SOMA: Solving Optical Marker-Based MoCap Automatically

Michael Black, Nima Ghorbani

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

nghorbani/moshpp — marked official in Papers with Code
nghorbani/soma — 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: SOMA transforms raw motion capture (mocap) point clouds (black dots) to labeled markers (colored dots). The cubes in yellow are detected "ghost" points; e.g. spurious reflections, non-body markers, or unidentified points. With labeled mocap we fit SMPL-X bodies (blue mesh) using MoSh [26, 28].

For agents

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

get_harvested_code_for_paper("2110.04431")
get_code_for_paper("2110.04431")
have("2110.04431")

Connect an agent — have() is free.