Research map / Probabilistic and scientific modeling / Molecules and proteins
Revisiting the Stack-Based Inverse 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 adaptive exposure and fusion pipeline instead of Deep Single | Inverse tone mapping · HDR-TEST | HDR-VDP-2.2: 64.28 -> 65.20 | Helped |
| Add the exposure adaptive block (ablation) | Stack-based ITM · HDR-TEST | HDR-VDP-2: 62.35 -> 63.89 | Helped |
| Add luminance-guided convolution (ablation) | Stack-based ITM with EAB · HDR-TEST | HDR-VDP-2: 63.89 -> 64.14 | Helped |
| Add cross-model attention (ablation) | Stack-based ITM with EAB and LGC · HDR-TEST | HDR-VDP-2: 64.14 -> 64.97 | Helped |
| Add the multi-exposure fusion model (ablation) | Stack-based ITM with EAB, LGC, and CMAB · HDR-TEST | HDR-VDP-2: 64.97 -> 65.20 | Helped |
| Add opposite-model features to CMAB (ablation) | ADEM · HDR-TEST | HDR-VDP-2.2: 64.52 -> 64.97 | Helped |
| Add perceptual loss to L1 training (ablation) | Exposure adjustment models · HDR-TEST | HDR-VDP-2.2: 63.37 -> 64.14 | Helped |
| Add progressive reconstruction loss (ablation) | Exposure adjustment models · HDR-TEST | HDR-VDP-2.2: 64.14 -> 64.69 | Helped |
| Add mask-aware generative adversarial loss (ablation) | Exposure adjustment models · HDR-TEST | HDR-VDP-2.2: 64.69 -> 65.20 | Helped |
| Replace classic MEF fusion with MEFM | Fusion of three multi-exposure images · Tesla V100 | running time: 1807ms -> 5ms | Helped |
Closest papers by meaning
- Learning Differential Pyramid Representation for Tone Mapping (NeurIPS 2025 · similarity 0.82)
- Multi-band Frequency Reconstruction for Neural Psychoacoustic Coding (ICML 2025 · similarity 0.80)
- RFWave: Multi-band Rectified Flow for Audio Waveform Reconstruction (ICLR 2025 · similarity 0.79)
- UniFlow-Audio: Unified Flow Matching for Audio Generation from Omni-Modalities (NeurIPS 2026 · similarity 0.78)
- Zero-Shot Structure-Preserving Diffusion Model for High Dynamic Range Tone Mapping (CVPR 2024 · similarity 0.78)
- WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling (ICLR 2025 · similarity 0.78)
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.