Computer Vision news and analysis on Web Pulse: 4325 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
EverestLabs launched Navigator, an agentic AI platform for materials recovery facilities, on August 24, moving beyond robotic sorters to coordinate entire recycling plants. Founder JD Ambati's system uses computer vision…
Flock Safety's AI-powered license plate recognition cameras have a distinctive oval, hooded shape with a circular lens and visible solar panel arrays, according to a CNET guide by a reporter who has covered the surveilla…
Higgsfield AI, a generative AI company with $500M in annual revenue run rate and 25M+ users, is hiring an on-site ML Engineer (Data Engine) in Almaty, Kazakhstan, to analyze video motion, train reward models, and build v…
A developer has released Palimpsest, a high-performance C++ CLI tool that extracts text from screen recordings of scrolling documents, deduplicating overlapping frames and outputting clean .txt or .docx files. The tool r…
A developer built APIC-Web, a full image editor that runs entirely in the browser using Canvas, WebAssembly, and on-device machine learning, ensuring photos never leave the device. The project demonstrates how to achieve…
Researchers propose ArtiMo, a zero-shot agent-driven framework that uses large language and vision-language models to animate articulated 3D meshes from text without fine-tuning, leveraging URDF kinematic constraints and…
Researchers released AGIDefect-4K, a dataset of 4,000 AI-generated images from 15 generative models with hierarchical annotations for defect detection, segmentation, explanation, and quality scoring, and introduced AGIDA…
Researchers introduced TopoSurfel, a framework that improves 3D surface reconstruction from Gaussian Splatting by dynamically extracting a continuous proxy mesh via a non-trainable differentiable iso-surfacing process, e…
Researchers propose PanoCtrl, an object-centric framework for text-to-panorama generation that converts textual descriptions into structured object-level spherical conditions, integrating them into the diffusion process.…
A new benchmark from arXiv (2608.20608v1) evaluates deep learning methods for grape leaf disease classification and detection, finding near-saturated classification on controlled datasets but sharp performance drops in c…
Researchers propose ANT, a segmentation-guided test-time adaptation framework that improves prostate cancer detection in micro-ultrasound by aligning encoder representations to prostate anatomy, achieving a 2.9% and 3.6%…
Grounded-Exo2Ego, a dual-branch video diffusion model introduced by researchers, outperforms recent state-of-the-art methods on the EgoExo4D dataset for exocentric-to-egocentric video generation, addressing extreme view …
Researchers introduced RECOUNT, a plug-and-play framework for image-guided zero-shot object counting that uses a single off-scene reference image and a diffusion model to generate a diverse exemplar gallery, improving co…
Researchers introduced StateSight, a procedurally generated benchmark for evaluating vision-language models' latent spatial-state reconstruction, and found that OpenAI's GPT-5.5 (API model identifier gpt-5.5) achieved 59…
A new arXiv preprint (2608.20548v1) introduces a disaster-conditioned kernel-regularized graph attention model for building damage classification that improves macro-F1 and reduces residual spatial autocorrelation under …
Qwen, Alibaba's AI team, has released Qwen-Image-2-Pro, a 20-billion-parameter text-to-image model now available on Replicate. The model excels at rendering complex text, particularly Chinese logographic characters, and …
Jichengdu at ByteDance developed Flux-Pulid, a face identity customization model built on the FLUX diffusion architecture that implements the PuLID method presented at NeurIPS 2024. The model uses contrastive alignment t…
Bria's Fibo-Edit model, available on Replicate, uses JSON-based control for deterministic, pixel-precise image editing, replacing ambiguous text prompts. The 8-billion-parameter model supports tasks like recoloring, reli…
The Hypir-Sd2 model, developed by 0x3f3f3f3fun at the Shenzhen Institutes of Advanced Technology, performs image restoration and upscaling using diffusion-based score priors, built on Stable Diffusion 2.1 with LoRA weigh…
Vufinder has released Vggt-1b-Depth, a feed-forward neural network based on research from Meta AI and the University of Oxford's Visual Geometry Group, which infers 3D scene attributes from single or multiple image views…