AI Paper Atlas

Research map / Video / Video generation

CoMo: Controllable Motion Generation through Language Guided Pose Code Editing

Yiming Huang, Weilin Wan, Yue Yang, Chris Callison-Burch, Mark Yatskar, Lingjie Liu

ECCV 2024 · Video › Video generation · approach: Text-to-motion diffusion · 43 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 LLM-generated fine-grained keywords as conditioning (ablation)CoMo · HumanML3D testR-Precision Top-1: 0.487 -> 0.502Improved
add LLM-generated fine-grained keywords as conditioning (ablation)CoMo · KIT testFID: 0.399 -> 0.332Improved
add fine-grained keywords (ablation)CoMo · KIT testDiversity: 11.26 -> 10.95Hurt
use codebook of 392 pose codes instead of 205 (ablation)CoMo reconstruction · HumanML3D val reconstructionFID: 0.059 -> 0.034Improved
enlarge codebook beyond 392 (661, 733 codes) (ablation)CoMo reconstruction · HumanML3D val reconstructionFID: 0.034 -> 0.047 (661), 0.037 (733)Hurt
use downsampling rate 4 instead of 16 (ablation)CoMo reconstruction · HumanML3D val reconstructionFID: 0.176 -> 0.034Improved
reduce downsampling rate from 4 to 2 (ablation)CoMo reconstruction · HumanML3D val reconstructionFID: 0.034 -> 0.021Improved
edit pose codes with an LLM instead of regenerating from edited textCoMo vs T2M-GPT and FineMoGen · Motion editing user study (54 participants)human preference: over 70% preferred CoMo on averageImproved
use semantic pose codes for generationCoMo · HumanML3D testMModality: 1.013 vs 2.799 (MDM)Hurt
use pose-code decoding with generation (vs T2M-GPT)CoMo · HumanML3D testinference time per sentence (s): 0.35 -> 0.62Hurt

Later papers that compared with this method

2 later accepted papers report CoMo as a baseline in their results tables; 2 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 0 of 1 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