Research map / Image generation / Image restoration
Learnable Feature Patches and Vectors for Boosting Low-light Image Enhancement without External Knowledge
Xiaogang Xu, Jiafei Wu, Qingsen Yan, Jiequan Cui, Richang Hong, Bei Yu
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 |
|---|---|---|---|
| add sample-updater (SU) when learning LFPVs (ablation) | SNR+LFPVs · SID | PSNR: 22.96 -> 23.15 | Improved |
| add mutual-updater (MU) when learning LFPVs (ablation) | SNR+LFPVs · SID | PSNR: 22.88 -> 23.15 | Improved |
| add identity embedding to LFPVs (ablation) | SNR+LFPVs · SID | PSNR: 22.94 -> 23.15 | Improved |
| place LFPVs in encoder instead of decoder (ablation) | SNR+LFPVs · SID | PSNR: 23.09 -> 23.15 | Improved |
| increase LFPVs from 8 to 16 (ablation) | SNR+LFPVs · SID | PSNR: 22.97 -> 23.15 | Improved |
| increase LFPVs from 16 to 32 (ablation) | SNR+LFPVs · SID | PSNR: 23.15 -> 23.29 | Improved |
| double layers of SU and MU (ablation) | SNR+LFPVs · SID | PSNR: 23.15 -> 23.30 | Improved |
| train SU with hard samples instead of random (ablation) | SNR+LFPVs · SID | PSNR: 23.15 -> 22.92 | Mixed |
| increase patch size from 4 to 8 (ablation) | SNR+LFPVs · SID | PSNR: 23.15 -> 22.81 | Mixed |
| train LLIE then LFPVs in order instead of jointly (ablation) | SNR+LFPVs · SID | PSNR: 23.15 -> 23.39 | Improved |
| implement SU and MU with LSTM instead of CNN (ablation) | SNR+LFPVs · SID | PSNR: 23.15 -> 23.85 | Improved |
| add LFPVs to Restormer | Restormer · SID | PSNR: 22.27 -> 23.60 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- RetinexFormer — Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement (ICCV 2023) · better on 1 of 1 shared result
- Restormer — Restormer: Efficient Transformer for High-Resolution Image Restoration (CVPR 2022) · better on 1 of 1 shared result
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
- Low-Light Image Enhancement with Multi-Stage Residue Quantization and Brightness-Aware Attention (ICCV 2023 · similarity 0.92)
- Low-Light Image and Video Enhancement Using Deep Learning: A Survey (TPAMI 2021 · similarity 0.91)
- Zero-Shot Low-Light Image Enhancement via Latent Diffusion Models (AAAI 2025 · similarity 0.90)
- Enhancing Low-Light Images: A Synthetic Data Perspective on Practical and Generalizable Solutions (AAAI 2025 · similarity 0.89)
- IniRetinex: Rethinking Retinex-type Low-Light Image Enhancer via Initialization Perspective (AAAI 2025 · similarity 0.87)
- DarkIR: Robust Low-Light Image Restoration (CVPR 2025 · 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.
