Computer Vision news and analysis on Web Pulse: 3357 curated articles tracking the latest Computer Vision developments, tools, and research, updated continuously from vetted sources.
Researchers propose GRE-Diff, a diffusion-based framework that automates floor plan creation and editing under user constraints, using Gaussian Room Embeddings to model rooms as spatial distributions. The system generate…
Researchers introduced GIRAF, a text-conditioned diffusion model that generates realistic full-body human interactions with articulated objects, addressing limitations of prior work focused on static objects or hand-only…
A new review of remote sensing foundation models (RSFMs) finds that no single geospatial foundation model is universally best and that inconsistent evaluation hinders fair comparison and reliable deployment. The chapter …
Researchers propose LightCrafter, a hybrid pipeline for video relighting that combines physically-based rendering (PBR) with generative video diffusion refinement. By translating a PBR proxy of the input video under targ…
Researchers propose LOGOS, a transformer-based model that uses textual prompts to guide oriented object detection in aerial and satellite imagery. The approach outperforms existing methods on the DOTA dataset, particular…
Researchers introduced DreamCharacter-1, a lightweight post-adaptation framework that enhances pretrained 3D foundation models for high-fidelity, production-ready 3D character generation. The framework includes geometry …
Researchers propose SAGA, a training-free stable acceleration guidance method for autoregressive video generation that reduces temporal errors like flickering and motion jitter by using spectral guidance and noise initia…
Researchers propose a hybrid classical-quantum image classification framework using a mixture of experts, achieving a two-fold reduction in failure rate on MNIST and Fashion-MNIST benchmarks compared to individual expert…
Researchers released Infinity-Parser2, a large multimodal model for end-to-end document parsing, along with a 5-million-sample bilingual corpus Infinity-Doc2-5M. The model uses multi-task reinforcement learning across ei…
Researchers introduced APIVOT, a VLM-based planner that adaptively interleaves language and visual thoughts for long-horizon robot planning. APIVOT outperforms general-purpose VLMs and prior frameworks on kitchen tasks, …
InternNav, an open-source toolbox for embodied navigation built on PyTorch, Habitat, and Isaac Sim, has been released. It supports modular navigation systems, multiple simulation platforms, and includes the InternVLA-N1 …
A developer launched bgchanger.video, an AI video background changer that runs entirely in the browser. The tool allows users to remove or replace video backgrounds without heavy editing software, targeting creators, ind…
Fleek, a B2B marketplace for secondhand clothing wholesale, raised $25 million in Series B funding led by Burda Principal Investments with participation from eBay, FJ Labs, and H14. The company uses AI-powered computer v…
A developer tested OpenCV Zoo's SFace face recognition model by generating 128-dimensional face embeddings and performing nearest neighbor search on two datasets: Olivetti Faces and Labeled Faces in the Wild. The test us…
A researcher used Anthropic's J-lens method to analyze LLaVA-1.5-7B's internal state during visual question answering, finding that the model's internal workspace accurately registers object presence or absence even when…
A new workflow using Claude Code and Gemini Omni enables video creators to generate custom AI B-roll footage, animated web highlights, and background effects without stock footage. The process involves extracting video f…
Runway and Seedance 2.0 enable solo creators to produce cinematic video intros and location transitions without a production crew. The workflow uses Runway's keyframe feature for controlled motion between frames and Seed…
Runway, Seedance 2.0, and Gemini Omni offer distinct AI video generation capabilities for content creators, with Runway providing polished cinematic motion at higher cost, Seedance delivering high-fidelity outputs from B…
A practical guide explains how to use AI screen monitoring by capturing screenshots every five seconds and analyzing them with computer vision to identify workflow inefficiencies, potentially recovering two or more hours…
AMD GPUs running SGLang Diffusion on ROCm achieve 1.5x to 6.3x speedups over Hugging Face Diffusers for image generation and editing tasks, as demonstrated on models including FLUX.1-dev, Qwen-Image, and Z-Image-Turbo. T…