# MVTokenFlow: High-quality 4D Content Generation using Multiview Token Flow

arXiv: https://arxiv.org/abs/2502.11697 · HTML: https://mlsanity.com/paper/2502.11697/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models.
- First posted on arXiv 17 Feb 2025.

## Placed in

- Diffusion models / [3D, point cloud and scene generation](https://mlsanity.com/diffusion/3d-point-cloud-and-scene-generation/)

## Built on by (most cited first, 17 of 17)

- [Rethinking Query-based Transformer for Continual Image Segmentation](https://mlsanity.com/paper/2507.07831/) (2025)
- [Why LVLMs Are More Prone to Hallucinations in Longer Responses: The Role of Context](https://mlsanity.com/paper/2510.20229/) (2025)
- [AnimaMimic: Imitating 3D Animation from Video Priors](https://mlsanity.com/paper/2512.14133/) (2025)
- [Intervene-All-Paths: Unified Mitigation of LVLM Hallucinations across Alignment Formats](https://mlsanity.com/paper/2511.17254/) (2025)
- [4DSTR: Advancing Generative 4D Gaussians with Spatial-Temporal Rectification for High-Quality and Consistent 4D Generation](https://mlsanity.com/paper/2511.07241/) (2025)
- [Sim-DETR: Unlock DETR for Temporal Sentence Grounding](https://mlsanity.com/paper/2509.23867/) (2025)
- [MV-Performer: Taming Video Diffusion Model for Faithful and Synchronized Multi-view Performer Synthesis](https://mlsanity.com/paper/2510.07190/) (2025)
- [Advances in 4D Representation: Geometry, Motion, and Interaction](https://mlsanity.com/paper/2510.19255/) (2025)
- [BiMotion: B-spline Motion for Text-guided Dynamic 3D Character Generation](https://mlsanity.com/paper/2602.18873/) (2026)
- [FB-4D: Spatial-Temporal Coherent Dynamic 3D Content Generation with Feature Banks](https://mlsanity.com/paper/2503.20784/) (2025)
- [No More Sibling Rivalry: Debiasing Human-Object Interaction Detection](https://mlsanity.com/paper/2509.00760/) (2025)
- [RefAny3D: 3D Asset-Referenced Diffusion Models for Image Generation](https://mlsanity.com/paper/2601.22094/) (2026)
- [Advances in 4D Generation: A Survey](https://mlsanity.com/paper/2503.14501/) (2025)
- [Augmenting Moment Retrieval: Zero-Dependency Two-Stage Learning](https://mlsanity.com/paper/2510.19622/) (2025)
- [Follow Your Track: Precise Skeleton Animation Controlled by 3D Trajectories](https://mlsanity.com/paper/2606.25344/) (2026)
- [AniGS: Bridging Rendering and Diffusion Prior for 3D Scene Animation](https://mlsanity.com/paper/2607.18539/) (2026)
- [Controllable Dynamic 3D Shape Generation via 3D Trajectories and Text](https://mlsanity.com/paper/2606.05162/) (2026)

## Abstract (arXiv)

In this paper, we present MVTokenFlow for high-quality 4D content creation from monocular videos. Recent advancements in generative models such as video diffusion models and multiview diffusion models enable us to create videos or 3D models. However, extending these generative models for dynamic 4D content creation is still a challenging task that requires the generated content to be consistent spatially and temporally. To address this challenge, MVTokenFlow utilizes the multiview diffusion model to generate multiview images on different timesteps, which attains spatial consistency across different viewpoints and allows us to reconstruct a reasonable coarse 4D field. Then, MVTokenFlow further regenerates all the multiview images using the rendered 2D flows as guidance. The 2D flows effectively associate pixels from different timesteps and improve the temporal consistency by reusing tokens in the regeneration process. Finally, the regenerated images are spatiotemporally consistent and utilized to refine the coarse 4D field to get a high-quality 4D field. Experiments demonstrate the effectiveness of our design and show significantly improved quality than baseline methods.