Research map / Video / Video generation
Blind Video Deflickering by Neural Filtering With a Flawed Atlas
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 |
|---|---|---|---|
| Add a neural atlas and neural filtering (ablation) | Blind deflickering · Synthetic videos | E_warp: 0.131 -> 0.088 | Helped |
| Add local refinement (ablation) | Blind deflickering · Synthetic videos | E_warp: 0.090 -> 0.088 | Helped |
| Add local refinement (ablation) | Blind deflickering · Real-world flickering videos | Perceptual quality | Helped |
| Use the proposed blind deflickering method instead of ConvLSTM | Synthetic videos · Synthetic videos | E_warp: 0.148 -> 0.088; 0.168 -> 0.091; 0.151 -> 0.086; 0.124 -> 0.086 | Helped |
| Use the proposed blind deflickering method instead of ConvLSTM | Synthetic videos · Synthetic videos | PSNR: 21.84 -> 26.46; 19.84 -> 27.75; 21.71 -> 26.40; 23.98 -> 25.21 | Helped |
| Use the proposed blind deflickering method instead of ConvLSTM | Blind deflickering · Processed videos | E_warp: 0.118 -> 0.094 | Helped |
| Use the proposed method without extra consistent-video guidance | Blind video temporal consistency methods · Processed videos, average | E_warp: 0.100 -> 0.094 | Helped |
Closest papers by meaning
- BurstDeflicker: A Benchmark Dataset for Flicker Removal in Dynamic Scenes (NeurIPS 2025 · similarity 0.86)
- SpikeReveal: Unlocking Temporal Sequences from Real Blurry Inputs with Spike Streams (NeurIPS 2024 · similarity 0.84)
- DeblurSR: Event-Based Motion Deblurring under the Spiking Representation (AAAI 2024 · similarity 0.84)
- Seeing Dark Videos via Self-Learned Bottleneck Neural Representation (AAAI 2024 · similarity 0.83)
- Spike-guided Motion Deblurring with Unknown Modal Spatiotemporal Alignment (CVPR 2024 · similarity 0.83)
- Rebalancing Reference Frame Dominance to Improve Motion in Image-to-Video Models (NeurIPS 2026 · similarity 0.82)
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.