LSD-3D: Large-Scale 3D Driving Scene Generation with Geometry Grounding
cs.CV, cs.AI, cs.GR
Submitted: 2025-08-26
Updated: 2026-11-05
Code: https://github.com/genmoai/models
Project page: https://light.princeton.edu/LSD-3D
Terminology
Sources
- 4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling
- Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
- Unity Perception: Generate Synthetic Data for Computer Vision
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- GeoDrive: 3D Geometry-Informed Driving World Model with Precise Action Control
- Objaverse-XL: A Universe of 10M+ 3D Objects
- Score-Based Generative Modeling with Critically-Damped Langevin Diffusion
- FlowR: Flowing from Sparse to Dense 3D Reconstructions
- MagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street Scenes
- MagicDrive-V2: High-Resolution Long Video Generation for Autonomous Driving with Adaptive Control
- MagicDrive: Street View Generation with Diverse 3D Geometry Control
- Imagen Video: High Definition Video Generation with Diffusion Models
- CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers
- Shap-E: Generating Conditional 3D Implicit Functions
- 3D Gaussian Splatting as Markov Chain Monte Carlo
- Auto-Encoding Variational Bayes
- DreamScene: 3D Gaussian-based Text-to-3D Scene Generation via Formation Pattern Sampling
- TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models
- NeuroNCAP: Photorealistic Closed-loop Safety Testing for Autonomous Driving
- InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs