Hugging Face Trending Papers
Overlapping Visual Grouping Without Semantic Priors
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv Computer Vision
Sep 24
Overlapping Visual Grouping Without Semantic Priors
The paper introduces Domain Parent Grouping (DPG), a sensor‑grounded method that forms perceptual units directly from raw measurements without relying on semantic priors. DPG operates across three domains—local luminance, direct chromatic, and contextual chromatic—creating spatially connected groups that overlap across domains, thus producing a non‑exclusive grouping representation. Experiments on the BSDS500 dataset show that DPG’s groups align with low‑level image structure and correlate with human‑annotated regions and boundaries.
Hugging Face Trending Papers
Aug 6
Prior-SG: Task and Prior Driven Region Segmentation for Scene Graphs in Arbitrarily-Structured Environments
Hierarchical 3D scene graphs are a promising representation for high-level spatial reasoning in autonomous mobile platforms. However, existing extraction frameworks typically rely on purely local visual clustering or strict geometric heuristics, such as wall-separated rooms, which fail in open-plan or arbitrarily-structured environments.
arXiv AI
Oct 2
Geometric Similarity in VLM Low-Level Vision Representations
The paper introduces GeoSim, a four‑level framework for analyzing how vision‑language models (VLMs) represent low‑level vision tasks. It evaluates hidden‑layer representations across 24 tasks and two VLM paradigms—autoregressive models and diffusion transformers—using global similarity, local geometry, sparse feature decomposition, and topological verification. The study uncovers the organizing principles of low‑level visual representations and highlights their limitations in cross‑task and cross‑model agreement, offering an interpretability lens for assessing latent transferability and diagnosing model‑specific issues.
Hugging Face Trending Papers
Aug 31
Semantic-Spatial Discriminability Enhancement for Generalized Visual Grounding
Generalized Visual Grounding (GVG) task aims to localize targets in an image based on referring expressions, extends the classical visual grounding paradigm by integrating multi-target and non-target...
arXiv Computer Vision
Sep 1
Semantic-Spatial Discriminability Enhancement for Generalized Visual Grounding
arXiv:2608.30233v1 Announce Type: new Abstract: Generalized Visual Grounding (GVG) task aims to localize targets in an image based on referring expressions, extends the classical visual grounding par...
arXiv Machine Learning
Aug 12
More Accurate, Less Human: Gestalt Grouping in Vision Models
arXiv:2608. 10195v1 Announce Type: cross Abstract: Human vision organizes what it sees into wholes: same-colored points group into series, similar marks cohere into categories, and shapes complete into recognizable objects.