Research map / Video / Video segmentation and tracking
Learning Event Guided High Dynamic Range Video Reconstruction
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 HDRev-Net to combine LDR video and events | HDR video reconstruction · Synthetic data | PSNR: 23.159 -> 24.071 | Helped |
| use HDRev-Net to combine LDR video and events | HDR video reconstruction · Synthetic data | SSIM: 0.901 -> 0.928 | Helped |
| use HDRev-Net to combine LDR video and events | HDR video reconstruction · Synthetic data | LPIPS: 0.104 -> 0.110 | Hurt |
| use HDRev-Net to combine LDR video and events | HDR video reconstruction · Synthetic data | VDP: 7.543 -> 8.108 | Helped |
| use HDRev-Net to combine LDR video and events | HDR video reconstruction · Synthetic data | VQM: 0.107 -> 0.103 | Helped |
| use staged multimodal representation alignment rather than end-to-end joint training (ablation) | HDRev-Net · Synthetic data | PSNR: 22.185 -> 24.071 | Helped |
| add confidence-guided multimodal fusion instead of a plain convolution over concatenated features (ablation) | HDRev-Net · Synthetic data | PSNR: 19.436 -> 24.071 | Helped |
| add recurrent ConvLSTM connections to the encoders (ablation) | HDRev-Net · Synthetic data | VQM: 0.173 -> 0.103 | Helped |
Closest papers by meaning
- EvHDR-GS: Event-guided HDR Video Reconstruction with 3D Gaussian Splatting (AAAI 2025 · similarity 0.90)
- Towards Real-World HDR Video Reconstruction: A Large-Scale Benchmark Dataset and A Two-Stage Alignment Network (CVPR 2024 · similarity 0.90)
- Single Shot HDR Recovery via a Video Diffusion Prior (NeurIPS 2026 · similarity 0.87)
- HDRFlow: Real-Time HDR Video Reconstruction with Large Motions (CVPR 2024 · similarity 0.87)
- Self-Supervised High Dynamic Range Imaging with Multi-Exposure Images in Dynamic Scenes (ICLR 2024 · similarity 0.86)
- High Dynamic Range Video Compression: A Large-Scale Benchmark Dataset and A Learned Bit-depth Scalable Compression Algorithm (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.