Research map / Video / Video generation
ActionMesh: Animated 3D Mesh Generation with Temporal 3D Diffusion
Remy Sabathier, David Novotny, Niloy J. Mitra, Tom Monnier
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 stage I temporal 3D diffusion over per-frame generation (ablation) | ActionMesh · ActionBench (32 scenes ablation) | CD-4D: 0.187 -> 0.069 | Improved |
| add stage II temporal 3D autoencoder (ablation) | ActionMesh · ActionBench (32 scenes ablation) | CD-3D: 0.050 -> 0.050 | No clear effect |
| add both stages on top of TripoSG (ablation) | TripoSG · ActionBench (32 scenes ablation) | CD-3D: 0.050 -> 0.050 | No clear effect |
| use TripoSG instead of Craftsman backbone (ablation) | ActionMesh · ActionBench (32 scenes ablation) | CD-4D: 0.117 -> 0.069 | Improved |
| use ActionMesh instead of best prior method | video-to-4D · ActionBench (128 scenes) | CD-4D: 0.126 -> 0.081 | Improved |
Later papers that compared with this method
3 later accepted papers report ActionMesh as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.
- Fast 4D Mesh Generation by Spatio-Temporal Attention Chains (NeurIPS 2026 · better on 7 of 8 shared results)
- DiTex4D: Direct Text-Driven 4D Generation with Structured Latent Diffusion (ECCV 2026 · better on 4 of 4 shared results)
- MotionDreamer: Universal Skeletal Motion Generation for 3D Rigged Shapes (ECCV 2026 · better on 3 of 3 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
- Generative Rendering: Controllable 4D-Guided Video Generation with 2D Diffusion Models (CVPR 2024 · similarity 0.90)
- Animate3D: Animating Any 3D Model with Multi-view Video Diffusion (NeurIPS 2024 · similarity 0.90)
- ARMesh: Autoregressive Mesh Generation via Next-Level-of-Detail Prediction (NeurIPS 2025 · similarity 0.89)
- PivotMesh: Generic 3D Mesh Generation via Pivot Vertices Guidance (ICLR 2025 · similarity 0.89)
- MeshArt: Generating Articulated Meshes with Structure-Guided Transformers (CVPR 2025 · similarity 0.88)
- DreamMesh4D: Video-to-4D Generation with Sparse-Controlled Gaussian-Mesh Hybrid Representation (NeurIPS 2024 · similarity 0.88)
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.
