Research map / 3D vision / NeRF and radiance fields
AdaptiveAE: An Adaptive Exposure Strategy for HDR Capturing in Dynamic Scenes
Tianyi Xu, Fan Zhang, Boxin Shi, Tianfan Xue, Yujin Wang
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 importance-mask reward P_priority to the base reward (ablation) | AdaptiveAE · HDRV | PSNR-mu: 38.21 -> 38.57 | Improved |
| add motion-region reward P_ghost (ablation) | AdaptiveAE · HDRV | PSNR-mu: 38.57 -> 39.70 | Improved |
| predict both ISO and shutter speed instead of fixed ISO 200 (ablation) | AdaptiveAE vs Wang et al. · HDRV | PSNR-mu: 37.64 -> 39.70 | Improved |
| tune the fixed ISO of Wang et al. to the best value (ablation) | Wang et al. · HDRV | PSNR-mu: 36.46 -> 37.64 | Improved |
| handle blur at capture time rather than post-capture deblurring (BANet before or after fusion) (ablation) | AdaptiveAE vs Wang et al. · HDRV | PSNR-mu: 37.33 -> 39.70 | Improved |
| use stronger fusion model (HDR-Transformer instead of DeepHDR) with AdaptiveAE exposures | AdaptiveAE · HDRV | PSNR-mu: 39.70 -> 41.37 | Improved |
| apply AdaptiveAE trained on HDRV to DeepHDRVideo (cross-dataset) | AdaptiveAE · DeepHDRVideo | PSNR-mu: 38.47 -> 39.81 | Improved |
| random exposure choice versus learned policy | AdaptiveAE · HDRV-test | PSNR-mu: 32.41 -> 39.70 | Improved |
Closest papers by meaning
- Single Shot HDR Recovery via a Video Diffusion Prior (NeurIPS 2026 · similarity 0.90)
- Color Event Enhanced Single-Exposure HDR Imaging (AAAI 2024 · similarity 0.87)
- High Dynamic Range Novel View Synthesis with Single Exposure (ICML 2025 · similarity 0.87)
- EvHDR-NeRF: Building High Dynamic Range Radiance Fields with Single Exposure Images and Events (AAAI 2025 · similarity 0.87)
- Self-Supervised High Dynamic Range Imaging with Multi-Exposure Images in Dynamic Scenes (ICLR 2024 · similarity 0.87)
- Towards Real-World HDR Video Reconstruction: A Large-Scale Benchmark Dataset and A Two-Stage Alignment Network (CVPR 2024 · similarity 0.87)
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.
