The 'tree-dependent components' of natural scenes are edge filters
We propose a new model for natural image statistics. Instead of minimizing dependency between components of natural images, we maximize a simple form of dependency in the form of tree-dependency. By learning filters and tree structures which are best suited for natural images we observe that the resulting filters are edge filters, similar to the famous ICA on natural images results. Calculating the likelihood of the model requires estimating the squared output of pairs of filters connected in the tree. We observe that after learning, these pairs of filters are predominantly of similar orientations but different phases, so their joint energy resembles models of complex cells.
Code (0)
등록된 구현이 없습니다.
Tasks
FormMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
CityRefer: Geography-aware 3D Visual Grounding Dataset on City-scale Point Cloud Data
City-scale 3D point cloud is a promising way to express detailed and complicated outdoor structures. It encompasses both the appearance and geometry features of segmented city components, including cars, streets, and bui…
3D visual groundingAutonomous VehiclesVisual GroundingThird-Order Edge Statistics: Contour Continuation, Curvature, and Cortical Connections
Association field models have been used to explain human contour grouping performance and to explain the mean frequency of long-range horizontal connections across cortical columns in V1. However, association fields esse…
Global-Aware Edge Prioritization for Pose Graph Initialization
The pose graph is a core component of Structure-from-Motion (SfM), where images act as nodes and edges encode relative poses. Since geometric verification is expensive, SfM pipelines restrict the pose graph to a sparse s…
Image RetrievalFrom Sparse and Imperfect 2D Anchors to Consistent 3D Gaussian Street Scenes: Support-Aware Appearance
Image priors can synthesize target conditions for 3D Gaussian street scenes, but independently edited views do not define a coherent 3D target. Direct fitting can propagate view-specific noise, while existing pipelines d…
Planar-SfM: Camera Pose Estimation via Homography Graph Embeddings
Structure from Motion (SfM) systems traditionally struggle with planar scenes, where standard epipolar geometry-based methods become degenerate. Rather than viewing planar surfaces as a limitation, we propose a unified f…
Camera Pose Estimation