gQIR：生成式量子图像重建
gQIR: Generative Quanta Image Reconstruction
把大规模文生图潜变量扩散模型迁移到极端光子受限的 SPAD 突发帧重建，用扩散先验同时完成对齐、去噪与彩色去马赛克；做低光照/短曝光复原的人可直接复用其潜空间复原+突发级时空推理的框架。
原文依据 adapts large text-to-image latent diffusion models to the photon-limited domain of quanta burst imaging
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论仅从少量探测到的光子中捕获高质量图像是计算成像中的一个基本挑战。单光子雪崩二极管（SPAD）传感器有望在传统相机失效的场景下实现高质量成像，但原始量子帧只包含稀疏、含噪的二值光子探测结果。从这样一组突发帧中恢复出一致连贯的图像，需要在远超标准复原流程或现代生成模型所假设的噪声统计条件下处理对齐、去噪以及（针对彩色的）去马赛克问题。我们提出一种方法，将大规模文本到图像潜变量扩散模型适配到量子突发成像的光子受限域。该方法利用互联网规模扩散模型的结构与语义先验，同时引入处理伯努利光子统计的机制。通过将潜空间复原与突发级时空推理相结合，我们的方法即使在高速运动下也能产生光度上忠实且感知上令人满意的重建结果。我们在合成基准和新的真实世界数据集上评估了该方法，包括首个彩色 SPAD 突发数据集和一个具有挑战性的形变（XD）视频基准。在所有设置下，该方法在感知质量上均显著优于经典基线和现代基于学习的基线，展示了将大规模生成先验适配到极端光子受限传感中的潜力。代码见 https://github.com/Aryan-Garg/gQIR。
英文原文摘要 1495 字符
Capturing high-quality images from only a few detected photons is a fundamental challenge in computational imaging. Single-photon avalanche diode (SPAD) sensors promise high-quality imaging in regimes where conventional cameras fail, but raw quanta frames contain only sparse, noisy, binary photon detections. Recovering a coherent image from a burst of such frames requires handling alignment, denoising, and demosaicing (for color) under noise statistics far outside those assumed by standard restoration pipelines or modern generative models. We present an approach that adapts large text-to-image latent diffusion models to the photon-limited domain of quanta burst imaging. Our method leverages the structural and semantic priors of internet-scale diffusion models while introducing mechanisms to handle Bernoulli photon statistics. By integrating latent-space restoration with burst-level spatio-temporal reasoning, our approach produces reconstructions that are both photometrically faithful and perceptually pleasing, even under high-speed motion. We evaluate the method on synthetic benchmarks and new real-world datasets, including the first color SPAD burst dataset and a challenging Deforming (XD) video benchmark. Across all settings, the approach substantially improves perceptual quality over classical and modern learning-based baselines, demonstrating the promise of adapting large generative priors to extreme photon-limited sensing. Code at https://github.com/Aryan-Garg/gQIR.