Research map / Image generation / Image restoration
Robust Unfolding Network for HDR Imaging with Modulo Cameras
Zhile Chen, Hui Ji
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 auxiliary outlier variable V for gradients violating Itoh's condition (ablation) | DUN · Synthetic modulo HDR | PSNR (dB): 41.43 -> 42.56 | Improved |
| use spiking neuron module instead of hard thresholding to sparsify V (ablation) | DUN · Synthetic modulo HDR | PSNR (dB): 41.79 -> 42.56 | Improved |
| use Nesterov accelerated gradient descent instead of one-step gradient descent (ablation) | DUN · Synthetic modulo HDR | PSNR (dB): 41.55 -> 42.56 | Improved |
| use LogCosh loss instead of l1 for the pixel term (ablation) | DUN · Synthetic modulo HDR | PSNR (dB): 42.28 -> 42.56 | Improved |
| reformulate modulo HDR in the gradient domain via Itoh's condition with unfolding network | modulo HDR reconstruction · Synthetic modulo HDR | PSNR (dB): 40.42 -> 42.56 | Improved |
| use single-image HDR models without retraining on modulo data | ExpandNet and Santos et al. · Synthetic modulo HDR | PSNR (dB): ExpandNet 21.20 vs 23.57 retrained; Santos 10.89 vs 39.09 retrained | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- UnModNet — UnModNet: Learning to Unwrap a Modulo Image for High Dynamic Range Imaging (NeurIPS 2020) · better on 4 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline (CVPR 2020 · similarity 0.89)
- UnModNet: Learning to Unwrap a Modulo Image for High Dynamic Range Imaging (NeurIPS 2020 · similarity 0.88)
- Single Shot HDR Recovery via a Video Diffusion Prior (NeurIPS 2026 · similarity 0.87)
- Pano-NeRF: Synthesizing High Dynamic Range Novel Views with Geometry from Sparse Low Dynamic Range Panoramic Images (AAAI 2024 · similarity 0.86)
- Generating Content for HDR Deghosting from Frequency View (CVPR 2024 · similarity 0.86)
- HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splatting (NeurIPS 2024 · similarity 0.85)
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.
