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.
By Teemu Saukkio, Hashem Haghbayan, Juha Plosila
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.
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.
By Shao-Jun Xia, Huixin Zhang, Zhen Lei, Anlan Sun, Yuner Zhang, Xiaoyang Chen
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: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...
By Kaiyan Lei, Xu-Yao Zhang
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.
By Sudhanva Manjunath Athreya, Sai Phani Kumar Malladi
We formulate computer vision as unified multimodal generation, where heterogeneous visual tasks are expressed in the native text and image generation spaces of a unified multimodal model, without task-specific architectures. Under this formulation, SenseNova-Vision uses natural-language instructions and optional visual prompts to specify tasks, target regions or views, and decoding conventions, and generates responses as text for symbolic outputs, images for dense spatial predictions, or mixed text-and-image outputs for compositional tasks.
arXiv:2607. 00620v1 Announce Type: cross Abstract: Generalized Category Discovery (GCD) aims to recognize known classes while autonomously discovering novel ones in open-world settings.
By Boyang Dai, Chaoqi Chen, Yizhou Yu
GrabVG is a visual grounding framework for UAV imagery that tackles the challenges of small, densely packed, and visually similar objects by separating the task into preattentive hypothesis search and graph-attentive feature binding. It first generates a compact set of reliable object hypotheses using distillation-guided proposal induction and text-aware filtering, then constructs a sparse graph where language-guided visual cues and inter-instance topological relationships are jointly bound and propagated via graph attention. Experiments on AerialVG and AerialSense demonstrate that GrabVG achieves a strong accuracy–speed trade‑off, reaching 67.31% and 80.34% Acc@0.5 and outperforming baselines by 10.55 and 8.76 percentage points.
Open-vocabulary remote sensing segmentation has recently emerged as a promising paradigm that enables pixel-level recognition of arbitrary categories specified by natural language, including classes unseen during training. However, geospatial domain shifts caused by heterogeneous regions, spatial resolutions, and acquisition platforms weaken visual-text matching and limit cross-dataset generalization.
DeCo introduces an efficient decouple-to-couple learning framework for multi-task visual grounding, addressing conflicts between localization and segmentation tasks. It first applies Task-aware Semantic Decoupling (TSD) to separate shared visual cues into task-specific features guided by salient words, then uses Hybrid Prior Coupling (HPC) to merge sentence-level semantic priors with mask-derived spatial priors for improved grounding. Experiments across multiple natural and remote sensing datasets show that DeCo achieves state‑of‑the‑art performance while requiring only lightweight trainable parameters on a frozen multimodal encoder.
By Xiaoqiang Lu, Licheng Jiao, Long Sun, Yuting Yang, Xu Liu, Lingling Li, Wenping Ma, Fang Liu
Where generalization capacity--the ability to extract context-invariant relational structures--first emerges remains a central question in AI and neuroscience. The foundation for this capacity lies up...