Research map / Architectures and efficiency / RNNs and normalization
A Hybrid l1-l0 Layer Decomposition Model for Tone Mapping
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use the hybrid ℓ1-ℓ0 decomposition with the multiscale tone-mapping scheme | Tone mapping HDR radiance maps · HDR database (40 images) | TMQI: 0.8746 -> 0.8851 | Helped |
| Use the hybrid ℓ1-ℓ0 decomposition with the multiscale tone-mapping scheme | Tone mapping HDR radiance maps · HDR database (40 images) | Naturalness: 0.5303 -> 0.5547 | Helped |
| Use the hybrid ℓ1-ℓ0 decomposition with the multiscale tone-mapping scheme | Tone mapping HDR radiance maps · HDR database (40 images) | Mean opinion score: 5.31 -> 6.43 | Helped |
| Use the hybrid ℓ1-ℓ0 decomposition with the multiscale tone-mapping scheme | Tone mapping HDR radiance maps · HDR database (40 images) | Fidelity: 0.8614 -> 0.8334 | Hurt |
| Use ℓ0 rather than ℓ1 gradient sparsity on the detail layer (ablation) | Layer decomposition for tone mapping · HDR images (Figure 1 comparison) | Over-enhancement | Helped |
| Use two-scale rather than one-scale decomposition (ablation) | Hybrid ℓ1-ℓ0 tone mapping · HDR images (Figure 3 comparison) | Natural appearance | Helped |
| Set λ2 to 0.0008 with λ1 fixed to 0.3 (ablation) | Hybrid ℓ1-ℓ0 decomposition · Detail layer | MLE: 2.33 | Hurt |
| Set λ2 to 0.008 with λ1 fixed to 0.3 (ablation) | Hybrid ℓ1-ℓ0 decomposition · Detail layer | MLE: 0.97 | Hurt |
| Use λ2 = 0.003 with λ1 fixed to 0.3 (ablation) | Hybrid ℓ1-ℓ0 decomposition · Detail layer | MLE: 1.55 | No clear effect |
| Set λ1 to 0.06 rather than 0.3 (ablation) | Hybrid ℓ1-ℓ0 decomposition · Base layer | MLE: 2.27 | Mixed |
| Set λ1 to 1 rather than 0.3 (ablation) | Hybrid ℓ1-ℓ0 decomposition · Base layer | MLE: 2.09 | Mixed |
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 0.89)
- GaussHDR: High Dynamic Range Gaussian Splatting via Learning Unified 3D and 2D Local Tone Mapping (CVPR 2025 · similarity 0.85)
- PixelART: Image-to-Layer Decomposition without Latents or Text-to-Image Pretraining (NeurIPS 2026 · similarity 0.84)
- Balancing Frequencies and Pixels in Flow Matching (NeurIPS 2026 · similarity 0.84)
- Plug-and-Play Tri-Branch Invertible Block for Image Rescaling (AAAI 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.