# Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation

arXiv: https://arxiv.org/abs/2509.19296 · HTML: https://mlsanity.com/paper/2509.19296/

## Key facts

- Cited by 41 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 198 of its 213 references that are in the map.
- First posted on arXiv 23 Sep 2025.

## 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, 30 of 198)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [Zero-1-to-3: Zero-shot One Image to 3D Object](https://mlsanity.com/paper/2303.11328/) (2023)
- [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://mlsanity.com/paper/2405.21060/) (2024)
- [Magic3D: High-Resolution Text-to-3D Content Creation](https://mlsanity.com/paper/2211.10440/) (2022)
- [ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation](https://mlsanity.com/paper/2305.16213/) (2023)
- [Efficient Geometry-aware 3D Generative Adversarial Networks](https://mlsanity.com/paper/2112.07945/) (2021)
- [MVDream: Multi-view Diffusion for 3D Generation](https://mlsanity.com/paper/2308.16512/) (2023)
- [LRM: Large Reconstruction Model for Single Image to 3D](https://mlsanity.com/paper/2311.04400/) (2023)
- [LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation](https://mlsanity.com/paper/2402.05054/) (2024)
- [Wonder3D: Single Image to 3D using Cross-Domain Diffusion](https://mlsanity.com/paper/2310.15008/) (2023)
- [Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation](https://mlsanity.com/paper/2303.13873/) (2023)
- [pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction](https://mlsanity.com/paper/2312.12337/) (2023)
- [Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion](https://mlsanity.com/paper/2407.01392/) (2024)
- [SyncDreamer: Generating Multiview-consistent Images from a Single-view Image](https://mlsanity.com/paper/2309.03453/) (2023)
- [Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation](https://mlsanity.com/paper/2212.00774/) (2022)
- [MotionCtrl: A Unified and Flexible Motion Controller for Video Generation](https://mlsanity.com/paper/2312.03641/) (2023)
- [DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision](https://mlsanity.com/paper/2312.16256/) (2023)
- [VideoCrafter1: Open Diffusion Models for High-Quality Video Generation](https://mlsanity.com/paper/2310.19512/) (2023)
- [Zero-Shot Text-Guided Object Generation with Dream Fields](https://mlsanity.com/paper/2112.01455/) (2021)

## Built on by (most cited first, 30 of 41)

- [Cosmos 3: Omnimodal World Models for Physical AI](https://mlsanity.com/paper/2606.02800/) (2026)
- [Lyra 2.0: Explorable Generative 3D Worlds](https://mlsanity.com/paper/2604.13036/) (2026)
- [HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds](https://mlsanity.com/paper/2604.14268/) (2026)
- [Generative Video Motion Editing with 3D Point Tracks](https://mlsanity.com/paper/2512.02015/) (2025)
- [WorldGen: From Text to Traversable and Interactive 3D Worlds](https://mlsanity.com/paper/2511.16825/) (2025)
- [WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memories](https://mlsanity.com/paper/2603.02049/) (2026)
- [BulletTime: Decoupled Control of Time and Camera Pose for Video Generation](https://mlsanity.com/paper/2512.05076/) (2025)
- [Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generator](https://mlsanity.com/paper/2510.13454/) (2025)
- [LagerNVS: Latent Geometry for Fully Neural Real-time Novel View Synthesis](https://mlsanity.com/paper/2603.20176/) (2026)
- [World Reconstruction From Inconsistent Views](https://mlsanity.com/paper/2603.16736/) (2026)
- [Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models](https://mlsanity.com/paper/2511.00503/) (2025)
- [Efficient Video Diffusion Models: Advancements and Challenges](https://mlsanity.com/paper/2604.15911/) (2026)
- [Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective](https://mlsanity.com/paper/2604.14025/) (2026)
- [Advances in 4D Representation: Geometry, Motion, and Interaction](https://mlsanity.com/paper/2510.19255/) (2025)
- [Research on World Models Is Not Merely Injecting World Knowledge into Specific Tasks](https://mlsanity.com/paper/2602.01630/) (2026)
- [Rein3D: Reinforced 3D Indoor Scene Generation with Panoramic Video Diffusion Models](https://mlsanity.com/paper/2604.10578/) (2026)
- [ProxyPose: 6-DoF Pose Tracking via Video-to-Video Translation](https://mlsanity.com/paper/2607.06555/) (2026)
- [StereoSpace: Depth-Free Synthesis of Stereo Geometry via End-to-End Diffusion in a Canonical Space](https://mlsanity.com/paper/2512.10959/) (2025)
- [Guardians of the Hair: Rescuing Soft Boundaries in Depth, Stereo, and Novel Views](https://mlsanity.com/paper/2601.03362/) (2026)
- [Free-Range Gaussians: Non-Grid-Aligned Generative 3D Gaussian Reconstruction](https://mlsanity.com/paper/2604.04874/) (2026)
- [Track the Noise, Move the World:3D-Grounded Motion-Consistent Noise for Controllable Video Generation](https://mlsanity.com/paper/2607.02798/) (2026)
- [Sparse auto-regressive modeling for scene generation from multi-view images](https://mlsanity.com/paper/2609.03931/) (2026)
- [AdvSplat: Adversarial Attacks on Feed-Forward Gaussian Splatting Models](https://mlsanity.com/paper/2603.23686/) (2026)
- [ST-Gen4D: Embedding 4D Spatiotemporal Cognition into World Model for 4D Generation](https://mlsanity.com/paper/2605.07390/) (2026)
- [UniFixer: A Universal Reference-Guided Fixer for Diffusion-Based View Synthesis](https://mlsanity.com/paper/2605.12169/) (2026)
- [Resolving Representation Ambiguity in Feedforward Novel View Synthesis Transformer via Semantic-Spatial Decoupling](https://mlsanity.com/paper/2605.18599/) (2026)
- [MMDiff: Extending Diffusion Transformers for Multi-Modal Generation](https://mlsanity.com/paper/2606.16673/) (2026)
- [FLAT: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene Generation](https://mlsanity.com/paper/2606.24876/) (2026)
- [FlexComposer: Unified Video Compositing from Images to Dynamic Footage with Flexible Trajectory Control](https://mlsanity.com/paper/2607.29627/) (2026)
- [GenRec: Knowing Where to Reconstruct and Where to Generate](https://mlsanity.com/paper/2608.17832/) (2026)

## Abstract (arXiv)

The ability to generate virtual environments is crucial for applications ranging from gaming to physical AI domains such as robotics, autonomous driving, and industrial AI. Current learning-based 3D reconstruction methods rely on the availability of captured real-world multi-view data, which is not always readily available. Recent advancements in video diffusion models have shown remarkable imagination capabilities, yet their 2D nature limits the applications to simulation where a robot needs to navigate and interact with the environment. In this paper, we propose a self-distillation framework that aims to distill the implicit 3D knowledge in the video diffusion models into an explicit 3D Gaussian Splatting (3DGS) representation, eliminating the need for multi-view training data. Specifically, we augment the typical RGB decoder with a 3DGS decoder, which is supervised by the output of the RGB decoder. In this approach, the 3DGS decoder can be purely trained with synthetic data generated by video diffusion models. At inference time, our model can synthesize 3D scenes from either a text prompt or a single image for real-time rendering. Our framework further extends to dynamic 3D scene generation from a monocular input video. Experimental results show that our framework achieves state-of-the-art performance in static and dynamic 3D scene generation.