AI Paper Atlas

Research map / 3D vision / 3D generation

Towards Storytelling Animations: Joint Synthesis of Human and Camera Motions

Boyuan Cheng, Yingjie Xi, Rui He, Jinhe Na, Ying Cao, Pengjie Wang, Jian J. Zhang, Xiaosong Yang

CVPR 2026 · 3D vision › 3D generation · approach: Scene-aware human motion synthesis

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 pairwise interaction modules between characters and camera (ablation)joint character-camera diffusion model · Two-character motionInterFID: 0.147 -> 0.083Improved
add pairwise interaction modules (ablation)joint model · Camera motionFrameFID: 0.335 -> 0.268Improved
add pairwise interaction modules (ablation)joint model · Character-camera coordinationCharacter-Camera Alignment: 2.298 -> 2.284Improved
use separate encoders per entity instead of a single shared encoder (ablation)joint model · Two-character motionFID: 0.214 -> 0.143Improved
use separate encoders per entity instead of a single shared encoder (ablation)joint model · Camera motionFrameFID: 0.430 -> 0.268Improved
use separate encoders per entity instead of a single shared encoder (ablation)joint model · Character-camera coordinationCharacter-Camera Alignment: 2.310 -> 2.284Improved
add interaction modules for camera SeqFID (ablation)joint model · Camera motionSeqFID: 0.081 -> 0.077No clear effect
independent encoders without interaction versus joint model on character diversity (ablation)joint model · Two-character motionDiversity: 0.580 (w/o Interaction) vs 0.550 (Ours)Hurt
joint character-camera diffusion versus specialized two-character baselinesjoint model · Two-character motionDiversity: 0.565 vs RIG 0.609Mixed
joint model versus specialized camera method DanceCamera3Djoint model · Camera motionSeqFID: 0.417 -> 0.256Improved
joint model versus specialized camera method on diversityjoint model · Camera motionDiversity: 1.036 (DC3D) vs 0.771 (Ours)Hurt

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