Research map / Video / Video segmentation and tracking
Quanta Video Restoration
Prateek Chennuri, Yiheng Chi, Enze Jiang, GM Dilshan Godaliyadda, Abhiram Gnanasambandam, Hamid R Sheikh, Istvan Gyongy, Stanley H Chan
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 pre-denoising stage (ablation) | QUIVER · I2-2000FPS (3.25 PPP) | PSNR: 24.9999 -> 26.2143 | Improved |
| add learnable optical flow module (ablation) | QUIVER · I2-2000FPS (3.25 PPP) | PSNR: 25.7521 -> 26.2143 | Improved |
| add multi-scale reconstruction (ablation) | QUIVER · I2-2000FPS (3.25 PPP) | PSNR: 24.3841 -> 26.2143 | Improved |
| initialise optical flow module with pre-trained SPyNet weights (ablation) | QUIVER · I2-2000FPS (3.25 PPP) | PSNR: 26.2143 -> 23.9479 | Hurt |
| use QUIVER instead of strongest baseline at lowest light | quanta video restoration · I2-2000FPS (3.25 PPP) | PSNR: 21.5476 -> 26.2143 | Improved |
| use QUIVER instead of FloRNN at higher light levels | quanta video restoration · X4K1000FPS (9.75 and 26 PPP) | PSNR: 9.75 PPP: 23.5874 (FloRNN) vs 23.1654; 26 PPP: 25.2483 vs 25.0086 | Mixed |
| scale down model to QUIVER-s | QUIVER · I2-2000FPS (3.25 PPP) | PSNR: 26.2143 -> 24.7013 | Mixed |
| add BM3D denoiser to QBP | QBP · I2-2000FPS (3.25 PPP) | PSNR: 15.9411 -> 21.5476 | Improved |
Closest papers by meaning
- bit2bit: 1-bit quanta video reconstruction via self-supervised photon prediction (NeurIPS 2024 · similarity 0.88)
- VQCNIR: Clearer Night Image Restoration with Vector-Quantized Codebook (AAAI 2024 · similarity 0.84)
- QMambaBSR: Burst Image Super-Resolution with Query State Space Model (CVPR 2025 · similarity 0.84)
- PMQ-VE: Progressive Multi-Frame Quantization for Video Enhancement (NeurIPS 2025 · similarity 0.84)
- Deep Linear Array Pushbroom Image Restoration: A Degradation Pipeline and Jitter-Aware Restoration Network (AAAI 2024 · similarity 0.83)
- MambaSCI: Efficient Mamba-UNet for Quad-Bayer Patterned Video Snapshot Compressive Imaging (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.
