Computer Vision news and analysis on Web Pulse: 3369 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
Retail stores are evolving from static transaction endpoints into dynamic decision engines, driven by AI-informed shoppers who seek confidence and personalization. Brands like Sephora and Nike are redesigning spaces with…
China's Ministry of State Security warned that a popular augmented reality game may be providing geospatial data to train foreign military AI models. The ministry cited reports that an AI company linked to the game harve…
A developer argues that browser-based AI agents fail not because of model limitations but because they lack a structured runtime perception layer that captures live page state. The post introduces SiFR (Structured Interf…
A solo developer added AI background removal to Convertify, a free image converter, in one week using only Rust and no Python. The backend runs ONNX models natively via the ort crate, avoiding the need for a separate Pyt…
The Mano-P team released Mano-CUA 2.0, a 4B-parameter GUI agent that runs on a MacBook, and found that the primary bottleneck was not model size but insufficient Chinese GUI training data. After adding more Chinese inter…
Recent AI research introduces RL-driven agentic optimization using dense token-level supervision and progress advantage signals to stabilize training. PhysiFormer injects 3D geometric reasoning into diffusion transformer…
Researchers introduced P3Sim, a physical world modeling system that simulates future scene states from partial observations and incomplete 3D transformation signals. The system combines a learned world model, geometric c…
Researchers introduced NormAct, a benchmark evaluating whether multimodal large language models comply with hidden social norms during embodied planning. Tests on GPT-5.4, Claude Opus 4.7, and Gemini 3 Pro showed models …
JD.com launched Oxygen AIIC, an industrial-scale platform using LLMs/VLMs to manage item knowledge for tens of billions of SKUs. The platform achieves 94.2% precision and 82.8% recall in knowledge production, processes h…
Researchers have developed OverFlowLight, a real-time framework that uses multi-modal sensing from cameras and radars to detect and prevent queue overflow at urban intersections. Deployed across 43 intersections in three…
Researchers propose CoIn, a novel framework for 3D scene inpainting that bridges 2D inpainting models and Gaussian Splatting through a multi-stage consistency pipeline. The method handles both object removal and insertio…
Researchers developed a distribution-based deep multiple instance learning method for tumor proportion scoring in non-small cell lung cancer, using only slide-level labels to predict zero-inflated beta parameters. The ap…
Researchers introduced TruEye, a model that detects and localizes AI-generated or manipulated humans in images with fine-grained classification across five compositional categories, including real humans composited into …
Researchers introduced SelectAnyTree, a promptable instance segmentation model for 3D forest LiDAR point clouds that delineates individual trees from a few clicks. The model achieves 78.2% Intersection over Union (IoU) f…
Researchers fine-tuned Gemini 2.5 Pro on 400 clinician-rated home videos to score 30 behavioral features for autism assessment, improving inter-rater reliability with clinicians by 40% and boosting zero-shot ASD diagnosi…
Researchers propose SemCityLoc, a semantic-geometric alignment system for aerial 6DoF localization that uses foundation-model-derived visual priors and standardized LoD-compliant 3D city models, improving recall by up to…
Researchers propose vMFProto, a distributional part-prototype framework that models each class as a mixture of von Mises-Fisher components on the hypersphere for interpretable classification. The method achieves state-of…
Researchers propose a framework to expand human motion generation by using large-scale synthetic motion data and a redesigned VQ-VAE tokenizer, overcoming the limited diversity of motion capture datasets. The approach im…
Researchers introduced DMV-Bench, the first interactive benchmark for multimodal-agent visual memory, testing agents' ability to recall visual cues from product images in a simulated e-commerce environment. Their propose…
Researchers introduced Tessellating the Earth (TTE), a learnable location encoder using Spherical Voronoi partitions that allocates representational capacity to discriminative areas. TTE sets a new state of the art in ge…