Skip to yearly menu bar Skip to main content


In Search of a Data Transformation That Accelerates Neural Field Training

Junwon Seo · Sangyoon Lee · Kwang In Kim · Jaeho Lee

Arch 4A-E Poster #130
[ ]
Wed 19 Jun 5 p.m. PDT — 6:30 p.m. PDT
Oral presentation: Orals 2B Deep learning architectures and techniques
Wed 19 Jun 1 p.m. PDT — 2:30 p.m. PDT


Neural field is an emerging paradigm in data representation that trains a neural network to approximate the given signal. A key obstacle that prevents its widespread adoption is the encoding speed - generating neural fields requires an overfitting of a neural network, which can take a significant number of SGD steps to reach the desired fidelity level. In this paper, we delve into the impacts of data transformations on the speed of neural field training, specifically focusing on how permuting pixel locations affect the convergence speed of SGD. Counterintuitively, we find that randomly permuting the pixel locations can considerably accelerate the training. To explain this phenomenon, we examine the neural field training through the lens of PSNR curves, loss landscapes, and error patterns. Our analyses suggest that the random pixel permutations remove the easy-to-fit patterns, which facilitate easy optimization in the early stage but hinder capturing fine details of the signal.

Live content is unavailable. Log in and register to view live content