Research map / Video / Video generation
3One2: One-Step Regression plus One-Step Diffusion for One-Hot Modulation in Dual-Path Video Snapshot Compressive Imaging
Ge Wang, Xing Liu, Xin Yuan
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 EfficientSCI regression network with RegDif (one-step regression plus one-step diffusion) | one-hot mask single-path video SCI · Grayscale video SCI average | PSNR (dB): 33.31 -> 35.22 | Improved |
| add compensatory optical path measurement fusion (DoP) | RegDif · Grayscale video SCI average | PSNR (dB): 35.22 -> 38.08 | Improved |
| add compensatory optical path measurement fusion (DoP) | EfficientSCI · Grayscale video SCI average | PSNR (dB): 33.31 -> 36.08 | Improved |
| RegDif over EfficientSCI on color datasets | one-hot mask single-path video SCI · Color video SCI average | PSNR (dB): 36.71 -> 37.39 | Improved |
| DoP-RegDif over DoP-EfficientSCI on color datasets | dual-path video SCI · Color video SCI average | PSNR (dB): 37.55 -> 38.24 | Improved |
| add alignment loss to regression and diffusion losses (ablation) | RegDif training · training loss curves | final output l2 distance | Improved |
| add regression loss to alignment and diffusion losses (ablation) | RegDif training · training loss curves | final output l2 distance | Improved |
| use pure multi-step diffusion inpainting instead of regression plus one-step diffusion (ablation) | video SCI reconstruction · video SCI | quality and speed | 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.
- BIRNAT — BIRNAT: Bidirectional Recurrent Neural Networks with Adversarial Training for Video Snapshot Compressive Imaging (ECCV 2020) · better on 1 of 1 shared result
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
- Self-Supervised One-Step Diffusion Refinement for Snapshot Compressive Imaging (AAAI 2026 · similarity 0.91)
- Deep Optics for Video Snapshot Compressive Imaging (ICCV 2023 · similarity 0.90)
- Plug-and-Play Algorithms for Video Snapshot Compressive Imaging (TPAMI 2021 · similarity 0.89)
- DiffSCI: Zero-Shot Snapshot Compressive Imaging via Iterative Spectral Diffusion Model (CVPR 2024 · similarity 0.88)
- Single Shot HDR Recovery via a Video Diffusion Prior (NeurIPS 2026 · similarity 0.86)
- Untrained Neural Nets for Snapshot Compressive Imaging: Theory and Algorithms (NeurIPS 2024 · 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.
