Papers › Generating Holistic 3D Human Motion from Speech

Generating Holistic 3D Human Motion from Speech

8 Dec 2022CVPR 2023 1arXiv:2212.04420archive 2025-07-28

Hongwei Yi, Hualin Liang, Yifei Liu, Qiong Cao, Yandong Wen, Timo Bolkart, DaCheng Tao, Michael J. Black

This work addresses the problem of generating 3D holistic body motions from human speech. Given a speech recording, we synthesize sequences of 3D body poses, hand gestures, and facial expressions that are realistic and diverse. To achieve this, we first build a high-quality dataset of 3D holistic body meshes with synchronous speech. We then define a novel speech-to-motion generation framework in which the face, body, and hands are modeled separately. The separated modeling stems from the fact that face articulation strongly correlates with human speech, while body poses and hand gestures are less correlated. Specifically, we employ an autoencoder for face motions, and a compositional vector-quantized variational autoencoder (VQ-VAE) for the body and hand motions. The compositional VQ-VAE is key to generating diverse results. Additionally, we propose a cross-conditional autoregressive model that generates body poses and hand gestures, leading to coherent and realistic motions. Extensive experiments and user studies demonstrate that our proposed approach achieves state-of-the-art performance both qualitatively and quantitatively. Our novel dataset and code will be released for research purposes at https://talkshow.is.tue.mpg.de.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

yhw-yhw/talkshow officialmentioned on GitHubpytorchSyntology: not harvested report
yhw-yhw/show mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
zhenglinzhou/headstudio mentioned on GitHubjaxMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to HeadStudio: Text to Animatable Head Avatars with 3D Gaussian Splatting (arXiv:2402.06149; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Face AnimationGesture GenerationMotion Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Face Animation BEAT2 TalkShow MSE 7.791 #3 of 5 Archive leaderboard report
Gesture Generation BEAT2 TalkShow FGD 0.6209 #9 of 14 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

VQ-VAE

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections