BlenderFusion is a novel framework that merges 3D graphics editing with diffusion models to enable precise, 3D-aware visual compositing. Unlike prior approaches that struggle with multi-object and camera disentanglement, BlenderFusion leverages Blender for fine-grained control and a diffusion-based compositor for realism, bringing unprecedented flexibility to scene editing and generative compositing. Key Highlights: 3D-Grounded Control: Segments…
Removing backgrounds from images is a common task in design and computer vision. Whether you’re prepping product shots, creating profile pictures, or building visual datasets, automating this process can save hours of manual work. In this blog, we will walk you through building a batch background removal tool using OpenCV. It’s fast, scalable, and outputs…
The Google DeepMind team has unveiled its latest evolution in their family of open models – Gemma 3, and it’s a monumental leap forward. While the AI space is crowded with updates, Gemma 3 isn’t just an incremental improvement; it’s a fundamental upgrade that makes state-of-the-art AI more powerful and accessible. Built on the same…
Thursday on OpenCV Live! we’ve got author and data scientist Kristen Kerher who will tell us about how her interest in computer vision led to writing a children’s book about using CV to let her kids know when the school bus was coming down their street. She holds a Master of Science degree in Applied…
The OpenCV Community Survey for 2025 is open, and we’re asking for your participation! It’s a short, focused online survey open to the entire OpenCV community that will take just a few minutes to complete. Your answers to the survey questions are important to the future of OpenCV. Please help the OpenCV project and take…
Earlier this year OpenCV was selected to be part of the GitHub Secure Open Source Fund, which provides OOS maintainers with financial support to participate in a three-week program educating them on the latest tooling and methods for ensuring the safety of Open Source Software projects. We are honored to be part of the 71…
In the complex world of modern medicine, two forms of data reign supreme: the visual and the textual. On one side, a deluge of images, X-rays, MRIs, and pathology slides. On the other, an ocean of text, clinical notes, patient histories, and research papers. For centuries, the bridge between these two worlds existed only within…
In the fast-paced world of artificial intelligence, a new model is making waves for its innovative approach and impressive performance: MOLMO (Multimodal Open Language Model), developed by the Allen Institute for AI (Ai2). Unlike many of today’s powerful vision-language models, which are often proprietary and closed-source, MOLMO stands out as a shining example of open-source…
Hello, Let me show you an image, can you describe what you see? Perfect! You nailed it: a bird sitting peacefully on a railing. Now, let’s flip it. I’ll describe something, and you imagine how it might appear: “A puppy sitting on a railway track.” Nice! Something like this might be popped right into your…
SimLingo unifies autonomous driving, vision-language understanding, and action reasoning-all from camera input only. It introduces Action Dreaming to test how well models follow instructions, and outperforms all prior methods on CARLA Leaderboard 2.0 and Bench2Drive. Key Highlights Unified Model – Combines driving, VQA, and instruction-following using a single Vision-Language Model (InternVL2-1B + Qwen2-0.5B). State-of-the-Art Driving – Ranks #1 on…