# UrbanGIRAFFE: Representing Urban Scenes as Compositional Generative Neural Feature Fields

arXiv: https://arxiv.org/abs/2303.14167 · HTML: https://mlsanity.com/paper/2303.14167/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 64 of its 74 references that are in the map.
- First posted on arXiv 24 Mar 2023.

## Builds on (most cited first, 30 of 64)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://mlsanity.com/paper/2106.10689/) (2021)
- [pixelNeRF: Neural Radiance Fields from One or Few Images](https://mlsanity.com/paper/2012.02190/) (2020)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [Efficient Geometry-aware 3D Generative Adversarial Networks](https://mlsanity.com/paper/2112.07945/) (2021)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [Neural Sparse Voxel Fields](https://mlsanity.com/paper/2007.11571/) (2020)
- [GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields](https://mlsanity.com/paper/2011.12100/) (2020)
- [MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo](https://mlsanity.com/paper/2103.15595/) (2021)
- [Block-NeRF: Scalable Large Scene Neural View Synthesis](https://mlsanity.com/paper/2202.05263/) (2022)
- [pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis](https://mlsanity.com/paper/2012.00926/) (2020)
- [IBRNet: Learning Multi-View Image-Based Rendering](https://mlsanity.com/paper/2102.13090/) (2021)
- [GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis](https://mlsanity.com/paper/2007.02442/) (2020)
- [Which Training Methods for GANs do actually Converge?](https://mlsanity.com/paper/1801.04406/) (2018)
- [KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs](https://mlsanity.com/paper/2103.13744/) (2021)
- [KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D](https://mlsanity.com/paper/2109.13410/) (2021)
- [StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets](https://mlsanity.com/paper/2202.00273/) (2022)
- [StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesis](https://mlsanity.com/paper/2110.08985/) (2021)
- [In-Place Scene Labelling and Understanding with Implicit Scene Representation](https://mlsanity.com/paper/2103.15875/) (2021)
- [MonoScene: Monocular 3D Semantic Scene Completion](https://mlsanity.com/paper/2112.00726/) (2021)

## Built on by (most cited first, 26 of 26)

- [End-to-end Autonomous Driving: Challenges and Frontiers](https://mlsanity.com/paper/2306.16927/) (2023)
- [Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting](https://mlsanity.com/paper/2401.01339/) (2024)
- [Deepfake Generation and Detection: A Benchmark and Survey](https://mlsanity.com/paper/2403.17881/) (2024)
- [Generative Gaussian Splatting for Unbounded 3D City Generation](https://mlsanity.com/paper/2406.06526/) (2024)
- [Streetscapes: Large-scale Consistent Street View Generation Using Autoregressive Video Diffusion](https://mlsanity.com/paper/2407.13759/) (2024)
- [Prometheus: 3D-Aware Latent Diffusion Models for Feed-Forward Text-to-3D Scene Generation](https://mlsanity.com/paper/2412.21117/) (2024)
- [S-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generation](https://mlsanity.com/paper/2402.02112/) (2024)
- [3D Scene Generation: A Survey](https://mlsanity.com/paper/2505.05474/) (2025)
- [AlignMiF: Geometry-Aligned Multimodal Implicit Field for LiDAR-Camera Joint Synthesis](https://mlsanity.com/paper/2402.17483/) (2024)
- [Urban Architect: Steerable 3D Urban Scene Generation with Layout Prior](https://mlsanity.com/paper/2404.06780/) (2024)
- [Sat2City: 3D City Generation from A Single Satellite Image with Cascaded Latent Diffusion](https://mlsanity.com/paper/2507.04403/) (2025)
- [RoDUS: Robust Decomposition of Static and Dynamic Elements in Urban Scenes](https://mlsanity.com/paper/2403.09419/) (2024)
- [Urban Scene Diffusion through Semantic Occupancy Map](https://mlsanity.com/paper/2403.11697/) (2024)
- [SyntheOcc: Synthesize Geometric-Controlled Street View Images through 3D Semantic MPIs](https://mlsanity.com/paper/2410.00337/) (2024)
- [Semantically-aware Neural Radiance Fields for Visual Scene Understanding: A Comprehensive Review](https://mlsanity.com/paper/2402.11141/) (2024)
- [Seeing through Satellite Images at Street Views](https://mlsanity.com/paper/2505.17001/) (2025)
- [Efficient Depth-Guided Urban View Synthesis](https://mlsanity.com/paper/2407.12395/) (2024)
- [LSD-3D: Large-Scale 3D Driving Scene Generation with Geometry Grounding](https://mlsanity.com/paper/2508.19204/) (2025)
- [Car-Studio: Learning Car Radiance Fields from Single-View and Endless In-the-wild Images](https://mlsanity.com/paper/2307.14009/) (2023)
- [Sat2City v2: Native 3D City Asset Generation from a Single Satellite Image](https://mlsanity.com/paper/2606.24138/) (2026)
- [SuperNeRF-GAN: A Universal 3D-Consistent Super-Resolution Framework for Efficient and Enhanced 3D-Aware Image Synthesis](https://mlsanity.com/paper/2501.06770/) (2025)
- [ABot-Earth 0.5: Generative 3D Earth Model](https://mlsanity.com/paper/2606.09967/) (2026)
- [PrITTI: Primitive-based Generation of Controllable and Editable 3D Semantic Urban Scenes](https://mlsanity.com/paper/2506.19117/) (2025)
- [HybridWorldSim: A Scalable and Controllable High-fidelity Simulator for Autonomous Driving](https://mlsanity.com/paper/2511.22187/) (2025)
- [ScenDi: 3D-to-2D Scene Diffusion Cascades for Urban Generation](https://mlsanity.com/paper/2601.15221/) (2026)
- [To See a World in a Living Context: Unified Indoor-Outdoor Urban World Generation](https://mlsanity.com/paper/2608.05879/) (2026)

## Abstract (arXiv)

Generating photorealistic images with controllable camera pose and scene contents is essential for many applications including AR/VR and simulation. Despite the fact that rapid progress has been made in 3D-aware generative models, most existing methods focus on object-centric images and are not applicable to generating urban scenes for free camera viewpoint control and scene editing. To address this challenging task, we propose UrbanGIRAFFE, which uses a coarse 3D panoptic prior, including the layout distribution of uncountable stuff and countable objects, to guide a 3D-aware generative model. Our model is compositional and controllable as it breaks down the scene into stuff, objects, and sky. Using stuff prior in the form of semantic voxel grids, we build a conditioned stuff generator that effectively incorporates the coarse semantic and geometry information. The object layout prior further allows us to learn an object generator from cluttered scenes. With proper loss functions, our approach facilitates photorealistic 3D-aware image synthesis with diverse controllability, including large camera movement, stuff editing, and object manipulation. We validate the effectiveness of our model on both synthetic and real-world datasets, including the challenging KITTI-360 dataset.