Research map / Video / Video segmentation and tracking
ReMoNet: Recurrent Multi-Output Network for Efficient Video Denoising
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 ReMoNet's multi-input multi-output recurrent architecture instead of FastDVDNet | video denoising · Set8, Gaussian noise σ = 30 | PSNR: 31.51 -> 31.59 | Helped |
| Use ReMoNet instead of FastDVDNet | video denoising · Set8, Gaussian noise σ = 30 | MACs per frame: 331G -> 26G | Helped |
| Use ReMoNet instead of FastDVDNet | video denoising · DAVIS-test, Gaussian noise σ = 30 | PSNR: 33.90 -> 33.93 | Helped |
| Use ReMoNet instead of FastDVDNet | video denoising · Set8, simulated ISP noise σ = 0.05 | PSNR: 25.28 -> 27.96 | Helped |
| Use ReMoNet instead of FastDVDNet | mobile video denoising on Qualcomm Snapdragon 888 · 360 × 640 | inference time per frame: 927ms -> 89.2ms per frame | Helped |
| Add recurrent temporal fusion rather than slow temporal fusion (ablation) | ReMoNet · Set8, Gaussian noise σ = 30 | PSNR: 31.30 -> 31.59 | Helped |
| Add MIMO to recurrent temporal fusion (ablation) | ReMoNet · Set8, Gaussian noise σ = 30 | PSNR: 31.45 -> 31.59 | Helped |
| Add the MOA block (ablation) | ReMoNet · Set8, Gaussian noise σ = 30 | PSNR: 31.29 -> 31.59 | Helped |
| Add similarity-based mutual distillation (ablation) | ReMoNet · Set8, Gaussian noise σ = 30 | PSNR: 31.49 -> 31.59 | Helped |
Closest papers by meaning
- Efficient Multi-Stage Video Denoising With Recurrent Spatio-Temporal Fusion (CVPR 2021 · similarity 0.87)
- FastDVDnet: Towards Real-Time Deep Video Denoising Without Flow Estimation (CVPR 2020 · similarity 0.86)
- Classic Video Denoising in a Machine Learning World: Robust, Fast, and Controllable (CVPR 2025 · similarity 0.86)
- MobileWan: Closing the Quality Gap for Mobile Video Diffusion (NeurIPS 2026 · similarity 0.85)
- FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attention (NeurIPS 2024 · similarity 0.83)
- FIFO-Diffusion: Generating Infinite Videos from Text without Training (NeurIPS 2024 · similarity 0.83)
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.