Research map / Video / Video segmentation and tracking
Streaming Quanta Sensors for Online, High-Performance Imaging and Vision
Tianyi Zhang, Matthew Dutson, Vivek Boominathan, Mohit Gupta, Ashok Veeraraghavan
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 |
|---|---|---|---|
| use streaming multi-exposure representation with U-Net instead of QBP | QBP · Synthetic Kubric local motion | PSNR: 23.74 -> 25.54 | Improved |
| use streaming representation with U-Net instead of QBP+BM3D | QBP+BM3D · Synthetic Kubric local motion | SSIM: 0.68 -> 0.80 | Improved |
| use streaming representation instead of QBP on NFS | QBP · Synthetic NFS interpolated | PSNR: 31.08 -> 28.60 | Hurt |
| use streaming representation instead of naive integration | Naive integration · Synthetic NFS interpolated | PSNR: 23.10 -> 28.60 | Improved |
| use streaming representation instead of naive integration | Naive integration · Synthetic Kubric local motion | PSNR: 22.10 -> 25.54 | Improved |
| add BM3D denoising to QBP (sigma=0.05) | QBP · Synthetic Kubric local motion | PSNR: 23.74 -> 25.22 | Improved |
| add BM3D denoising to QBP (sigma=0.05) | QBP · Synthetic NFS interpolated | PSNR: 31.08 -> 31.10 | No clear effect |
| use streaming method instead of QBP for runtime | QBP · Reconstruction runtime | time per reconstruction: 1.5-2 minutes -> about 12 ms | Improved |
| increase motion speed beyond 1000 pixels/s (ablation) | QBP and ours · Synthetic motion-speed sweep | PSNR/SSIM | Hurt |
| reduce light level (maximum photons per second 10k to 100) (ablation) | all methods · Synthetic light-level sweep | PSNR/SSIM | Hurt |
Closest papers by meaning
- Quanta Neural Networks: From Photons to Perception (ICCV 2025 · similarity 0.91)
- bit2bit: 1-bit quanta video reconstruction via self-supervised photon prediction (NeurIPS 2024 · similarity 0.86)
- GPLQ: A General, Practical, and Lightning QAT Method for Vision Transformers (NeurIPS 2025 · similarity 0.84)
- QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edge (CVPR 2025 · similarity 0.83)
- AIQViT: Architecture-Informed Post-Training Quantization for Vision Transformers (AAAI 2025 · similarity 0.83)
- ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation (ICLR 2025 · 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.
