AI Paper Atlas

Research map / Video / Video generation

ParCo: Part-Coordinating Text-to-Motion Synthesis

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

ECCV 2024 · Video › Video generation · approach: Text-to-motion diffusion · 42 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add part coordination module to 6-part generators (ablation)ParCo · HumanML3D testFID: 3.652 -> 0.109Improved
add part coordination module to upper/lower-body generators (ablation)Up&LowBody discretization · HumanML3D testFID: 0.497 -> 0.172Improved
add part coordination module to 6-part generators (ablation)ParCo · HumanML3D testR-Precision Top-1: 0.375 -> 0.515Improved
use 6-part partition instead of upper/lower body, with coordination (ablation)ParCo · HumanML3D testFID: 0.172 -> 0.109Improved
use 6 parts without coordination instead of 2 parts without coordination (ablation)part generators without coordination · HumanML3D testFID: 0.497 -> 3.652Hurt
evaluate ReMoDiffuse with random motion length instead of ground-truth length (ablation)ReMoDiffuse · HumanML3D testFID: 0.103 -> 0.281Hurt
evaluate ReMoDiffuse with random motion length instead of ground-truth length (ablation)ReMoDiffuse · KIT-ML testFID: 0.155 -> 0.589Hurt
use ParCo instead of T2M-GPT across text-length quartilestext-to-motion · HumanML3D test subsets by text lengthmetrics across quartilesImproved
use six small part generators instead of a single large generatorT2M-GPT baseline · HumanML3D testparameters (M) / inference time (s): 237.6 -> 168.4 M; 0.544 -> 0.036 sImproved
use ParCo's 6 part VQ-VAEs instead of a single whole-body VQ-VAE (ablation)motion VQ-VAE · HumanML3D reconstructionFID: 0.070 -> 0.021Improved
ParCo vs AttT2M on diversity of generation for one textParCo · HumanML3D testMModality: 2.452 -> 1.382Hurt

Later papers that compared with this method

3 later accepted papers report ParCo as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy