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:2512. 05672v2 Announce Type: replace-cross Abstract: Recent approaches in controllable novel view video generation often rely on fine-tuning pre-trained Video Diffusion Models (VDMs).
SlowFast‑SCI introduces a dual‑speed deep‑unfolding framework for spectral compressive imaging that combines a slow, pre‑trained backbone with a fast, test‑time adaptation stage. The slow phase distills a priors‑based model into a compact fast‑unfolding network, while the fast phase embeds lightweight modules that self‑supervise at test time without retraining the backbone. This design yields significant reductions in parameters and FLOPs, improves out‑of‑distribution PSNR by up to 5.79 dB, and accelerates adaptation four‑fold, all while remaining modular enough to integrate with any existing deep‑unfolding system.
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:2607. 02628v1 Announce Type: cross Abstract: While diffusion models have revolutionized image synthesis, their application to real-world inverse problems is often hampered by the need for massive datasets and the difficulty of imposing strict physical constraints.
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. 17048v1 Announce Type: new Abstract: Diffusion and flow-based models learn powerful data priors by training a denoiser to reverse Gaussian corruption.
arXiv:2510. 02208v3 Announce Type: replace-cross Abstract: Diffusion models have emerged as powerful generative priors for solving inverse imaging problems.
The paper introduces a Posterior‑Dynamics Framework that leverages pretrained diffusion models as multiscale priors for linear imaging inverse problems such as deblurring, super‑resolution, and inpainting. By constructing a surrogate likelihood centered on the clean image and incorporating diffusion uncertainty, the authors derive continuous posterior dynamics and a tunable Langevin component for adaptive exploration. They prove theoretical guarantees (endpoint consistency, finite‑horizon tracking, weak accuracy) and present the PD‑IMEX sampler, which achieves high‑quality reconstructions with only 100 score evaluations and controllable fidelity‑diversity trade‑offs.
The paper introduces MS-Flow, a method that represents a flow-based generative model’s trajectory as a sequence of intermediate latent states instead of a single initial code. By enforcing local flow dynamics and coupling trajectory segments with matching penalties, the approach alternates between updating latent states and ensuring consistency with observed data. This strategy reduces memory usage and improves reconstruction quality on tasks such as image inpainting, super‑resolution, and computed tomography.
arXiv:2607. 19333v1 Announce Type: cross Abstract: Diffusion-based methods have achieved remarkable empirical success in solving inverse problems.
WildRelight is the first in-the-wild dataset designed to evaluate single-image relighting models, featuring high-resolution outdoor scenes captured under strictly aligned, temporally varying natural illuminations paired with high-dynamic-range environment maps. The benchmark demonstrates that state-of-the-art models trained on synthetic data suffer severe domain shifts when applied to real-world imagery. Leveraging the dataset’s temporal structure, the authors introduce a physics-guided inference framework combining Diffusion Posterior Sampling with Temporal Sampling-Aware Test-Time Adaptation, enabling synthetic models to self-supervise and align with real-world statistics on-the-fly.
arXiv:2602. 23214v2 Announce Type: replace-cross Abstract: Plug-and-Play diffusion prior (PnPDP) frameworks have emerged as a powerful paradigm for solving imaging inverse problems by treating pretrained generative models as modular priors.