Single-photon avalanche diode (SPAD) cameras produce binary images where each pixel records zero or one photon arrival, making scene reconstruction a fundamentally one-to-many inverse problem. As more binary frames are accumulated, the uncertainty diminishes, transitioning from stochastic to near-deterministic scene understanding. The study introduces a conditional generative framework using a Hypergeometric frame‑thinning process to model this ambiguity and evaluates its impact on tasks such as character recognition, QR code decoding, and facial analysis.
arXiv:2609.22479v1 Announce Type: new Abstract: We address the problem of recovering high-speed videos from dynamic scenes under extreme photon sparsity. Existing methods rely on aggregating photon d...
The paper introduces a self‑supervised approach for Poisson inverse imaging problems that leverages frozen CLIP RN50 features as a lightweight prior within an ADMM‑inspired unrolled solver. By decoupling data‑consistency from the prior and using a parameter‑efficient decoder, the method adapts foundation vision representations without extensive fine‑tuning. Experiments on Poisson CFA demosaicing and deblurring demonstrate competitive image quality, enhanced robustness to dataset and acquisition shifts, and self‑supervised performance close to that of supervised training.
arXiv:2608.27584v1 Announce Type: new Abstract: Autonomous systems rely on extracting information from light, yet remain brittle in extreme environments, from nighttime navigation to high-speed robot...
Raw images inherently suffer from noise due to the stochastic nature of light and sensor hardware imperfections. As real photon counts fall, the ratio of this noise to the signal degrades; consequently, for low-light conditions, robust denoising is especially vital for high-quality results.
The paper introduces a state‑aware framework that reconstructs both foreground and hidden scenes from single‑photon LiDAR histograms affected by partially transmissive occluders. It classifies each ray into no‑return, single‑return, or dual‑return states, guiding a two‑head neural field that jointly refines waveform reconstruction and geometry localization. A new paired dataset of occluded and clean LiDAR captures validates the method, showing improved depth and point‑cloud accuracy over existing baselines.
The paper investigates how to model dynamic system transfer functions for event-based vision sensors. It analyzes three temporal probes—step, linear ramp, and exponential ramp—within a linear shift‑invariant optical system to determine which probe best matches a specified modulation transfer function. The study finds that step probes are vulnerable to threshold mismatch but robust to photon shot‑noise, while ramp probes maintain accuracy even with high mismatch, and it proposes dynamic point spread functions as part of a unified forward model for computational neuromorphic imaging.
The paper investigates how to model dynamic system transfer functions for event‑based vision sensors by analyzing the correspondence between temporal probes and the resulting event streams in a linear shift‑invariant optical system. Using a first‑order filter pixel model and three temporal probes—a step, a linear ramp, and an exponential ramp—the authors derive the inverse chain for different event statistics and compare the results to the system’s modulation transfer function. The study finds that the step probe is highly sensitive to threshold mismatch but robust to photon shot‑noise, whereas linear and exponential probes maintain accurate signal inference even under significant mismatch, highlighting their potential for dynamic point spread function estimation in computational neuromorphic imaging.
The paper introduces the Ensemble-conditioned Inverse Problem (EIP), a multivariate statistical framework for inferring an ensemble that follows the pushforward of a prior through a forward process. It applies to fields such as high‑energy physics, full waveform inversion, and inverse imaging, and proposes non‑iterative inference‑time methods using ensemble inverse generative models that avoid explicit forward model use during inference. The authors demonstrate the approach on synthetic and real datasets and provide code for replication.
arXiv:2606. 02331v1 Announce Type: cross Abstract: Diffusion-based inverse problem solvers can produce realistic reconstructions, but realism alone does not ensure that the recovered details are supported by the measurement.
arXiv:2606. 02309v1 Announce Type: new Abstract: Generative models are increasingly used as priors for inverse problems, but their ability to produce realistic images creates a basic trust problem: a plausible reconstruction may be supported by the measurements, or it may be filled in by the prior along unobserved directions.
arXiv:2608.29243v1 Announce Type: new Abstract: Existing diffusion-based enhancement methods provide strong generative capability for low-light image enhancement (LLIE), yet they either rely on paire...
arXiv:2608.21970v1 Announce Type: new Abstract: Two-photon calcium imaging presents a challenging setting for foundation models: image appearance varies substantially across recordings and experiment...