Amortized Set Prediction for Inverse IFS Reconstruction from Density Maps

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.