{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Computer Vision Decoded","title":"What's New in 2025 for Computer Vision?","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/daa5e3a7\"></iframe>","width":"100%","height":180,"duration":3003,"description":"After an 18 month hiatus, we are back! In this episode of Computer Vision Decoded, hosts Jonathan Stephens and Jared Heinly discuss the latest advancements in computer vision technology, personal updates, and insights from the industry. They explore topics such as real-time 3D reconstruction, computer vision research, SLAM, event cameras, and the impact of generative AI on robotics. The conversation highlights the importance of merging traditional techniques with modern machine learning approaches to solve real-world problems effectively.\nChapters00:00 Intro & Personal Updates\n04:36 Real-Time 3D Reconstruction on iPhones\n09:40 Advancements in SfM\n14:56 Event Cameras\n17:39 Neural Networks in 3D Reconstruction\n26:30 SLAM and Machine Learning Innovation\n29:48 Applications of SLAM in Robotics\n34:19 NVIDIA's Cosmos and Physical AI\n40:18 Generative AI for Real-World Applications\n43:50 The Future of Gaussian Splatting and 3D Reconstruction\nThis episode is brought to you by EveryPoint. Learn more about how EveryPoint is building an infinitely scalable data collection and processing platform for the next generation of spatial computing applications and services: https://www.everypoint.io","thumbnail_url":"https://img.transistorcdn.com/svbWV6r49-pdpieSXBZA2AID_LcN1G2vaCDgYbQPMcg/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS9zaG93/LzMxOTQ2LzE2NTU4/MzEwMTItYXJ0d29y/ay5qcGc.webp","thumbnail_width":300,"thumbnail_height":300}