The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence) Trends in Computer Vision with Georgia Gkioxari - #549
25 snips
Jan 3, 2022 
Georgia Gkioxari, a research scientist at Meta AI specializing in computer vision, dives into the year's groundbreaking advancements. She discusses how Neural Radiance Fields (NeRF) are reshaping 3D scene reconstruction and the advantages of transformers over CNNs in image recognition. Gkioxari examines the evolving role of ImageNet and the exciting challenges posed by emerging fields like the metaverse. Additionally, she highlights promising startups and the collaborative future for hardware and software researchers in the AI landscape.
AI Snips
Chapters
Transcript
Episode notes
NERF's Impact
- NERF reconstructs photorealistic 3D scenes from images, not CAD models.
- It uses implicit functions and volumetric rendering, allowing novel viewpoint synthesis.
NERF's Expanding Influence
- NERF's impact extends beyond scene reconstruction to dynamic scenes, lighting, and materials.
- The combination of implicit functions and volumetric rendering drives innovation in graphics.
Transformers in Vision
- Transformers are replacing CNNs in computer vision, especially with large datasets.
- They treat images as sequences of tokens, offering greater representational power but needing more data.