Computer Vision news and analysis on Web Pulse: 4311 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
A developer built a Digital Udhar Record System for a shopkeeper friend, digitizing handwritten credit notes into a searchable, secure record-keeping app. The project uses a Flask and SQLite backend with an HTML/CSS fron…
Jabhook is a boxing training system that uses pose estimation and a frontier LLM to analyze a fighter's combinations and deliver specific corrective feedback, according to its developer. The system records movement with …
Researchers at Brown University led by engineering professor Arto Nurmikko built a brain-inspired imaging system that combines a dynamic vision sensor with a deep spiking neural network to image and track randomly moving…
A new approach called LEGO-Anything turns single photos into editable Blender code for 3D scenes, with GPT-6 Astra leading an accompanying benchmark at up to 53 percent reconstruction accuracy, according to The Decoder. …
A developer measured the white fringe that appears when background-removed PNGs are composited over dark backgrounds and found that premultiplied alpha does not remove it: on a test cutout the fringe averaged a luminance…
Researchers Alpay Ozkan and colleagues released UnRL, an adaptive 3D mapping framework that refines voxels using semantic entropy, geometric curvature, and texture richness, and adds a reinforcement learning agent that l…
A study of hZACH-ViT, a compact Vision Transformer with Euclidean, Poincaré, and spherical prototype heads, found that reducing Poincaré curvature from c=1 to c=0.1 improved clean MacroF1 in all 15 paired seed-dataset co…
Tavus announced Griffin, which it calls the first model to pass the video Turing test, with 48% of people who talked to it live believing it was a real human, versus a pass rate below 3% for previous systems. Tavus said …
A developer at AI Flip Room built a three-gate validation pipeline that checks every AI-generated room render before it reaches users, combining a structured-output vision judge, 16 indoor and 9 outdoor preservation chec…
A developer behind CardGrade, a phone-photo trading-card pre-grading app, described an architecture in which a border-detection model warps each card side to a flat canvas and slices it into 16 inspection zones, with a v…
A developer built a Kaggle benchmark of 336 synthetic Grafana-style monitoring panels to test whether vision models can read dashboards the way an on-call engineer does, grading each model on five fields: event type, sta…
JED AI has launched J3D Eye, a real-time global camera intelligence and OSINT dashboard that aggregates live multi-source video feeds, satellite overlays and perimeter feeds into a unified command center. The team says t…
Roboflow published a walkthrough of turning vision-language model predictions into a production inspection system, using GPT-6 Astra's detection of hot spots in thermal images of solar panels as the example. The post det…
A 12-year-old developer has released KODA Web v25, a browser-based AI coding mentor running on a Cloudflare Worker, adding native OCR and file ingestion so it can read screenshots and uploaded source files directly. The …
Ortus AI released RightWayUp, an Apache-2.0 licensed 360° image rotation model that predicts how far an image is rotated (0–359°) with a confidence score and abstains when it cannot determine which way is up. The model i…
A developer built SignBridge, an open-source bidirectional real-time sign language interpreter, for a deaf friend who communicates primarily through Vietnamese Sign Language. The system runs MediaPipe hand-landmark track…
Researchers posted arXiv:2610.00040v1, introducing DSSR-3D, an inference-time framework for view-dependent referring segmentation on continuous 3D Gaussian fields that requires no retraining of the underlying semantic fi…
Researchers introduced the Function-Space Transformer (FST), a framework that learns from functions via a spatially adaptive continuous latent representation, storing features at anchors whose locations are predicted fro…
Researchers introduced Spatial Lifting (SL), a method that lifts 2D image inputs into a higher-dimensional space and processes them with networks such as a 3D U-Net, according to the arXiv paper 2610.00017v1. The authors…
Researchers introduced MRFFU-Net, a deep learning architecture that adds a Multi-Resolution Feature Fusion (MRFF) module to U-Net-like encoder-decoder structures for MRI segmentation, according to an arXiv paper (arXiv:2…