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.
Instacart is deploying AI-powered Caper Carts, edge computing, and computer vision to bridge online grocery intelligence with in-store shopping, aiming to reinvent the grocery store experience. The technology enables rea…
Korea's Royal Palaces and Tombs Center, under the Royal Heritage Administration, announced Friday it is launching a four-month field test of autonomous AI patrol robots at Deoksu Palace and the Seooreung Royal Tombs thro…
A new arXiv paper (2608.19553v1) introduces label-free precision refinement (LFPR), a method that improves grounding bounding-box accuracy by routing predicted-small regions to a higher-resolution pass without accessing …
Researchers introduced VGI-bench, a benchmark with 27 tasks and 810 instances for evaluating visual reasoning in video generation models, finding that even the strongest model, Seedance 2.0, achieves only 51.0% accuracy.…
Researchers proposed HiRA-CAM, an improved gradient-based visual explanation method for convolutional neural networks (CNNs), and showed it outperforms LayerCAM and Grad-CAM on creating saliency maps for object classific…
Researchers propose CVSD-Reg, a global LiDAR registration framework that distills visual semantic priors from a vision foundation model into LiDAR representations, achieving strict success rates of 97.7% on KITTI, 99.0% …
Researchers from NEC Laboratories America introduced CAViAR (Causal Accident Video and Incident Analysis Repository), a human-annotated dashcam benchmark of 2,249 real-world accident videos from CarCrashDataset (CCD) and…
Researchers introduced TT-Net, a conditional GAN architecture that replaces per-channel SVD denoising with a two-cut tensor-train decomposition to access cross-channel information, and in controlled comparisons it outper…
Researchers propose Stream4D, a method that replaces the static 3D reconstruction critic with a feed-forward 4D reconstruction reward to improve streaming autoregressive diffusion video models, addressing geometric drift…
Researchers propose Answer-Level Trust Selection (ATS), a post-hoc framework that accepts or rejects individual vision-language model (VLM) predictions for physical quantity estimation without fine-tuning or internal log…
A new study from arXiv (2608.20149v1) evaluates neural-based hillshading against analytical methods in downtown Calgary using high-resolution DEM and DSM data, finding that the machine-learning system Eduard, trained on …
A new framework called VideoRun2D Demo uses markerless human pose estimation to perform biomechanical analysis of sprinters, achieving average root-mean-square errors between 11.46° and 5.83° for the best trackers, which…
Australian start-up Cropify will commercially grade pulses such as lentils and chickpeas using artificial intelligence for the first time this harvest, a world-first that promises efficiency gains for the nation's $22bn …
A developer has built a real-time multimodal nutrition engine using OpenAI's GPT-4o Vision API, which can estimate calories and macronutrients from a photo of a meal. The system uses few-shot prompting and Pydantic for s…
DeepSeek released DeepSeek-V4-Flash-Vision-Exp on August 21, 2026, pricing every image at up to 384 tokens with no vision surcharge, making bulk product-catalogue image QA cost about $0.000225 per image off-peak. The 384…
A new approach to generating visual datasets uses script-generated images with reproducible metadata and Adobe Generator tools, enabling controlled evaluation and diagnostics for machine learning models. The method allow…
Iceland, the UK frozen food retailer, has cut losses from theft and shrink by 80% after rolling out SAI One, an AI-powered loss prevention platform from SAI, across its more than 1,000 UK stores. The system, which uses c…
The City of Moreton Bay will trial a $170,000 AI-powered traffic signal system at the Moreton Parade and Paper Avenue intersection in Petrie, north of Brisbane, later in 2026, marking Australia's first such trial. The sy…
Flock Safety CEO Garrett Langley said on the All-In Podcast that drones are the company's fastest-growing business unit and will account for nearly half of its future revenue, as the surveillance firm expands beyond lice…
Instacart is hiring a Senior Machine Learning Engineer for its Digital Twin Platform team, offering a salary of $206k–218k/yr for remote work in Canada (ON, AB, BC, or NS). The role involves developing and deploying ML m…