Detection, segmentation, depth and recognition research, plus the vision backbones that keep displacing the last generation.
arXiv:2609.14654v1 Announce Type: new Abstract: Convolutional neural networks (CNNs) are typically evaluated using held-out classification accuracy, an approach that presupposes predictions are based...
arXiv:2609.15659v1 Announce Type: cross Abstract: Native 3D generators turn one image into a single mesh. TRELLIS.2 and its peers deliver high-fidelity non-watertight geometry with materials, but the...
arXiv:2609.15400v1 Announce Type: new Abstract: Vessel segmentation in X-ray coronary angiography (XCA) is a fundamental step for quantitative coronary analysis and subsequent assessment of coronary...
arXiv:2609.14377v1 Announce Type: new Abstract: Camouflage image generation (CIG) aims to synthesize realistic camouflaged images by blending foreground objects into concealment-compatible background...
MedVA is an end‑to‑end neuro‑symbolic agentic system designed to streamline medical volume visualization. It combines a neuro‑symbolic intent formulation agent that refines natural‑language requests with symbolic reasoning, a multi‑model ROI identification agent that uses pretrained medical segmentation models to locate specified regions, and an objective‑driven visualization optimization agent that evaluates ROI visibility using a volume‑based objective. Extensive evaluations and a formative user study demonstrate the system’s effectiveness and high usability across users with varying expertise.
arXiv:2609.14619v1 Announce Type: new Abstract: LiDAR--4-D radar fusion combines accurate spatial geometry with motion and reflectivity cues from radar, offering a promising solution for 3-D object d...
The paper introduces a flexible symbolic framework that efficiently computes logical explanations for deep neural networks by parameterizing explanations with internal neuron activations and leveraging general-purpose logical engines like SMT solvers. Unlike previous methods that rely on specialized verifiers or are limited to individual input features, this approach is not restricted in shape and can scale to deep architectures. Experiments on image recognition and medical benchmarks demonstrate improved computational efficiency and the ability to explain networks that were previously intractable for logic-based methods.
arXiv:2609.14943v1 Announce Type: new Abstract: Pseudo-labeling is a strong paradigm for semi-supervised medical image segmentation, yet its effectiveness is highly sensitive to confidence thresholdi...
arXiv:2609.14185v1 Announce Type: cross Abstract: Bird's Eye View (BEV)-based multi-view 3D object detection suffers from challenges of computational complexity, multi-scale feature extraction, and e...
arXiv:2609.14106v1 Announce Type: new Abstract: We evaluated parameter-efficient fine-tuning (PEFT) of the Segment Anything Model (SAM) for liver tumor segmentation in abdominal CT of colorectal live...
arXiv:2609.13654v1 Announce Type: new Abstract: Pretrained foundation models (FMs) have achieved remarkable success in computer vision, yet their high fine-tuning cost limits practical deployment. Pa...
arXiv:2603.13044v2 Announce Type: replace-cross Abstract: Medical image segmentation (MIS) is a fundamental component of computer-assisted diagnosis and clinical decision support. Over the past decad...
arXiv:2412.03044v3 Announce Type: replace Abstract: Video anomaly detection (VAD) is a vital yet complex open-set task in computer vision, commonly tackled through reconstruction-based methods. Howev...
arXiv:2609.13647v1 Announce Type: new Abstract: The rapid development of unmanned aerial vehicle (UAV) technology has made aerial-image object detection increasingly important for natural-resource mo...
arXiv:2609.15228v1 Announce Type: new Abstract: Unsupervised registration of large-scale LiDAR point clouds remains challenging due to the geometric ambiguity inherent in outdoor scenes, which degrad...
arXiv:2603.02790v2 Announce Type: replace Abstract: Foundation models are changing the way we develop medical artificial intelligence. By learning broadly generalizable features across diverse data m...
arXiv:2609.13246v1 Announce Type: new Abstract: Plane segmentation from a single RGB image remains challenging due to imprecise region grouping and geometrically inconsistent supervision, often leadi...
The paper evaluates eleven vision‑language models (VLMs) for extracting structured fields from business documents, focusing on robustness, cost, and governance rather than just accuracy. Using a held‑out set of 750 synthetic checks, the study finds that fine‑tuning open‑source VLMs on 3,000 samples yields an F1 score above 0.98, surpassing all zero‑shot commercial systems, while GPT‑5 tops the commercial group and Claude Sonnet 4.5 fails on date extraction. The authors also present a practitioner‑oriented selection framework that maps task profiles—such as quality, latency, governance, and volume—to recommended approaches via filtering and total‑cost minimization, demonstrated on a mid‑volume document‑extraction scenario.
arXiv:2609.13267v1 Announce Type: new Abstract: Scientific charts encode quantities in axes, legends, and geometric marks, yet large vision-language models still treat them as natural photographs. Vi...
arXiv:2609.13226v1 Announce Type: new Abstract: Machine learning for neglected tropical diseases is limited by data, not algorithms: public annotated image sets for leprosy (Hansen's disease) number...