Learning to Predict High Frequency Signals via Low Frequency Embeddings

Existing machine learning models still struggle to predict high-frequency details present in data due to regularization, a technique necessary to avoid overfitting.

Hence, researches are conducted whereby high-frequency information is procedurally embedded into low-frequency data so that when the latter is smoothed by the network, the former still retains its high-frequency detail.

Join us on February 8 as Stanford research fellow Jane Wu discusses the specific application of predicting cloth geometry and dynamics, focusing on the efficacy of learning perturbations embedded in low-frequency geometric structures for the specific application of virtual cloth.

Jane has been investigating methods for predicting high-frequency geometric details via low-frequency embeddings for the application of cloth capture.

A recipient of the Don Chamberlin Research Award in 2018 and presenter at the Symposium on Computer Animation (SCA) 2021, Jane has conducted researches in underwater robotics, human-robot interaction, with Google, and with NVIDIA's Autonomous Vehicles Perception team.

As an R&D software engineer in Simulation Technology at NVIDIA, Jane's research interests include computer vision and graphics, including human body and cloth capture, neural rendering, and physics-based machine learning.

======================================================================

Date: February 8, 2022, Tuesday
Time: 7:00 pm - 8:00 pm PT
Venue: https://us02web.zoom.us/j/88215943478?pwd=eW81UDZ4TUZQdG00MVhRaHBObVdsZz09

See you all at the event!

Producer: Elisa Agor, Chair, Silicon Valley ACM SIGGRAPH