Research map / Image generation / Editing and style transfer
Hist2Style: Histogram-Guided Stylization with Bilateral Grids
Dekel Galor, Adam Pikielny, Zhoutong Zhang, Ke Wang, Laura Waller, Jiawen Chen, Ilya Chugunov
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 changed | Where | Measured | Effect |
|---|---|---|---|
| apply the loss in perceptual (VGG) space instead of raw color space (ablation) | Hist2Style · Unsplash style transfer | fidelity / color richness and contrast (qualitative) | Improved |
| train with the true target histogram instead of a histogram from another image of the same style (ablation) | Hist2Style · Unsplash style transfer | color accuracy (qualitative) | Improved |
| Hist2Style vs PhotoWCT2 in a pairwise user study | Hist2Style · User study | H2S win %: 61.62% win, 6.26% tie, 32.12% lose | Improved |
| Hist2Style vs SA-LUT in a pairwise user study | Hist2Style · User study | H2S win %: 82.57% win, 3.56% tie, 13.86% lose | Improved |
| Hist2Style vs Xia et al. on SQA | Hist2Style · Stylization comparison | SQA: 24.12 -> 50.00 | Improved |
| Hist2Style vs Xia et al. on FID | Hist2Style · Stylization comparison | FID: 50.46 -> 71.44 | Hurt |
| Hist2Style vs PhotoWCT2 on color matching Y' | Hist2Style · Stylization comparison | Color matching W22 (Y'): 224.86 -> 387.30 | Hurt |
| Hist2Style vs PhotoWCT2 on cycle consistency | Hist2Style · Stylization comparison | Cycle consistency MSE: 1012.90 -> 401.92 | Improved |
| Hist2Style vs IDT on cycle consistency | Hist2Style · Stylization comparison | Cycle consistency MSE: 215.57 -> 401.92 | Hurt |
| Hist2Style vs Xia et al. runtime at 4096x4096 | Hist2Style · Runtime at 4096x4096 | runtime (s): 0.03 -> 0.1 | Hurt |
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.
- SA-LUT — SA-LUT: Spatial Adaptive 4D Look-Up Table for Photorealistic Style Transfer (ICCV 2025) · better on 4 of 4 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
- Joint Bilateral Learning for Real-time Universal Photorealistic Style Transfer (ECCV 2020 · similarity 0.88)
- Photorealistic Style Transfer via Wavelet Transforms (ICCV 2019 · similarity 0.88)
- Non-Local Representation Based Mutual Affine-Transfer Network for Photorealistic Stylization (TPAMI 2021 · similarity 0.88)
- CoCoDiff: Correspondence-Consistent Diffusion Model for Fine-grained Style Transfer (ICLR 2026 · similarity 0.87)
- TANGO: Text-driven Photorealistic and Robust 3D Stylization via Lighting Decomposition (NeurIPS 2022 · similarity 0.87)
- A Content Transformation Block for Image Style Transfer (CVPR 2019 · similarity 0.87)
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.
