AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
1min snip
Google DeepMind's Vision for AI, Search and Gemini with Oriol Vinyals from Google DeepMind
No Priors: Artificial Intelligence | Technology | Startups
Sampling Beyond Limits: The Illusion of Super-Resolution
Sampling and reconstruction in signal processing adhere to the Nyquist theorem, which states that to accurately reconstruct a signal, one must sample at least twice the frequency of the signal. However, advancements in super-resolution generative models challenge this traditional principle. These models can create high-resolution images from low-resolution inputs by 'hallucinating' additional details based on learned patterns in data. While they provide impressive results, this process essentially circumvents the foundational rules of sampling and reconstruction by leveraging inherent structures in the data, illustrating a tension between theoretical principles and practical innovations in image generation.
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode
Save any
moment
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Share
& Export
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode