Learning Neural Volumetric Representations of Dynamic Humans in Minutes

Zhen Xu, Hujun Bao, Xiaowei Zhou, Sida Peng, Chen Geng

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.

Repositories linked to this paper

zju3dv/instant-nvr — marked official in Papers with Code

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

Abstract

Figure 1. Convergence rate of training. Given a monocular video of a human performer, our model can be learned in ∼5 minutes to produce photorealistic novel view rendering, which is 100 times faster than Neural Body [58].

For agents

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

get_harvested_code_for_paper("2302.12237")
get_code_for_paper("2302.12237")
have("2302.12237")

Connect an agent — have() is free.