Amortized Set Prediction for Inverse IFS Reconstruction from Density Maps

• URL: http://arxiv.org/abs/2608.24175v1
• Date: Tue, 25 Aug 2026 07:40:30 GMT
• Title: Amortized Set Prediction for Inverse IFS Reconstruction from Density Maps
• Abstract summary: Iterated Function Systems (IFS) generate self-similar fractals from a few contractive affine maps.<n>We replace the inverse problem of estimating maps from an image with a learned estimator that predicts the affine-map set directly from a visit-frequency density map.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Iterated Function Systems (IFS) generate self-similar fractals from a few contractive affine maps. The forward map from parameters to images is computationally inexpensive and well understood, whereas the inverse problem of estimating maps from an image is difficult and is typically handled by per-image optimization. We replace this loop with a single forward pass of a learned estimator that predicts the affine-map set directly from a visit-frequency density map, thereby amortizing the inverse problem. The design follows two constraints. First, density maps do not uniquely identify IFS parameters, so evaluation is based on reconstruction rather than parameter recovery; unordered map sets are handled by Hungarian matching, and ground-truth parameters provide a stable training surrogate. Second, the fully known forward model lets us generate exact synthetic training pairs and also supports image-only test-time refinement. On in-distribution tests, amortized initialization plus a few refinement steps lies on a better quality--speed frontier than equal-budget random-initialized per-image optimization, and a 30-step refinement (about $0.56$ s per sample) remains better than a doubled-budget baseline. Extending optimization to 1000 steps shows that the benefit is not only speed: amortized initialization reaches high-quality reconstructions more frequently than random starts. On real images (MNIST and Fashion-MNIST), it improves density metrics on average over a published per-image optimizer while being roughly 12 to 2600 times faster.

Related papers

• Soft Anisotropic Diagrams for Differentiable Image Representation [30.776360247134704]
  Soft Anisotropic Diagrams (SAD) are parameterized by a set of adaptive sites in the image plane.<n>We induce a soft anisotropic additively weighted Voronoi partition with learnable per-site temperatures.<n>We demonstrate the effectiveness of SAD by showcasing the seamless integration with differentiable pipelines for forward and inverse problems.
  arXiv  Detail & Related papers  (2026-04-23T18:07:27Z)
• QuickSplat: Fast 3D Surface Reconstruction via Learned Gaussian Initialization [69.50126552763157]
  Surface reconstruction is fundamental to computer vision and graphics, enabling applications in 3D modeling, mixed reality, robotics, and more.<n>Existing approaches based on rendering obtain promising results, but optimize on a per-scene basis, resulting in a slow optimization that can struggle to model textureless regions.<n>We introduce QuickSplat, which learns data-driven priors to generate dense initializations for 2D gaussian splatting optimization of large-scale indoor scenes.
  arXiv  Detail & Related papers  (2025-05-08T18:43:26Z)
• FastMap: Revisiting Structure from Motion through First-Order Optimization [26.930994695116198]
  We propose FastMap, a new global structure from motion method focused on speed and simplicity.<n>We show that FastMap is up to 10 times faster than COLMAP and GLOMAP with GPU acceleration and achieves comparable pose accuracy.
  arXiv  Detail & Related papers  (2025-05-07T17:56:15Z)
• Locally Orderless Images for Optimization in Differentiable Rendering [80.09571356394574]
  We introduce a method that uses locally orderless images, where each pixel maps to a histogram of intensities that preserves local variations in appearance.<n>We validate our method on various inverse problems using both synthetic and real data.
  arXiv  Detail & Related papers  (2025-03-27T19:17:58Z)
• Fast constrained sampling in pre-trained diffusion models [80.99262780028015]
  We propose an algorithm that enables fast, high-quality generation under arbitrary constraints.<n>Our approach produces results that rival or surpass the state-of-the-art training-free inference methods.
  arXiv  Detail & Related papers  (2024-10-24T14:52:38Z)
• InstantSplat: Sparse-view Gaussian Splatting in Seconds [91.77050739918037]
  We introduce InstantSplat, a novel approach for addressing sparse-view 3D scene reconstruction at lightning-fast speed.<n>InstantSplat employs a self-supervised framework that optimize 3D scene representation and camera poses.<n>It achieves an acceleration of over 30x in reconstruction and improves visual quality (SSIM) from 0.3755 to 0.7624 compared to traditional SfM with 3D-GS.
  arXiv  Detail & Related papers  (2024-03-29T17:29:58Z)
• Deep Richardson-Lucy Deconvolution for Low-Light Image Deblurring [48.80983873199214]
  We develop a data-driven approach to model the saturated pixels by a learned latent map. Based on the new model, the non-blind deblurring task can be formulated into a maximum a posterior (MAP) problem. To estimate high-quality deblurred images without amplified artifacts, we develop a prior estimation network.
  arXiv  Detail & Related papers  (2023-08-10T12:53:30Z)
• FMapping: Factorized Efficient Neural Field Mapping for Real-Time Dense RGB SLAM [3.6985351289638957]
  We introduce FMapping, an efficient neural field mapping framework that facilitates the continuous estimation of a colorized point cloud map in real-time dense RGB SLAM. We propose an effective factorization scheme for scene representation and introduce a sliding window strategy to reduce the uncertainty for scene reconstruction.
  arXiv  Detail & Related papers  (2023-06-01T11:51:46Z)
• An Optimal Transport Perspective on Unpaired Image Super-Resolution [97.24140709634203]
  Real-world image super-resolution (SR) tasks often do not have paired datasets, which limits the application of supervised techniques.<n>We investigate optimization problems which arise in such models and find two surprising observations.<n>We prove and empirically show that the learned map is biased, i.e., it does not actually transform the distribution of low-resolution images to high-resolution ones.
  arXiv  Detail & Related papers  (2022-02-02T16:21:20Z)
• Generative Modeling with Optimal Transport Maps [83.59805931374197]
  Optimal Transport (OT) has become a powerful tool for large-scale generative modeling tasks. We show that the OT map itself can be used as a generative model, providing comparable performance.
  arXiv  Detail & Related papers  (2021-10-06T18:17:02Z)
• Solving Inverse Problems by Joint Posterior Maximization with Autoencoding Prior [0.0]
  We address the problem of solving ill-posed inverse problems in imaging where the prior is a JPal autoencoder (VAE) We show that our technique is quite sufficient that it satisfies the proposed objective function. Results also show the robustness of our approach to provide more robust estimates.
  arXiv  Detail & Related papers  (2021-03-02T11:18:34Z)
• End-to-end Interpretable Learning of Non-blind Image Deblurring [102.75982704671029]
  Non-blind image deblurring is typically formulated as a linear least-squares problem regularized by natural priors on the corresponding sharp picture's gradients. We propose to precondition the Richardson solver using approximate inverse filters of the (known) blur and natural image prior kernels.
  arXiv  Detail & Related papers  (2020-07-03T15:45:01Z)
• A deep primal-dual proximal network for image restoration [8.797434238081372]
  We design a deep network, named DeepPDNet, built from primal-dual iterations associated with the minimization of a standard penalized likelihood with an analysis prior. Two different learning strategies: "Full learning" and "Partial learning" are proposed, the first one is the most efficient numerically. Extensive results show that the proposed DeepPDNet demonstrates excellent performance on the MNIST and the more complex BSD68, BSD100, and SET14 datasets for image restoration and single image super-resolution task.
  arXiv  Detail & Related papers  (2020-07-02T08:29:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.