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
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 maps for basis 3D LUT fusion (ablation) | 3D LUT baseline · HDR+ 480p | PSNR: 23.16 -> 24.41 | Improved |
| replace CNN backbone with tiny transformer (ablation) | LUT + weight map · HDR+ 480p | PSNR: 24.41 -> 25.34 | Improved |
| add image-adaptive learnable local Laplacian filter (ablation) | LUT + weight map + transformer · HDR+ 480p | PSNR: 25.34 -> 26.62 | Improved |
| add weight map (ablation) | 3D LUT baseline · HDR+ 480p | Delta E: 7.04 -> 6.23 | Improved |
| add learnable Laplacian filter (ablation) | LUT + weight map + transformer · HDR+ 480p | LPIPS: 0.101 -> 0.063 | Improved |
| increase low-frequency image resolution 64x64 to 256x256 (ablation) | full model · HDR+ 480p | PSNR: 26.62 -> 26.81 | Improved |
| increase I_low resolution 64x64 to 128x128 (ablation) | full model · HDR+ 480p | PSNR: 26.62 -> 26.69 | Improved |
| reduce I_low from 256x256 to 64x64 for 30% less compute (ablation) | full model · HDR+ 480p | PSNR: 26.81 -> 26.62 | No clear effect |
| use image-level 3D LUT + Laplacian pyramid (Ours) over sLUT | sLUT · HDR+ original | PSNR: 23.98 -> 25.32 | Improved |
| Ours over sLUT at 480p | sLUT · HDR+ 480p | PSNR: 26.13 -> 26.62 | Improved |
| Ours over CSRNet on FiveK | CSRNet · MIT-FiveK 480p | LPIPS: 0.052 -> 0.055 | Hurt |
| Ours over CSRNet on FiveK | CSRNet · MIT-FiveK 480p | PSNR: 25.31 -> 25.53 | Improved |
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.
- CSRNet — CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes (CVPR 2018) · better on 3 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
- Learning Differential Pyramid Representation for Tone Mapping (NeurIPS 2025 · similarity 0.89)
- Zero-Shot Structure-Preserving Diffusion Model for High Dynamic Range Tone Mapping (CVPR 2024 · similarity 0.87)
- GaussHDR: High Dynamic Range Gaussian Splatting via Learning Unified 3D and 2D Local Tone Mapping (CVPR 2025 · similarity 0.85)
- Boosting ViT-based MRI Reconstruction from the Perspectives of Frequency Modulation, Spatial Purification, and Scale Diversification (AAAI 2025 · similarity 0.85)
- Real-Time Exposure Correction via Collaborative Transformations and Adaptive Sampling (CVPR 2024 · similarity 0.84)
- From Zero to Detail: Deconstructing Ultra-High-Definition Image Restoration from Progressive Spectral Perspective (CVPR 2025 · similarity 0.84)
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.
