Open Source
GramStatTexNet: Efficient, Interpretable, and Neuro-Inspired Texture Analysis-by-Synthesis
arXiv cs.GR0 views
arXiv:2611.23755v1 Announce Type: cross Abstract: Deep networks achieve high realism in texture synthesis but often rely on opaque, over-parameterized representations that have limited direct connection to biological vision. Neuroscience-informed pyramid models are interpretable, compact, and biologically inspired, but rely on small, hand-curated statistics sets that are difficult to generalize or extend. We introduce GramStatTexNet, a hybrid analysis-by-synthesis framework that combines the multi-scale Gabor filter structure of classical models with the flexibility of Gramian-based correlations, organized into structured filter families. This structured representation enables analyses that are challenging for deep-feature methods: each statistic carries a named filter-family identity, allowing us to decompose synthesis fidelity into per-family contributions and to learn an interpretable, low-dimensional embedding that preserves perceptual texture content. We compare our framework to classical and deep texture-synthesis baselines across diverse texture categories, and on multiple perceptual metrics, highlighting the compactness and interpretability advantages of this hybrid representation, alongside competitive synthesis quality. This same framework extends naturally to peripheral textures via spatial pooling, and to dynamic textures using a spatiotemporal filter bank. GramStatTexNet provides a unified, interpretable framework for analyzing and modeling visual information with natural extensions across space, time, and eccentricity. Project page: https://vdutell.github.io/gstn
Source:https://arxiv.org/abs/2611.23755PreviousNIRJALA: Draining the Sea out of Gaussian Splatting with Three-Path Optics and Reversible PhysicsNextProbing Physics in Motion Diffusion Models Against Their Own Estimate
Related posts
UPDF 3.0: One PDF Workflow from OCR and Editing to eSign
0FOSS Bytes
Revenant XSpark Signs Pranav Venkatesh as Its First Chess Player for Google Play Arena
0FOSS Bytes
The 1 MB problem: what 2,023 real PDFs say about file size in 2026
0dev.to UX
umux v1.8.1 through v1.8.6: software that stopped pretending
0dev.to Productivity
Tests that prove something: break a copy and see the test fail
0dev.to Testing

Independent Deployability Has Two Halves. Most Teams Built One.
0dev.to Kubernetes