# Vid3D: Synthesis of Dynamic 3D Scenes using 2D Video Diffusion

arXiv: https://arxiv.org/abs/2406.11196 · HTML: https://mlsanity.com/paper/2406.11196/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models.
- Builds on 15 of its 20 references that are in the map.
- First posted on arXiv 17 Jun 2024.

## Placed in

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

## Builds on (most cited first, 15 of 15)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [Zero-1-to-3: Zero-shot One Image to 3D Object](https://mlsanity.com/paper/2303.11328/) (2023)
- [SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusion](https://mlsanity.com/paper/2403.12008/) (2024)
- [DreamGaussian4D: Generative 4D Gaussian Splatting](https://mlsanity.com/paper/2312.17142/) (2023)
- [4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling](https://mlsanity.com/paper/2311.17984/) (2023)
- [Re-imagine the Negative Prompt Algorithm: Transform 2D Diffusion into 3D, alleviate Janus problem and Beyond](https://mlsanity.com/paper/2304.04968/) (2023)
- [Animate124: Animating One Image to 4D Dynamic Scene](https://mlsanity.com/paper/2311.14603/) (2023)
- [V3D: Video Diffusion Models are Effective 3D Generators](https://mlsanity.com/paper/2403.06738/) (2024)
- [VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models](https://mlsanity.com/paper/2403.12034/) (2024)
- [Auto-Tuned Sim-to-Real Transfer](https://mlsanity.com/paper/2104.07662/) (2021)
- [HUMAN4D: A Human-Centric Multimodal Dataset for Motions and Immersive Media](https://mlsanity.com/paper/2110.07235/) (2021)
- [HUMBI: A Large Multiview Dataset of Human Body Expressions and Benchmark Challenge](https://mlsanity.com/paper/2110.00119/) (2021)

## Built on by (most cited first, 1 of 1)

- [Generating 360deg Video is What You Need For a 3D Scene](https://mlsanity.com/paper/2504.02045/) (2025)

## Abstract (arXiv)

A recent frontier in computer vision has been the task of 3D video generation, which consists of generating a time-varying 3D representation of a scene. To generate dynamic 3D scenes, current methods explicitly model 3D temporal dynamics by jointly optimizing for consistency across both time and views of the scene. In this paper, we instead investigate whether it is necessary to explicitly enforce multiview consistency over time, as current approaches do, or if it is sufficient for a model to generate 3D representations of each timestep independently. We hence propose a model, Vid3D, that leverages 2D video diffusion to generate 3D videos by first generating a 2D "seed" of the video's temporal dynamics and then independently generating a 3D representation for each timestep in the seed video. We evaluate Vid3D against two state-of-the-art 3D video generation methods and find that Vid3D is achieves comparable results despite not explicitly modeling 3D temporal dynamics. We further ablate how the quality of Vid3D depends on the number of views generated per frame. While we observe some degradation with fewer views, performance degradation remains minor. Our results thus suggest that 3D temporal knowledge may not be necessary to generate high-quality dynamic 3D scenes, potentially enabling simpler generative algorithms for this task.