Quanta Diffusion
Prateek Chennuri, Dongdong Fu, Stanley H. Chan
Abstract
We present Quanta Diffusion (QuDi), a powerful generative video reconstruction method for single-photon imaging. QuDi is an algorithm supporting the latest Quanta Image Sensors (QIS) and Single Photon Avalanche Diodes (SPADs) for extremely low-light imaging conditions. Compared to existing methods, QuDi overcomes the difficulties of simultaneously managing the motion and the strong shot noise. The core innovation of QuDi is to inject a physics-based forward model into the diffusion algorithm, while keeping the motion estimation in the loop. QuDi demonstrates an average of 2.4 dB PSNR improvement over the best existing methods.
Related Papers
DINO-VO: A Feature-based Visual Odometry Leveraging a Visual Foundation Model2025-07-17HiM2SAM: Enhancing SAM2 with Hierarchical Motion Estimation and Memory Optimization towards Long-term Tracking2025-07-10GSVR: 2D Gaussian-based Video Representation for 800+ FPS with Hybrid Deformation Field2025-07-08EndoMUST: Monocular Depth Estimation for Robotic Endoscopy via End-to-end Multi-step Self-supervised Training2025-06-19Uncertainty-Driven Radar-Inertial Fusion for Instantaneous 3D Ego-Velocity Estimation2025-06-17Spatio-Temporal State Space Model For Efficient Event-Based Optical Flow2025-06-09Object-centric 3D Motion Field for Robot Learning from Human Videos2025-06-04Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generation2025-06-04