Pith. sign in

REVIEW

Aggregated Multi-GANs for Controlled 3D Human Motion Prediction

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2103.09755 v1 pith:TGKGDG4L submitted 2021-03-17 cs.CV

Aggregated Multi-GANs for Controlled 3D Human Motion Prediction

classification cs.CV
keywords motionpredictionhumanactivityaggregatedbodycurrentfuture
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Human motion prediction from historical pose sequence is at the core of many applications in machine intelligence. However, in current state-of-the-art methods, the predicted future motion is confined within the same activity. One can neither generate predictions that differ from the current activity, nor manipulate the body parts to explore various future possibilities. Undoubtedly, this greatly limits the usefulness and applicability of motion prediction. In this paper, we propose a generalization of the human motion prediction task in which control parameters can be readily incorporated to adjust the forecasted motion. Our method is compelling in that it enables manipulable motion prediction across activity types and allows customization of the human movement in a variety of fine-grained ways. To this aim, a simple yet effective composite GAN structure, consisting of local GANs for different body parts and aggregated via a global GAN is presented. The local GANs game in lower dimensions, while the global GAN adjusts in high dimensional space to avoid mode collapse. Extensive experiments show that our method outperforms state-of-the-art. The codes are available at https://github.com/herolvkd/AM-GAN.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.