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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add pairwise interaction modules between characters and camera (ablation) | joint character-camera diffusion model · Two-character motion | InterFID: 0.147 -> 0.083 | Improved |
| add pairwise interaction modules (ablation) | joint model · Camera motion | FrameFID: 0.335 -> 0.268 | Improved |
| add pairwise interaction modules (ablation) | joint model · Character-camera coordination | Character-Camera Alignment: 2.298 -> 2.284 | Improved |
| use separate encoders per entity instead of a single shared encoder (ablation) | joint model · Two-character motion | FID: 0.214 -> 0.143 | Improved |
| use separate encoders per entity instead of a single shared encoder (ablation) | joint model · Camera motion | FrameFID: 0.430 -> 0.268 | Improved |
| use separate encoders per entity instead of a single shared encoder (ablation) | joint model · Character-camera coordination | Character-Camera Alignment: 2.310 -> 2.284 | Improved |
| add interaction modules for camera SeqFID (ablation) | joint model · Camera motion | SeqFID: 0.081 -> 0.077 | No clear effect |
| independent encoders without interaction versus joint model on character diversity (ablation) | joint model · Two-character motion | Diversity: 0.580 (w/o Interaction) vs 0.550 (Ours) | Hurt |
| joint character-camera diffusion versus specialized two-character baselines | joint model · Two-character motion | Diversity: 0.565 vs RIG 0.609 | Mixed |
| joint model versus specialized camera method DanceCamera3D | joint model · Camera motion | SeqFID: 0.417 -> 0.256 | Improved |
| joint model versus specialized camera method on diversity | joint model · Camera motion | Diversity: 1.036 (DC3D) vs 0.771 (Ours) | Hurt |
Closest papers by meaning
- Sitcom-Crafter: A Plot-Driven Human Motion Generation System in 3D Scenes (ICLR 2025 · similarity 0.89)
- Unveiling the Value of Motion for Cinematic Camera Trajectories (NeurIPS 2026 · similarity 0.88)
- MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequences (ICLR 2025 · similarity 0.88)
- Auteur: Language-Driven Cinematographic Framing for Human-Centric Video Generation (NeurIPS 2026 · similarity 0.88)
- Look-Before-Move: Narrative-Grounded World Visual Attention in Dynamic 3D Story Worlds (NeurIPS 2026 · similarity 0.87)
- Move-in-2D: 2D-Conditioned Human Motion Generation (CVPR 2025 · similarity 0.87)
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.
