Research map / Architectures and efficiency / Attention and transformers
Ghost-Free High Dynamic Range Imaging with Context-Aware Transformer
Zhen Liu, Yinglong Wang, Bing Zeng, Shuaicheng Liu
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 |
|---|---|---|---|
| replace vanilla Transformer encoder with CA-ViT (ablation) | tiny SwinIR baseline · Kalantari test set (ablation) | PSNR-mu: 43.42 -> 44.03 | Improved |
| replace vanilla Transformer encoder with CA-ViT (ablation) | tiny SwinIR baseline · Kalantari test set (ablation) | HDR-VDP-2: 64.52 -> 65.94 | Improved |
| add spatial attention module (ablation) | tiny SwinIR baseline · Kalantari test set (ablation) | PSNR-mu: 43.42 -> 43.77 | Improved |
| add spatial attention module (ablation) | tiny SwinIR baseline · Kalantari test set (ablation) | HDR-VDP-2: 64.52 -> 65.30 | Improved |
| add SA on top of CA-ViT (ablation) | tiny SwinIR baseline · Kalantari test set (ablation) | PSNR-mu: 44.03 -> 44.26 | Improved |
| add SA on top of CA-ViT (ablation) | tiny SwinIR baseline · Kalantari test set (ablation) | PSNR-l: 41.99 -> 42.09 | Improved |
| add perceptual loss to CA-ViT + SA model (ablation) | tiny SwinIR baseline · Kalantari test set (ablation) | PSNR-mu: 44.26 -> 44.32 | Improved |
| add perceptual loss to CA-ViT + SA model (ablation) | tiny SwinIR baseline · Kalantari test set (ablation) | PSNR-l: 42.09 -> 42.18 | Improved |
| add perceptual loss to CA-ViT + SA model (ablation) | tiny SwinIR baseline · Kalantari test set (ablation) | HDR-VDP-2: 65.97 -> 66.03 | Improved |
Closest papers by meaning
- Towards Practical and Efficient High-Resolution HDR Deghosting with CNN (ECCV 2020 · similarity 0.91)
- Alignment-free HDR Deghosting with Semantics Consistent Transformer (ICCV 2023 · similarity 0.90)
- Selective TransHDR: Transformer-Based Selective HDR Imaging Using Ghost Region Mask (ECCV 2022 · similarity 0.90)
- Generating Content for HDR Deghosting from Frequency View (CVPR 2024 · similarity 0.87)
- Real-Time Scene-Adaptive Tone Mapping for High-Dynamic Range Object Detection (NeurIPS 2025 · similarity 0.86)
- GaussHDR: High Dynamic Range Gaussian Splatting via Learning Unified 3D and 2D Local Tone Mapping (CVPR 2025 · similarity 0.86)
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.
