AI Paper Atlas

Research map / 3D vision / 3D generation

Making Avatars Interact: Towards Text-Driven Human-Object Interaction for Controllable Talking Avatars

youliang zhang, zhengguang zhou, Zhentao Yu, Ziyao Huang, Teng Hu, Sen Liang, Guozhen Zhang, Ziqiao Peng, Shunkai Li, Yi Chen, Zixiang Zhou, Yuan Zhou and 2 more

ECCV 2026 · 3D vision › 3D generation · approach: Scene-aware human motion synthesis · 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 PIM motion planning (joint generation) (ablation)AIM-only video generator · GroundedInterVLM-QA: 26.19 -> 28.89Improved
add PIM motion planning (joint generation) (ablation)AIM-only video generator · GroundedInterHand Quality (HQ): 0.711 -> 0.925Improved
use joint training instead of cascaded frozen PIM (ablation)InteractAvatar · GroundedInterVLM-QA: 28.19 -> 28.89Improved
use layer-wise injection instead of last-layer-only injection (ablation)InteractAvatar · GroundedInterVLM-QA: 28.31 -> 28.89Improved
use zero-initialized residual injection instead of simple addition (ablation)InteractAvatar · GroundedInterVLM-QA: 28.46 -> 28.89Improved
add modified RoPE for ref image (ablation)PIM · GroundedInterVLM-QA: 26.36 -> 27.15Improved
add detection data in PIM pre-training (ablation)PIM · GroundedInterVLM-QA: 27.15 -> 27.87Improved
add Det.+Cont. data in PIM pre-training (ablation)PIM · GroundedInterVLM-QA: 27.87 -> 28.89Improved
prepend instead of append ref image (ablation)PIM · GroundedInterVLM-QA: 26.71 -> 27.15Improved
use RGB motion instead of 2D (x,y) motion (ablation)InteractAvatar · GroundedInterVLM-QA: 26.07 -> 28.89Improved
add audio-only pre-training stage before joint audio-motion training (ablation)AIM · GroundedInterSync_conf: 4.23 -> 5.49Improved
train audio first then add motion instead of motion first (ablation)AIM · GroundedInterSync_conf: 3.98 -> 5.49Improved

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