Computer Vision news and analysis on Web Pulse: 3343 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
China Telecom's Institute of Artificial Intelligence (TeleAI) and Harbin Institute of Technology have developed ShotPlan, a cinematic video generation method built on Wan2.1-T2V-14B that uses learnable planning tokens to…
Researchers introduced GenSyn10, a CIFAR-10-aligned synthetic image dataset of 60,000 images generated using three architecturally diverse models (FLUX.2-dev, HunyuanImage-3.0, and Qwen-Image-2512) to benchmark AI-genera…
Researchers propose Neural Depth Field (NDF), showing that a depth estimator can function as a scene-level implicit field for 3D geometry inpainting and reconstruction. NDF reduces cross-view inconsistency by 63.3% and i…
ForensicNet, a lightweight deep learning framework combining MobileNetV2 with Convolutional Block Attention Modules, achieves 92.4% accuracy and 90.8% precision on face identification across 15,000 images from LFW and SC…
Researchers propose Identity-Consistent Expression Fields (ICEF), a framework that disentangles static identity-specific radiance from dynamic expression-conditioned deformation in Neural Radiance Fields for few-shot fac…
Researchers introduced ARGO, a fully-sensorized smart eyewear platform that uses the STM32N6 microcontroller's integrated Neural Processing Unit (NPU) to run on-device machine learning, achieving 10 FPS and ~113 minutes …
Researchers show that the frozen predictor from Joint-Embedding Predictive Architectures (JEPAs) can be transferred across encoder families to improve occluded feature completion. In experiments, pairing CLIP with the I-…
A new benchmark called RobustMAD, developed by researchers and described in arXiv:2607.16243v1, reveals that multimodal small language models (MSLMs) can outperform larger models like GPT-5 Nano on industrial anomaly det…
A new arXiv preprint introduces ColGraphRAG, a late-interaction evidence retrieval method for multimodal GraphRAG that replaces single-vector bi-encoder similarity with MaxSim-style multi-vector scoring for graph-linked …
Researchers propose DocOCR-Eval, an annotation-free framework for automatically evaluating and selecting OCR tools without ground-truth labels. The framework uses a three-stage correction and ranking strategy that aggreg…
Researchers introduce Alignment-Aware Bridge Matching (A²BM), a bridge matching method that leverages image pair alignment during training to improve image-to-image translation fidelity with weakly aligned data. A²BM con…
Researchers have released MFGNet-Gear, a synthetic 3D dataset of 24,000 paired polygon meshes and point clouds across 12 gear designs and 4 quality classes, to support deep learning for manufacturing quality inspection. …
Researchers propose 3D FaceShell, a framework that adds subtle, learnable perturbations to 3D face avatars to mislead vision-language models (VLMs) from inferring sensitive attributes, while preserving geometric fidelity…
Researchers propose Supermartingale-based Label Transition (SLT), an anchor-free loss correction framework for robust quantum neural network (QNN)-based medical image classification under noisy labels. SLT models entropy…
A developer compares PyTorch and TensorFlow for computer vision projects, noting that PyTorch dominates research with dynamic computation graphs and recent performance improvements via torch.compile(), while TensorFlow l…
A developer has launched Portraify, an AI tool that converts 1–3 casual photos into professional headshots and ID photos, addressing the inconvenience and cost of traditional photo studios. The AI prioritizes likeness wi…
Researchers from MIT and other institutions have developed iTracker, a convolutional neural network for eye tracking that works on commodity mobile phones and tablets without additional sensors, achieving a prediction er…
Neat, the AI-native workplace collaboration platform, announced two distributed AI capabilities at InfoComm 2026: Neat Pulse MCP for agent-driven device management and Intelligent Framing for equitable meeting experience…
Eventual Inc. released daft-physical-ai, an open-source Python library built on Daft that provides ready-made operations for turning raw robot video into training-ready data, starting with hand tracking and reward scorin…
Vidmoat, a new video editor built for AI agents, allows users to edit videos by giving plain-language commands to an integrated agent or connecting external agents like Claude Code and Cursor via the Model Context Protoc…