Research map / Image generation / Image restoration
High-Resolution Photo Enhancement in Real-Time: A Laplacian Pyramid Network
Feng Zhang, Haoyou Deng, Zhiqiang Li, Lida Li, Bin Xu, Qingbo Lu, Zisheng Cao, Minchen Wei, Changxin Gao, Nong Sang, Xiang Bai
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 pixel-level weight map to 3D LUT (ablation) | 3D LUT baseline · HDR+ (480p) | PSNR: 23.16 -> 24.41 | Improved |
| replace lightweight CNN with tiny transformer for weight prediction (ablation) | LLF-LUT++ with weight map · HDR+ (480p) | PSNR: 24.41 -> 25.34 | Improved |
| add learnable local Laplacian filter (ablation) | LLF-LUT++ with transformer · HDR+ (480p) | PSNR: 25.34 -> 26.62 | Improved |
| add combined weight fusion (point + map) (ablation) | LLF-LUT++ with LLF · HDR+ (480p) | PSNR: 26.62 -> 27.09 | Improved |
| replace tiny transformer with spatial-frequency transformer (ablation) | LLF-LUT++ · HDR+ (480p) | PSNR: 27.09 -> 27.94 | Improved |
| add specific layer pyramid network for reconstruction (ablation) | LLF-LUT++ · HDR+ (480p) | PSNR: 27.94 -> 28.43 | Improved |
| use weight map instead of weight point (ablation) | LLF-LUT++ · HDR+ (480p) | PSNR: 25.28 -> 27.51 | Improved |
| combine weight point (HR) and weight map (LR) instead of weight map only (ablation) | LLF-LUT++ · HDR+ (480p) | PSNR: 27.51 -> 28.43 | Improved |
| raise low-frequency image resolution from 16x16 to 64x64 (ablation) | LLF-LUT++ · HDR+ (480p) | PSNR: 27.12 -> 28.43 | Improved |
| raise low-frequency image resolution from 64x64 to 256x256 (ablation) | LLF-LUT++ · HDR+ (480p) | PSNR: 28.43 -> 28.51 | No clear effect |
| replace LLF-LUT with LLF-LUT++ (spatial-frequency transformer, pyramid network) | LLF-LUT · HDR+ (original) | PSNR: 25.32 -> 27.96 | Improved |
| replace LLF-LUT with LLF-LUT++ | LLF-LUT · MIT-FiveK (480p) | PSNR: 25.53 -> 26.06 | Improved |
Closest papers by meaning
- Lookup Table meets Local Laplacian Filter: Pyramid Reconstruction Network for Tone Mapping (NeurIPS 2023 · similarity 0.90)
- Real-Time Exposure Correction via Collaborative Transformations and Adaptive Sampling (CVPR 2024 · similarity 0.87)
- Luminance-Aware Statistical Quantization: Unsupervised Hierarchical Learning for Illumination Enhancement (NeurIPS 2025 · similarity 0.87)
- Enhancing Low-Light Images: A Synthetic Data Perspective on Practical and Generalizable Solutions (AAAI 2025 · similarity 0.85)
- Zero-Shot Low-Light Image Enhancement via Latent Diffusion Models (AAAI 2025 · similarity 0.85)
- LaMAR: Laplacian Pyramid for Multimodal Adaptive Super Resolution (Student Abstract) (AAAI 2024 · similarity 0.85)
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.
