# SS4D: Native 4D Generative Model via Structured Spacetime Latents

arXiv: https://arxiv.org/abs/2512.14284 · HTML: https://mlsanity.com/paper/2512.14284/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 49 references that are in the map.
- First posted on arXiv 16 Dec 2025.

## Builds on (most cited first, 30 of 33)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [Magic3D: High-Resolution Text-to-3D Content Creation](https://mlsanity.com/paper/2211.10440/) (2022)
- [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018)
- [LRM: Large Reconstruction Model for Single Image to 3D](https://mlsanity.com/paper/2311.04400/) (2023)
- [Objaverse-XL: A Universe of 10M+ 3D Objects](https://mlsanity.com/paper/2307.05663/) (2023)
- [Structured 3D Latents for Scalable and Versatile 3D Generation](https://mlsanity.com/paper/2412.01506/) (2024)
- [LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation](https://mlsanity.com/paper/2402.05054/) (2024)
- [CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets](https://mlsanity.com/paper/2406.13897/) (2024)
- [Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation](https://mlsanity.com/paper/2501.12202/) (2025)
- [LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching](https://mlsanity.com/paper/2311.11284/) (2023)
- [Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation](https://mlsanity.com/paper/2306.17115/) (2023)
- [RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D](https://mlsanity.com/paper/2311.16918/) (2023)
- [L4GM: Large 4D Gaussian Reconstruction Model](https://mlsanity.com/paper/2406.10324/) (2024)
- [SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistency](https://mlsanity.com/paper/2407.17470/) (2024)
- [Consistent4D: Consistent 360deg Dynamic Object Generation from Monocular Video](https://mlsanity.com/paper/2311.02848/) (2023)
- [4Diffusion: Multi-view Video Diffusion Model for 4D Generation](https://mlsanity.com/paper/2405.20674/) (2024)
- [STAG4D: Spatial-Temporal Anchored Generative 4D Gaussians](https://mlsanity.com/paper/2403.14939/) (2024)
- [A Unified Approach for Text- and Image-guided 4D Scene Generation](https://mlsanity.com/paper/2311.16854/) (2023)
- [4Real: Towards Photorealistic 4D Scene Generation via Video Diffusion Models](https://mlsanity.com/paper/2406.07472/) (2024)
- [SV4D 2.0: Enhancing Spatio-Temporal Consistency in Multi-View Video Diffusion for High-Quality 4D Generation](https://mlsanity.com/paper/2503.16396/) (2025)
- [EG4D: Explicit Generation of 4D Object without Score Distillation](https://mlsanity.com/paper/2405.18132/) (2024)
- [Puppeteer: Rig and Animate Your 3D Models](https://mlsanity.com/paper/2508.10898/) (2025)
- [V2M4: 4D Mesh Animation Reconstruction from a Single Monocular Video](https://mlsanity.com/paper/2503.09631/) (2025)

## Built on by (most cited first, 8 of 8)

- [Action Images: End-to-End Policy Learning via Multiview Video Generation](https://mlsanity.com/paper/2604.06168/) (2026)
- [FreeOrbit4D: Training-Free Arbitrary Camera Redirection for Monocular Videos via Foreground-Complete 4D Reconstruction](https://mlsanity.com/paper/2601.18993/) (2026)
- [World Tracing: Generative Pixel-Aligned Geometry Beyond the Visible](https://mlsanity.com/paper/2606.13652/) (2026)
- [AniGen: Unified S3 Fields for Animatable 3D Asset Generation](https://mlsanity.com/paper/2604.08746/) (2026)
- [ViPS: Video-informed Pose Spaces for Auto-Rigged Meshes](https://mlsanity.com/paper/2604.17623/) (2026)
- [Helix4D: Complex 4D Mesh Generation](https://mlsanity.com/paper/2605.26109/) (2026)
- [Feed-forward Motion In-betweening for Any 4D](https://mlsanity.com/paper/2606.22131/) (2026)
- [Cepheid: Decoupling Scale from Structure for Cross-Family Motion Completion](https://mlsanity.com/paper/2610.18871/) (2026)

## Abstract (arXiv)

We present SS4D, a native 4D generative model that synthesizes dynamic 3D objects directly from monocular video. Unlike prior approaches that construct 4D representations by optimizing over 3D or video generative models, we train a generator directly on 4D data, achieving high fidelity, temporal coherence, and structural consistency. At the core of our method is a compressed set of structured spacetime latents. Specifically, (1) To address the scarcity of 4D training data, we build on a pre-trained single-image-to-3D model, preserving strong spatial consistency. (2) Temporal consistency is enforced by introducing dedicated temporal layers that reason across frames. (3) To support efficient training and inference over long video sequences, we compress the latent sequence along the temporal axis using factorized 4D convolutions and temporal downsampling blocks. In addition, we employ a carefully designed training strategy to enhance robustness against occlusion