# VEGS: View Extrapolation of Urban Scenes in 3D Gaussian Splatting using Learned Priors

arXiv: https://arxiv.org/abs/2407.02945 · HTML: https://mlsanity.com/paper/2407.02945/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 46 references that are in the map.
- First posted on arXiv 3 Jul 2024.

## Builds on (most cited first, 30 of 39)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [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)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021)
- [pixelNeRF: Neural Radiance Fields from One or Few Images](https://mlsanity.com/paper/2012.02190/) (2020)
- [D-NeRF: Neural Radiance Fields for Dynamic Scenes](https://mlsanity.com/paper/2011.13961/) (2020)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [Nerfies: Deformable Neural Radiance Fields](https://mlsanity.com/paper/2011.12948/) (2020)
- [Depth-supervised NeRF: Fewer Views and Faster Training for Free](https://mlsanity.com/paper/2107.02791/) (2021)
- [Block-NeRF: Scalable Large Scene Neural View Synthesis](https://mlsanity.com/paper/2202.05263/) (2022)
- [Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields](https://mlsanity.com/paper/2304.06706/) (2023)
- [RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs](https://mlsanity.com/paper/2112.00724/) (2021)
- [Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding](https://mlsanity.com/paper/2011.02523/) (2020)
- [Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation](https://mlsanity.com/paper/2212.00774/) (2022)
- [KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D](https://mlsanity.com/paper/2109.13410/) (2021)
- [FastNeRF: High-Fidelity Neural Rendering at 200FPS](https://mlsanity.com/paper/2103.10380/) (2021)
- [Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular Video](https://mlsanity.com/paper/2012.12247/) (2020)
- [MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction](https://mlsanity.com/paper/2206.00665/) (2022)
- [Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesis](https://mlsanity.com/paper/2104.00677/) (2021)
- [Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughs](https://mlsanity.com/paper/2112.10703/) (2021)
- [Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans](https://mlsanity.com/paper/2110.04994/) (2021)
- [Neural RGB-D Surface Reconstruction](https://mlsanity.com/paper/2104.04532/) (2021)
- [FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularization](https://mlsanity.com/paper/2303.07418/) (2023)
- [Neural Scene Graphs for Dynamic Scenes](https://mlsanity.com/paper/2011.10379/) (2020)

## Built on by (most cited first, 25 of 25)

- [DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation](https://mlsanity.com/paper/2410.13571/) (2024)
- [ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration](https://mlsanity.com/paper/2411.19548/) (2024)
- [StreetCrafter: Street View Synthesis with Controllable Video Diffusion Models](https://mlsanity.com/paper/2412.13188/) (2024)
- [ReconDreamer++: Harmonizing Generative and Reconstructive Models for Driving Scene Representation](https://mlsanity.com/paper/2503.18438/) (2025)
- [MTGS: Multi-Traversal Gaussian Splatting](https://mlsanity.com/paper/2503.12552/) (2025)
- [Extrapolated Urban View Synthesis Benchmark](https://mlsanity.com/paper/2412.05256/) (2024)
- [Driving View Synthesis on Free-form Trajectories with Generative Prior](https://mlsanity.com/paper/2412.01717/) (2024)
- [Learning-based 3D Reconstruction in Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2503.14537/) (2025)
- [LSD-3D: Large-Scale 3D Driving Scene Generation with Geometry Grounding](https://mlsanity.com/paper/2508.19204/) (2025)
- [Pointmap-Conditioned Diffusion for Consistent Novel View Synthesis](https://mlsanity.com/paper/2501.02913/) (2025)
- [GenAssets: Generating in-the-wild 3D Assets in Latent Space](https://mlsanity.com/paper/2604.23010/) (2026)
- [VDEGaussian: Video Diffusion Enhanced 4D Gaussian Splatting for Dynamic Urban Scenes Modeling](https://mlsanity.com/paper/2508.02129/) (2025)
- [JRN-Geo: A Joint Perception Network based on RGB and Normal images for Cross-view Geo-localization](https://mlsanity.com/paper/2509.05696/) (2025)
- [sshELF: Single-Shot Hierarchical Extrapolation of Latent Features for 3D Reconstruction from Sparse-Views](https://mlsanity.com/paper/2502.04318/) (2025)
- [FPGS: Feed-Forward Semantic-aware Photorealistic Style Transfer of Large-Scale Gaussian Splatting](https://mlsanity.com/paper/2503.09635/) (2025)
- [Hybrid Gaussian Splatting for Novel Urban View Synthesis](https://mlsanity.com/paper/2510.12308/) (2025)
- [DIAL-GS: Dynamic Instance Aware Reconstruction for Label-free Street Scenes with 4D Gaussian Splatting](https://mlsanity.com/paper/2511.06632/) (2025)
- [FaithFusion: Harmonizing Reconstruction and Generation via Pixel-wise Information Gain](https://mlsanity.com/paper/2511.21113/) (2025)
- [SurfFill: Completion of LiDAR Point Clouds via Gaussian Surfel Splatting](https://mlsanity.com/paper/2512.03010/) (2025)
- [Diffusion-guided Generalizable Enhancer for Urban Scene Reconstruction](https://mlsanity.com/paper/2605.22420/) (2026)
- [3D Gaussian Splatting against Moving Objects for High-Fidelity Street Scene Reconstruction](https://mlsanity.com/paper/2503.12001/) (2025)
- [UrbanCraft: Urban View Extrapolation via Hierarchical Sem-Geometric Priors](https://mlsanity.com/paper/2505.23434/) (2025)
- [ArbiViewGen: Controllable Arbitrary Viewpoint Camera Data Generation for Autonomous Driving via Stable Diffusion Models](https://mlsanity.com/paper/2508.05236/) (2025)
- [Enhancing Novel View Synthesis via Geometry Grounded Set Diffusion](https://mlsanity.com/paper/2601.07540/) (2026)
- [G2ARD-GS: Geometry-Guided Anchor-Regularized Gaussian Splatting Distillation](https://mlsanity.com/paper/2608.05704/) (2026)

## Abstract (arXiv)

Neural rendering-based urban scene reconstruction methods commonly rely on images collected from driving vehicles with cameras facing and moving forward. Although these methods can successfully synthesize from views similar to training camera trajectory, directing the novel view outside the training camera distribution does not guarantee on-par performance. In this paper, we tackle the Extrapolated View Synthesis (EVS) problem by evaluating the reconstructions on views such as looking left, right or downwards with respect to training camera distributions. To improve rendering quality for EVS, we initialize our model by constructing dense LiDAR map, and propose to leverage prior scene knowledge such as surface normal estimator and large-scale diffusion model. Qualitative and quantitative comparisons demonstrate the effectiveness of our methods on EVS. To the best of our knowledge, we are the first to address the EVS problem in urban scene reconstruction. Link to our project page: https://vegs3d.github.io/.