SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2212.00190 · 2022

Mixed Neural Voxels for Fast Multi-view Video Synthesis

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 3 functions out of this paper's own repositories and ran 3 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.

RepositoryRoleRan
fengres/mixvoxels canonical 3 of 3
FunctionStatusWhere it lives
positional_encoding Ran fengres/mixvoxels/models/mixvoxels.py
pointer only (licence: GPL-3.0) · get_code("11a10efa60767162")
sigma2alpha Ran fengres/mixvoxels/models/mixvoxels.py
pointer only (licence: GPL-3.0) · get_code("f5952b9b949ac285")
static_raw2alpha Ran fengres/mixvoxels/models/mixvoxels.py
pointer only (licence: GPL-3.0) · get_code("17d2e357cb6ba1bb")

Repositories linked to this paper

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

Abstract

Synthesizing high-fidelity videos from real-world multi-view input is challenging because of the complexities of real-world environments and highly dynamic motions. Previous works based on neural radiance fields have demonstrated high-quality reconstructions of dynamic scenes. However, training such models on real-world scenes is time-consuming, usually taking days or weeks. In this paper, we present a novel method named MixVoxels to better represent the dynamic scenes with fast training speed and competitive rendering qualities. The proposed MixVoxels represents the 4D dynamic scenes as a mixture of static and dynamic voxels and processes them with different networks. In this way, the computation of the required modalities for static voxels can be processed by a lightweight model, which essentially reduces the amount of computation, especially for many daily dynamic scenes dominated by the static background. To separate the two kinds of voxels, we propose a novel variation field to estimate the temporal variance of each voxel. For the dynamic voxels, we design an inner-product time query method to efficiently query multiple time steps, which is essential to recover the high-dynamic motions. As a result, with 15 minutes of training for dynamic scenes with inputs of 300-frame videos, MixVoxels achieves better PSNR than previous methods. Codes and trained models are available at https://github.com/fengres/mixvoxels

For agents

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

get_harvested_code_for_paper("2212.00190")
get_code_for_paper("2212.00190")
have("2212.00190")

Connect an agent — have() is free.