Skip to content

← ArchivePaper2019

Robust Marker Trajectory Repair for MOCAP Using Kinematic Reference

Maksym Perepichka, Daniel Holden, Sudhir P. Mudur, Tiberiu Popa

MIGUbisoft18 cites1 descendantRetargeting

Automatic method for repairing missing and noisy marker trajectories in mocap data using kinematic skeleton as a reference.

Abstract

Processing motion capture data from optical markers for use in computer animations presents numerous technical challenges. Artifacts caused by noise, marker swaps, and marker occlusions often require manual intervention of a professionally trained marker tracking artist that spends large amounts of time and effort fixing these issues. Existing automatic solutions that attempt to fix marker data lack robustness due to either failing to properly detect and fix marker paths, or generating solutions that are challenging to integrate within current animation pipelines. In this paper, we present a method that robustly identifies invalid marker paths, removes the associated segments and generates new kinematically correct paths. We start by comparing the kinematic solutions generated by commercial software against the one generated by the state-of-the-art methods, using this information to determine which animation keyframes are invalid. Subsequently, we regenerate marker paths from the neural network based method [Holden 2018] and use a sophisticated marker filling algorithm to combine them with the original marker paths at sections where we detect the original data to be invalid. Our method outperforms alternatives by generating solutions that are both closer to the ground truth and more robust, allowing for manual intervention if required.

How to read this

Category
Method: automatic repair of optical mocap marker trajectories
Contributions
  • Robustly identifies invalid marker paths (noise, marker swaps, occlusions), removes the bad segments, and regenerates kinematically correct paths
  • Detects invalid keyframes by comparing the kinematic solution from commercial software against a state-of-the-art neural method
  • Combines neural-regenerated marker paths (Holden 2018) with original marker data via a marker-filling algorithm at detected invalid sections
Context
Relates to optical mocap cleanup and builds directly on neural marker-solving work (Holden 2018), using a kinematic skeleton reference to gate where regeneration is applied.
Correctness
Targets robustness over prior automatic methods and pipeline integrability; validity detection depends on agreement between commercial and neural kinematic solvers, so failure modes where both agree on a wrong solution are a reader caveat.
Clarity
Accessible to anyone familiar with mocap pipelines; a first pass conveys the detect-remove-regenerate strategy, a second pass clarifies the filling algorithm.
How to read it
First pass for the detect-and-repair pipeline and where it slots into existing tools; second pass on the invalid-keyframe detection and marker-filling steps if you process optical mocap.

Builds on

Nothing in the archive, this is a starting point.

Built upon by

Related work

Keywords

This page summarises the entry and links to its original source. The archive never hosts or redistributes the publication itself.Show it in the full archive list →