1 code implementation • 17 Mar 2024 • Paul S. Scotti, Mihir Tripathy, Cesar Kadir Torrico Villanueva, Reese Kneeland, Tong Chen, Ashutosh Narang, Charan Santhirasegaran, Jonathan Xu, Thomas Naselaris, Kenneth A. Norman, Tanishq Mathew Abraham
Reconstructions of visual perception from brain activity have improved tremendously, but the practical utility of such methods has been limited.
1 code implementation • 12 Dec 2023 • Reese Kneeland, Jordyn Ojeda, Ghislain St-Yves, Thomas Naselaris
At each iteration, we sample a small library of images from an image distribution (a diffusion model) conditioned on a seed reconstruction from the previous iteration.
1 code implementation • 1 Jun 2023 • Reese Kneeland, Jordyn Ojeda, Ghislain St-Yves, Thomas Naselaris
This emphasis belies the fact that there is always a family of images that are equally compatible with any evoked brain activity pattern, and the fact that many image-generators are inherently stochastic and do not by themselves offer a method for selecting the single best reconstruction from among the samples they generate.
no code implementations • 30 Apr 2023 • Reese Kneeland, Jordyn Ojeda, Ghislain St-Yves, Thomas Naselaris
Past reconstruction algorithms employed brute-force search through a massive library to select candidate images that, when passed through an encoding model, accurately predict brain activity.