Computer Vision news and analysis on Web Pulse: 3381 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
Sungkyunkwan University researchers developed a technology that strengthens or weakens AI semiconductor memory by changing light color, using material disorder and defects to mimic brain memory homeostasis. The team expe…
A developer built a selector-free web scraper using Opticparse, an AI-powered tool that captures webpage screenshots and uses Gemini's multimodal vision to extract structured JSON data. The scraper bypasses dynamic CSS c…
A developer launched AlgoVisual Hub, a free and ad-free interactive platform for learning algorithms, operating systems, AI, and computer graphics. The platform offers step-by-step animations for CPU scheduling, sorting,…
Two exhibitions at Kukje Gallery in Seoul explore photography's enduring relationship with observation and material reality amid the rise of AI-generated imagery. Curated by Koo Bohn-chang, "Objects in Oscillation" featu…
Researchers at arXiv analyzed the performance of Med-DDPM, a 3D generative diffusion model for MRI synthesis, across three generations of NVIDIA GPUs. They identified inefficiencies in memory access and Tensor Core utili…
Researchers propose a one-shot novel view and pose human image synthesis method using a conditional denoising diffusion model guided by 3D human priors. The approach outperforms existing techniques on public datasets and…
Researchers propose Conditional-Composition Domain Match (CCDM), a training-free metric family that predicts the utility of synthetic data for object detection, achieving a Spearman correlation of 1.0 with YOLOv8 perform…
Researchers introduced PerceptionDLM, a multimodal diffusion language model that enables parallel region perception for visual tasks, achieving significant speed improvements over sequential methods. The model, built on …
Researchers introduced GLARE, an LLM-based natural language interface that translates user questions into SQL queries over local explanation data to provide global explanations for black-box image classifiers. The system…
Researchers propose a method to learn asynchronous denoising schedules for multi-representation diffusion models, improving visual synthesis. On ImageNet 256x256, their approach achieves FID 1.05 with 4x less training th…
Researchers propose REVEAL++, a differentiable phenotypic grouping method for vision-language retinal modeling that improves Alzheimer's disease risk prediction by treating phenotypic similarity as a continuous, learnabl…
Researchers introduced Language-Instructed Vision Embeddings (LIVE), a method that uses language to dynamically guide vision encoders, eliminating the need for task-specific retraining. LIVE reduced visual hallucinations…
Researchers propose HypOProto, a hyperbolic prototype-based framework for interpretable left ventricular filling pressure classification from B-mode echocardiography, achieving state-of-the-art performance while maintain…
Researchers propose ImageWAM, a world action model that replaces video generation with image editing for robot control, achieving superior performance while reducing computational cost to 1/6 FLOPs and 1/4 latency of vid…
Researchers propose VFACamou, an end-to-end framework for generating adversarial camouflage that remains effective under UAV reconnaissance with changing viewpoints, poses, and lighting. The method integrates UV-volume r…
Researchers propose TeleMorpher, a one-shot framework for simultaneous motion-location editing in videos, addressing a gap in diffusion model-based editing. The method disentangles protagonist and background, uses motion…
Researchers introduced LooseControlVideo, a framework that uses sparse, oriented 3D boxes as a proxy for spatial blocking in text-to-video generation, enabling intuitive control over layout and trajectory. Fine-tuned on …
Researchers introduced LaViSA, a benchmark to evaluate vision-language models' ability to resolve structural ambiguity using visual scenes. Tests on proprietary and open-source models showed they can partially leverage v…
Researchers introduced BrainG3N, a dual-purpose tokenizer for 3D brain MRI generation that decouples encoder and decoder using a masked-autoencoder, enabling both clinically informative embeddings and anatomically faithf…
Researchers propose ProMUSE, a progressive multi-modal uncertainty-guided network for Alzheimer's disease classification that adaptively determines when additional imaging modalities are needed, reducing MRI/PET usage by…