Research map / Video / Video generation
DiTex4D: Direct Text-Driven 4D Generation with Structured Latent Diffusion
Xiaozhe Chen, Mengqi Rong, Jian Liu, Shuhan Shen
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 mixed-4D RoPE (4D RoPE + 3D APE) instead of 1D RoPE + 3D APE (ablation) | DiTex4D base · 4D generation from scratch (8 frames) | CLIP score: 25.48 -> 25.54 | Improved |
| add mixed-4D RoPE instead of only 4D RoPE (ablation) | DiTex4D base · 4D generation from scratch (8 frames) | CLIP score: 23.64 -> 25.54 | Improved |
| add mixed-4D RoPE instead of only 4D RoPE (ablation) | DiTex4D base · 4D generation from scratch (8 frames) | motion smoothness: 0.964 -> 0.996 | Improved |
| add correlated noise injection (ablation) | DiTex4D base · 4D generation from scratch (8 frames) | motion smoothness: 0.977 -> 0.996 | Improved |
| add correlated noise injection (ablation) | DiTex4D base · 4D generation from scratch (8 frames) | CLIP score: 25.17 -> 25.54 | Improved |
| add correlated noise injection (ablation) | DiTex4D base · 4D generation from scratch (8 frames) | dynamic degree: 0.406 -> 0.281 | Mixed |
| add 4D interpolation model (ablation) | DiTex4D base · 4D generation from scratch (8 frames) | motion smoothness: 0.986 -> 0.996 | Improved |
| add multi-view CLIP image condition (ablation) | DiTex4D animation · 3D animation from static mesh | I2V: 0.918 -> 0.948 | Improved |
| add multi-view CLIP image condition (ablation) | DiTex4D animation · 3D animation from static mesh | dynamic degree: 0.377 -> 0.250 | Mixed |
| use DiTex4D instead of ActionMesh | ActionMesh · 4D generation from scratch | CLIP score: 25.38 -> 25.51 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- ActionMesh — ActionMesh: Animated 3D Mesh Generation with Temporal 3D Diffusion (CVPR 2026) · better on 4 of 4 shared results
- AnimateAnyMesh — AnimateAnyMesh: A Feed-Forward 4D Foundation Model for Text-Driven Universal Mesh Animation (ICCV 2025) · better on 3 of 4 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
- A Unified Approach for Text- and Image-guided 4D Scene Generation (CVPR 2024 · similarity 0.92)
- Diffusion4D: Fast Spatial-temporal Consistent 4D generation via Video Diffusion Models (NeurIPS 2024 · similarity 0.91)
- Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models (CVPR 2024 · similarity 0.91)
- 4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling (CVPR 2024 · similarity 0.91)
- EG4D: Explicit Generation of 4D Object without Score Distillation (ICLR 2025 · similarity 0.91)
- 4Real: Towards Photorealistic 4D Scene Generation via Video Diffusion Models (NeurIPS 2024 · similarity 0.90)
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.
