Research map / Video / Video generation
Lodge++: High-Quality and Long Dance Generation With Robust Choreography Patterns
Ronghui Li, Hongwen Zhang, Yachao Zhang, Yuxiang Zhang, Youliang Zhang, Jie Guo, Yan Zhang, Xiu Li, Yebin Liu
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 Global Choreography Network (GCN) (ablation) | Lodge++ · FineDance (long dance, 1024 frames) | FID_k: 63.38 -> 40.77 | Improved |
| add Global Choreography Network (GCN) (ablation) | Lodge++ · FineDance (long dance, 1024 frames) | Div_k: 4.50 -> 5.53 | Improved |
| add Global Choreography Network (GCN) (ablation) | Lodge++ · FineDance (long dance, 1024 frames) | BAS: 0.2156 -> 0.2423 | Improved |
| use PDDM instead of diffusion guidance (ablation) | Lodge++ · FineDance (long dance, 1024 frames) | FID_k: 53.48 -> 40.77 | Improved |
| use PDDM instead of diffusion guidance (ablation) | Lodge++ · FineDance (long dance, 1024 frames) | BAS: 0.2071 -> 0.2423 | Improved |
| add Foot Refine Block (ablation) | PDDM denoise network · FineDance (long dance, 1024 frames) | FID_k: 52.23 -> 43.72 | Improved |
| add Foot Refine Block (ablation) | PDDM denoise network · FineDance (long dance, 1024 frames) | Foot skating ratio (%): 5.92 -> 3.31 | Improved |
| add Multi-Genre Discriminator (ablation) | PDDM denoise network · FineDance (long dance, 1024 frames) | FID_k: 52.23 -> 45.50 | Improved |
| add Multi-Genre Discriminator to Foot Refine Block (ablation) | PDDM denoise network · FineDance (long dance, 1024 frames) | FID_k: 43.72 -> 40.77 | Improved |
| add Multi-Genre Discriminator to Foot Refine Block (ablation) | PDDM denoise network · FineDance (long dance, 1024 frames) | Foot skating ratio (%): 3.31 -> 4.11 | Hurt |
| add Penetration Guidance (ablation) | Lodge++ · FineDance (long dance, 1024 frames) | Penetration ratio (%): 0.1928 -> 0.0079 | Improved |
| add Penetration Guidance (ablation) | Lodge++ · FineDance (long dance, 1024 frames) | FID_k: 38.92 -> 40.77 | Hurt |
Later papers that compared with this method
11 later accepted papers report Lodge as a baseline in their results tables; 10 of them report a better number on most of the results they share with it.
- FlowerDance: MeanFlow for Efficient and Refined 3D Dance Generation (ECCV 2026 · better on 5 of 7 shared results)
- DiscoForcing: A Unified Framework for Real-Time Audio-Driven Character Control with Diffusion Forcing (ICML 2026 · better on 4 of 6 shared results)
- Walk Before You Dance: High-fidelity and Editable Dance Synthesis via Generative Masked Motion Prior (AAAI 2026 · better on 3 of 5 shared results)
- MotivDance: Fine-Grained Text-Guided Motivation Choreography with Music Synchronization (AAAI 2026 · better on 3 of 4 shared results)
- Music-to-Dance Generation via Atomic Movements (ECCV 2026 · better on 4 of 4 shared results)
- HiChor: Hierarchical Choreography Generation from Pop Music with Choreographic Primitives (ECCV 2026 · better on 3 of 3 shared results)
- Odoriko: A Shape-Aware Multimodal Diffusion Framework for Human Motion (ECCV 2026 · better on 3 of 3 shared results)
- Text Dictates, Music Decorates: Energy-based Attention for Editable Dance Generation (ECCV 2026 · better on 1 of 2 shared results)
3 more not listed.
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
- Lodge: A Coarse to Fine Diffusion Network for Long Dance Generation Guided by the Characteristic Dance Primitives (CVPR 2024 · similarity 0.93)
- MEGADance: Mixture-of-Experts Architecture for Genre-Aware 3D Dance Generation (NeurIPS 2025 · similarity 0.87)
- Breaking the Group Size Barrier: Parameter-Efficient Group Dance Generation with Chain-of-Dancers (NeurIPS 2026 · similarity 0.86)
- DanceAnyWay: Synthesizing Beat-Guided 3D Dances with Randomized Temporal Contrastive Learning (AAAI 2024 · similarity 0.86)
- Controllable 3D Dance Generation Using Diffusion-Based Transformer U-Net (AAAI 2025 · similarity 0.86)
- Harmonious Music-driven Group Choreography with Trajectory-Controllable Diffusion (AAAI 2025 · similarity 0.85)
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.
