Papers › ParCo: Part-Coordinating Text-to-Motion Synthesis

ParCo: Part-Coordinating Text-to-Motion Synthesis

27 Mar 2024arXiv:2403.18512archive 2025-07-28

Qiran Zou, Shangyuan Yuan, Shian Du, Yu Wang, Chang Liu, Yi Xu, Jie Chen, Xiangyang Ji

We study a challenging task: text-to-motion synthesis, aiming to generate motions that align with textual descriptions and exhibit coordinated movements. Currently, the part-based methods introduce part partition into the motion synthesis process to achieve finer-grained generation. However, these methods encounter challenges such as the lack of coordination between different part motions and difficulties for networks to understand part concepts. Moreover, introducing finer-grained part concepts poses computational complexity challenges. In this paper, we propose Part-Coordinating Text-to-Motion Synthesis (ParCo), endowed with enhanced capabilities for understanding part motions and communication among different part motion generators, ensuring a coordinated and fined-grained motion synthesis. Specifically, we discretize whole-body motion into multiple part motions to establish the prior concept of different parts. Afterward, we employ multiple lightweight generators designed to synthesize different part motions and coordinate them through our part coordination module. Our approach demonstrates superior performance on common benchmarks with economic computations, including HumanML3D and KIT-ML, providing substantial evidence of its effectiveness. Code is available at https://github.com/qrzou/ParCo .

PaperPDFCode

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

Code

qrzou/parco officialmentioned in papermentioned on GitHubpytorchApache-2.0 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.

Code Syntology ran Syntology

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

Tasks

Motion Synthesis

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Motion Synthesis HumanML3D ParCo Diversity 9.576 #16 of 37 Archive leaderboard report
Motion Synthesis HumanML3D ParCo FID 0.109 #16 of 37 Archive leaderboard report
Motion Synthesis HumanML3D ParCo Multimodality 1.382 #16 of 37 Archive leaderboard report
Motion Synthesis HumanML3D ParCo R Precision Top3 0.801 #16 of 37 Archive leaderboard report
Motion Synthesis KIT Motion-Language ParCo Diversity 10.95 #18 of 31 Archive leaderboard report
Motion Synthesis KIT Motion-Language ParCo FID 0.453 #18 of 31 Archive leaderboard report
Motion Synthesis KIT Motion-Language ParCo Multimodality 1.245 #18 of 31 Archive leaderboard report
Motion Synthesis KIT Motion-Language ParCo R Precision Top3 0.772 #18 of 31 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

Absolute Position EncodingsAdamAttentionAttention DropoutBPECosine AnnealingDense ConnectionsDiscriminative Fine-TuningDropoutGPTLabel SmoothingLayer NormalizationLinear LayerLinear Warmup With Cosine AnnealingMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformerVQ-VAEWeight Decay

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