Semantic Motion Correction Via Iterative Nonlinear Optimization and Animation

TL;DR

This paper introduces an end-to-end approach for creating and correcting 2D goalkeeper animations from raw video using iterative nonlinear optimization, ensuring realistic and semantically consistent motion correction.

Contribution

The method combines pose detection with nonlinear optimization to automatically correct goalkeeper motions in animations, improving realism and accuracy compared to prior techniques.

Findings

Successfully corrects various goalkeeper mistakes

Produces semantically similar and realistic animations

Robust to different types of motion errors

Abstract

Here, we present an end-to-end method to create 2D animation for a goalkeeper attempting to block a penalty kick, and then correct that motion using an iterative nonlinear optimization scheme. The input is a raw video that is fed into pose and object detection networks to find the skeleton of the goalkeeper and the ball. The output is a set of key frames of the skeleton associated with the corrected motion so that if the goalkeeper missed the ball, the animation will show then successfully deflecting it. Our method is robust enough correct different kinds of mistakes the goalkeeper can make, such as not lunging far enough or jumping to the incorrect side. Our method is also meant to be semantically similar to the goalkeeper's original motion, which helps keep our animation grounded with respect to actual human behavior.