Computer Vision news and analysis on Web Pulse: 4297 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
Researchers posted arXiv paper 2610.07031v1, titled "Artemis: Geometry-Grounded Multi-Agent Driving World Models with Shared 3D State and Progressive Memory Update," which proposes a multi-agent driving world model that …
A study posted to arXiv (2610.07071v1) presents BEMD-QBF, a framework combining Bidimensional Empirical Mode Decomposition with Quaternion Bilateral Filtering that converts sharp-kernel CT images into soft-kernel-like re…
A graph neural network combining facial and upper-body skeletal keypoints classified simulated train-driver states into alert, not-alert and emergency classes with 81% accuracy in light conditions, according to a study p…
Researchers posted arXiv paper 2610.07018v1, "When to Rethink: Learning Multi-Perspective Self-Verification for Vision-Language Models," introducing MOTIVE, a Multi-View Self-Verification with Reliability-Guided Selectiv…
Researchers propose DDT-RFE, a Decoupled Diffusion Transformer variant that removes residual connections around the Self-Attention and MLP operations in each encoder block while fusing the input patch embedding with inte…
Researchers introduced learnable spectral activations (LSA), a method that replaces fixed neuron-level nonlinearities with a residual truncated Fourier series whose harmonic amplitudes are learned during training, accord…
A new arXiv paper (2610.07555v1) introduces Global Transport (GT), a global class-agnostic optimal-transport coupling computed without class labels, which consistently improves conditional image generation when combined …
ImgKit launched as a browser-based image toolkit offering 62 tools that process photos locally without uploading them to a server. The tool performs compression, resizing, format conversion, background removal, face blur…
Video world models can generate visually convincing but physically inconsistent sequences, according to research on evaluating their reliability for prediction and planning in embodied AI systems. Existing evaluations ty…
A developer built GoSeek, a mobile scavenger hunt web app that gives players riddle clues instead of direct instructions and requires a live in-app photo of the matching real-world object to score points. The app splits …
A developer built BugDex, an open-source AI-powered insect collection game that uses Google's Gemini multimodal vision API to identify insects, spiders, and arthropods from smartphone photos in real time. The app extract…
Tencent released Prism, an open-source image-to-video AI model that generates native 2K video with synchronized 48kHz audio from a single image, but requires 80GB of VRAM to run at just 720p. Prism is built on Tencent's …
A developer built FloraFind & Grounded, a gamified single-page web app that turns outdoor breaks into quests and uses Google AI Studio's open-weight Gemma 2 and Gemini Flash models to identify plants from text descriptio…
GPT-6 Astra [Max] leads the 4DCodeBench leaderboard, followed closely by Claude Opus 5.5 [High], on a new benchmark that evaluates coding agents on reconstructing dynamic scenes from video by writing executable graphics …
TwelveLabs released Pegasus 1.6, its first AI model built to understand egocentric video shot from the point of view of the person doing the work, targeting robotics, drone, and autonomous-vehicle developers. CEO Jae Lee…
A developer built Bairro em Ação, a walk-first mobile web app that lets residents photograph neighborhood problems like potholes and broken benches with a single tap while walking, then uses Gemma 3 4B running locally th…
A developer released photofresh, an open-source Python script that watches an inbox folder and applies adaptive, per-photo touch-ups to phone JPEGs before writing them into year/month subfolders for an Immich external li…
TwelveLabs released Pegasus 1.6 on October 6, 2026, a video intelligence model with native egocentric video support that automates action segmentation, dense captioning of spatial interactions and quality control for rob…
A York University study led by neuroscientist Kohitij Kar found that nine AI vision networks failed to reproduce the human "motion aftereffect" illusion, while two macaques tested alongside 79 humans showed responses sim…
A developer released a free native macOS image editor built with Swift and Rust that includes an optional AI agent harness allowing a model to remote-control the application to build documents from layers, effects, and b…