AI Paper Atlas

Research map / Detection and segmentation / CNN features

SplitHDR: Saturation-Aware HDR Recovery and Denoising for Real-Time Detection

Jaewon Kim, Sol Namkung, Dongsuk Jeon

ECCV 2026 · Detection and segmentation › CNN features · approach: Context for hard detection conditions · 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
extend input stack from two to three exposures (ablation)SplitHDR C1 · ROD synthetic HDR benchmark (ablation)PSNR-µ: 40.67 -> 40.93Improved
extend input stack from two to three exposures (ablation)SplitHDR C1 · ROD synthetic HDR benchmark (ablation)AP: 37.88 -> 37.68Hurt
add dual-mode configuration with full model always executed (ablation)SplitHDR C2 · ROD synthetic HDR benchmark (ablation)PSNR-µ: 40.93 -> 44.01Improved
add dual-mode configuration with full model always executed (ablation)SplitHDR C2 · ROD synthetic HDR benchmark (ablation)AP: 37.68 -> 37.80No clear effect
add masked supervision to dual-mode (ablation)SplitHDR C3 · ROD synthetic HDR benchmark (ablation)AP: 37.80 -> 38.38Improved
add masked supervision to dual-mode (ablation)SplitHDR C3 · ROD synthetic HDR benchmark (ablation)PSNR-µ: 44.01 -> 44.96Improved
add saturation-aware conditional execution (ablation)SplitHDR C4 · ROD synthetic HDR benchmark (ablation)GMACs: 10.23 -> 3.63Improved
add saturation-aware conditional execution (ablation)SplitHDR C4 · ROD synthetic HDR benchmark (ablation)AP: 38.38 -> 38.38No clear effect
use soft mask instead of binary mask at 90% threshold (ablation)SplitHDR · ROD synthetic HDR benchmark (mask/threshold sweep)AP: 38.35 -> 38.38Improved
raise saturation threshold from 90% to 99% (ablation)SplitHDR soft mask · ROD synthetic HDR benchmark (mask/threshold sweep)AP: 38.38 -> 37.75Hurt
use 128x128 tiles with conditional execution vs without (ablation)SplitHDR · ROD synthetic HDR benchmark (tile size)Total latency (ms): 17.70 -> 15.24Improved
use 32x32 tiles instead of 128x128 (ablation)SplitHDR · ROD synthetic HDR benchmark (tile size)Total latency (ms): 15.24 -> 21.24Hurt

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