolution schedule (ablation)CARA · KodakPSNR (dB): 40.32 -> 41.03Improved
use entropy instead of l2 energy as information proxy (ablation)CARA · KodakPSNR (dB): 38.52 -> 41.03Improved
use entropy instead of variance as information proxy (ablation)CARA · KodakPSNR (dB): 38.74 -> 41.03Improved
replace analytic uniform-hash factor with empirical occupancy ratio (ablation)CARA · KodakPSNR (dB): 41.03 -> 41.07No clear effect
replace analytic uniform-hash factor with empirical occupancy ratio (ablation)CARA · Tokyo gigapixelPSNR (dB): 37.22 -> 37.17No clear effect
use anti-aliased resizing instead of Gaussian low-pass (ablation)CARA · KodakPSNR (dB): 40.07 -> 41.03Improved
use anti-aliased resizing instead of Gaussian low-pass (ablation)CARA · PlutoPSNR (dB): 62.52 -> 64.32Improved
use Butterworth instead of anti-aliased resizing (ablation)CARA · KodakPSNR (dB): 41.03 -> 41.22No clear effect
add pixel shuffle s=2 at ~6.6M params (ablation)CARA · Tokyo gigapixelPSNR (dB): 18.69 -> 24.64Improved
add pixel shuffle s=2 at ~24M params (ablation)CARA · Tokyo gigapixelPSNR (dB): 26.38 -> 31.76Improved
add pixel shuffle s=2 at ~91-93M params (ablation)CARA · Tokyo gigapixelPSNR (dB): 35.52 -> 34.66Hurt
add pixel shuffle s=2 at ~239-248M params (ablation)CARA · Tokyo gigapixelPSNR (dB): 39.73 -> 37.74Hurt

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