AI Paper Atlas

Research map / Video / Video generation

InterGen: Diffusion-Based Multi-human Motion Generation Under Complex Interactions

Han Liang, Wenqian Zhang, Wenxuan Li, Jingyi Yu A, Lan Xu

IJCV 2024 · Video › Video generation · approach: Text-to-motion diffusion · 174 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
use non-canonical shared-frame representation instead of canonical (ablation)InterGen · InterHuman testFID: 11.322 -> 5.918Improved
use non-canonical shared-frame representation instead of canonical (ablation)InterGen · InterHuman testR-Precision Top-1: 0.134 -> 0.371Improved
add mutual attention conditioning instead of concatenation (ablation)InterGen · InterHuman testFID: 6.273 -> 5.918Improved
add mutual attention conditioning instead of concatenation (ablation)InterGen · InterHuman testR-Precision Top-1: 0.303 -> 0.371Improved
add weights sharing between the two denoisers (ablation)InterGen · InterHuman testFID: 8.059 -> 5.918Improved
add weights sharing between the two denoisers (ablation)InterGen · InterHuman testR-Precision Top-1: 0.153 -> 0.371Improved
add masked joint distance map (DM) loss (ablation)InterGen · InterHuman testFID: 6.653 -> 5.918Improved
add relative orientation (RO) loss (ablation)InterGen · InterHuman testFID: 6.311 -> 5.918Improved
add regularization loss schedule t<=0.7T instead of none (ablation)InterGen · InterHuman testFID: 7.862 -> 5.918Improved
apply regularization loss at all timesteps instead of t<=0.7T (ablation)InterGen · InterHuman testFID: 5.918 -> 7.037Hurt
raise regularization threshold from 0.7T to 0.8T (ablation)InterGen · InterHuman testFID: 5.918 -> 6.521Hurt
replace CLIP-ViT-L/14 text encoder with LLaMA-7B (ablation)InterGen · InterHuman testFID: 5.918 -> 5.865Mixed

Later papers that compared with this method

19 later accepted papers report InterGen as a baseline in their results tables; 18 of them report a better number on most of the results they share with it.

11 more not listed.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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