The paper introduces an amortized estimator that predicts the set of affine maps defining an Iterated Function System (IFS) directly from a visit‑frequency density map, eliminating the need for per‑image optimization. By training on synthetic pairs generated from the known forward model and evaluating reconstructions via Hungarian matching, the method achieves faster and higher‑quality IFS reconstructions on both synthetic and real datasets. Experiments show that a single forward pass followed by a few refinement steps outperforms random‑initialized per‑image optimization in both speed and reconstruction quality.
arXiv:2606. 19802v1 Announce Type: new Abstract: Image restoration faces a fundamental tradeoff: methods that minimize error produce blurry reconstructions, while those that maximize perceptual quality yield sharp but less faithful images.
arXiv:2508. 05321v4 Announce Type: replace-cross Abstract: Assume you encounter an inverse problem that shall be solved for a large number of data, but no ground-truth data is available.
arXiv:2510. 02208v3 Announce Type: replace-cross Abstract: Diffusion models have emerged as powerful generative priors for solving inverse imaging problems.
arXiv:2607. 26860v1 Announce Type: new Abstract: We propose amortized moment matching, utilizing neural networks to learn data moments as distributional training signals.
arXiv:2605.11506v2 Announce Type: replace Abstract: Score-based diffusion models achieve state-of-the-art performance for inverse problems, but their practical deployment is hindered by long inferenc...
arXiv:2602.05391v3 Announce Type: replace Abstract: Dataset distillation seeks to synthesize a compact surrogate dataset that enables performance comparable to training on the original dataset for do...
arXiv:2603. 15925v2 Announce Type: replace Abstract: Inverse design aims to find design parameters $x$ achieving target performance $y^*$.
arXiv:2506. 06006v3 Announce Type: replace-cross Abstract: Can unified vision-language models (VLMs) perform forward dynamics prediction (FDP), i.
arXiv:2609.12953v1 Announce Type: new Abstract: Flow matching approaches to imaging inverse problems commonly incorporate measurements in two ways. Conditioning-based approaches supply measurement-de...
arXiv:2601. 23231v2 Announce Type: replace-cross Abstract: Flow-based generative models provide strong unconditional priors for inverse problems, but guiding their dynamics for conditional generation remains challenging.
arXiv:2609.37529v1 Announce Type: cross Abstract: Pretrained denoisers provide a powerful way to incorporate image priors into restoration algorithms. Plug-and-Play and RED approaches exploit fixed-n...
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.