AI Paper Atlas

Research map / Video / Video generation

Disentangled Hierarchical VAE for 3D Human-Human Interaction Generation

Zichen Geng, Zeeshan Hayder, Bo Miao, Jian Liu, Wei Liu, Ajmal Saeed Mian

ICLR 2026 · Video › Video generation · approach: Text-to-motion diffusion · 3 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 triplet-loss contrastive learning on z_o (ablation)DHVAE + denoiser · InterHumangFID: 5.063 -> 5.015Improved
add triplet-loss contrastive learning on z_o (ablation)DHVAE + denoiser · InterHumanrFID: 0.499 -> 0.503No clear effect
add triplet-loss contrastive learning on z_o (ablation)DHVAE · InterHuman penetrationPenetration Volume: 0.446 -> 0.390Improved
add global interaction latent z_o (ablation)DHVAE · InterHumangFID: 5.886 -> 5.015Improved
add CoTransformer (ablation)DHVAE · InterHumangFID: 5.593 -> 5.015Improved
use disentangled hierarchical VAE instead of MLD-VAE (ablation)DHVAE · InterHumangFID: 5.694 -> 5.015Improved
use DHVAE instead of MLD-VAE for reconstructionDHVAE · InterHuman reconstructionrFID: 1.011 -> 0.503Improved
add structural positional embedding (SPE) in denoiser (ablation)Denoiser · InterHumangFID: 7.452 -> 5.015Improved
add token scaling in denoiser (ablation)Denoiser · InterHumangFID: 6.531 -> 5.015Improved
add skip connections in denoiser (ablation)Denoiser · InterHumangFID: 5.343 -> 5.015Improved
increase individual encoder layers from 4 to 8 (3 CoTransformer layers) (ablation)DHVAE · InterHumanFID: 5.015 -> 5.612Hurt
increase latent size l from 1 to 7 (ablation)DHVAE · InterHumanFID: 5.015 -> 5.670Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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