Streamable Neural Fields

Eunbyung Park, Junwoo Cho, Seungtae Nam, Daniel Rho, Jong Ko

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 4 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• jwcho5576/streamable_nf — marked official in Papers with Code; named in the paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Neural fields have emerged as a new data representation paradigm and have shown remarkable success in various signal representations. Since they preserve signals in their network parameters, the data transfer by sending and receiving the entire model parameters prevents this emerging technology from being used in many practical scenarios. We propose streamable neural fields, a single model that consists of executable sub-networks of various widths. The proposed architectural and training techniques enable a single network to be streamable over time and reconstruct different qualities and parts of signals. For example, a smaller sub-network produces smooth and lowfrequency signals, while a larger sub-network can represent fine details. Experimental results have shown the effectiveness of our method in various domains, such as 2D images, videos, and 3D signed distance functions. Finally, we demonstrate that our proposed method improves training stability, by exploiting parameter sharing. Our code is available at https://github.com/jwcho5576/streamable_nf.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2207.09663")
get_code_for_paper("2207.09663")
have("2207.09663")

Connect an agent — have() is free.