AI Paper Atlas

Research map / 3D vision / Depth and stereo

Lookup Table meets Local Laplacian Filter: Pyramid Reconstruction Network for Tone Mapping

Feng Zhang, Ming Tian, Zhiqiang Li, Bin Xu, Qingbo Lu, Changxin Gao, Nong Sang

NeurIPS 2023 · 3D vision › Depth and stereo · approach: Snapshot hyperspectral imaging · 3 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 pixel-level weight maps for basis 3D LUT fusion (ablation)3D LUT baseline · HDR+ 480pPSNR: 23.16 -> 24.41Improved
replace CNN backbone with tiny transformer (ablation)LUT + weight map · HDR+ 480pPSNR: 24.41 -> 25.34Improved
add image-adaptive learnable local Laplacian filter (ablation)LUT + weight map + transformer · HDR+ 480pPSNR: 25.34 -> 26.62Improved
add weight map (ablation)3D LUT baseline · HDR+ 480pDelta E: 7.04 -> 6.23Improved
add learnable Laplacian filter (ablation)LUT + weight map + transformer · HDR+ 480pLPIPS: 0.101 -> 0.063Improved
increase low-frequency image resolution 64x64 to 256x256 (ablation)full model · HDR+ 480pPSNR: 26.62 -> 26.81Improved
increase I_low resolution 64x64 to 128x128 (ablation)full model · HDR+ 480pPSNR: 26.62 -> 26.69Improved
reduce I_low from 256x256 to 64x64 for 30% less compute (ablation)full model · HDR+ 480pPSNR: 26.81 -> 26.62No clear effect
use image-level 3D LUT + Laplacian pyramid (Ours) over sLUTsLUT · HDR+ originalPSNR: 23.98 -> 25.32Improved
Ours over sLUT at 480psLUT · HDR+ 480pPSNR: 26.13 -> 26.62Improved
Ours over CSRNet on FiveKCSRNet · MIT-FiveK 480pLPIPS: 0.052 -> 0.055Hurt
Ours over CSRNet on FiveKCSRNet · MIT-FiveK 480pPSNR: 25.31 -> 25.53Improved

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