Research map / 3D vision / Depth and stereo
Dynamic Low-light Imaging with Quanta Image Sensors
Yiheng Chi, Abhiram Gnanasambandam, Vladlen Koltun, 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 student-teacher training (both teachers) over pretrained-encoder baseline (ablation) | QIS reconstruction student network · Synthetic QIS, 1 ppp, 28 px motion | test PSNR (dB): 21.51 dB -> 23.87 dB | Improved |
| add student-teacher training (both teachers) over single-encoder model (ablation) | QIS reconstruction student network · Synthetic QIS, 1 ppp, 28 px motion | test PSNR (dB): 22.74 dB -> 23.87 dB | Improved |
| add the motion teacher to a denoising-teacher-only student (ablation) | Ours-I · Synthetic QIS, 1 ppp, 28 px motion | test PSNR (dB): 23.53 dB -> 23.87 dB | Improved |
| add the denoising teacher to a motion-teacher-only student (ablation) | Ours-II · Synthetic QIS, 1 ppp, 28 px motion | test PSNR (dB): 23.65 dB -> 23.87 dB | Improved |
| use two smaller encoders instead of a single encoder (no teacher) (ablation) | Config B vs Config A · Synthetic QIS, 1 ppp, 28 px motion | test PSNR (dB): 22.74 dB -> 21.51 dB | Hurt |
| add a single teacher (denoising) over single encoder without teacher (ablation) | Config B · Synthetic QIS, 1 ppp, 28 px motion | test PSNR (dB): 22.74 dB -> 23.53 dB | Improved |
| proposed student-teacher method vs KPN, mRED and BM4D across motion magnitude | Proposed method · Synthetic QIS, 2 ppp, varying motion | PSNR: 1.5 dB to 3 dB | Improved |
Closest papers by meaning
- Image Classification in the Dark using Quanta Image Sensors (ECCV 2020 · similarity 0.90)
- Quanta Neural Networks: From Photons to Perception (ICCV 2025 · similarity 0.88)
- Panoramas from Photons (ICCV 2023 · similarity 0.86)
- Passive Inter-Photon Imaging (CVPR 2021 · similarity 0.86)
- bit2bit: 1-bit quanta video reconstruction via self-supervised photon prediction (NeurIPS 2024 · similarity 0.85)
- Towards 3D Vision with Low-Cost Single-Photon Cameras (CVPR 2024 · similarity 0.84)
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.
