Research map / Video / Video generation
Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal Consistency
Tianqi Liu, Zihao Huang, Zhaoxi Chen, Guangcong Wang, Shoukang Hu, Liao Shen, Huiqiang Sun, Zhiguo Cao, Wei Li, Ziwei 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 MonST3R 4D structure initialization (ablation) | Free4D · User study (ablation) | user preference, consistency (without / with): 14% / 86% | Improved |
| add adaptive CFG (ablation) | Free4D · User study (ablation) | user preference, consistency (without / with): 14% / 86% | Improved |
| add point cloud guided denoising (ablation) | Free4D · User study (ablation) | user preference, consistency (without / with): 14% / 86% | Improved |
| add reference latent replacement (ablation) | Free4D · User study (ablation) | user preference, consistency (without / with): 24% / 76% | Improved |
| add fine-stage refinement (ablation) | Free4D · User study (ablation) | user preference, consistency (without / with): 4% / 96% | Improved |
| add modulation-based refinement (ablation) | Free4D · User study (ablation) | user preference, consistency (without / with): 5% / 95% | Improved |
| use modulation-based refinement instead of SDS (ablation) | Free4D · User study (ablation) | user preference, consistency (without / with): 8% / 92% | Improved |
| add MonST3R 4D structure initialization (ablation) | Free4D · User study (ablation) | user preference, aesthetic (without / with): 9% / 91% | Improved |
| add fine-stage refinement (ablation) | Free4D · User study (ablation) | user preference, aesthetic (without / with): 6% / 94% | Improved |
| add modulation-based refinement (ablation) | Free4D · User study (ablation) | user preference, aesthetic (without / with): 6% / 94% | Improved |
| add reference latent replacement (ablation) | Free4D · User study (ablation) | user preference, dynamic (without / with): 31% / 69% | Improved |
Later papers that compared with this method
2 later accepted papers report Free4D as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- Geometry-Aware Single-Image 4D Synthesis via Dense Trajectory Generation (ECCV 2026 · better on 3 of 4 shared results)
- S$^{2}$VG: 3D Stereoscopic and Spatial Video Generation via Denoising Frame Matrix (TPAMI 2026 · better on 2 of 2 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- 4Real — 4Real: Towards Photorealistic 4D Scene Generation via Video Diffusion Models (NeurIPS 2024) · 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
- Diffusion4D: Fast Spatial-temporal Consistent 4D generation via Video Diffusion Models (NeurIPS 2024 · similarity 0.91)
- EG4D: Explicit Generation of 4D Object without Score Distillation (ICLR 2025 · similarity 0.90)
- 4Diffusion: Multi-view Video Diffusion Model for 4D Generation (NeurIPS 2024 · similarity 0.90)
- Consistent4D: Consistent 360° Dynamic Object Generation from Monocular Video (ICLR 2024 · similarity 0.90)
- SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistency (ICLR 2025 · similarity 0.90)
- CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models (CVPR 2025 · 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.
