Impressive ML research building a coloured 3D model from a single photo of an outfit!
https://shunsukesaito.github.io/PIFu/
ML still seems to be making major strides. I'm not sure if this means technique breakthroughs, or if we're just fine-tuning established techniques.
miniblog.
Related Posts
Really cute approach to reporting type errors: when there's a type error, show an example of a runtime error that the type check has prevented!
Data-Driven Techniques for Type Error Diagnosis https://escholarship.org/uc/item/59s4h4pv
On how far programming language research has come, and the maturity of tools and techniques that make more ambitious projects viable:
Generated Code Generates Overconfident Coders: https://www.deeplearning.ai/the-batch/issue-180/
A study of programmers found that using a LLM for completion produced buggier code but users were more confident in it.
I wonder if this generalises to other completion techniques?
