# GINA-3D: Learning to Generate Implicit Neural Assets in the Wild

arXiv: https://arxiv.org/abs/2304.02163 · HTML: https://mlsanity.com/paper/2304.02163/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 128 of its 161 references that are in the map.
- First posted on arXiv 4 Apr 2023.

## Builds on (most cited first, 30 of 128)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [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)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop](https://mlsanity.com/paper/1506.03365/) (2015)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [Efficient Geometry-aware 3D Generative Adversarial Networks](https://mlsanity.com/paper/2112.07945/) (2021)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [MaskGIT: Masked Generative Image Transformer](https://mlsanity.com/paper/2202.04200/) (2022)
- [StarGAN v2: Diverse Image Synthesis for Multiple Domains](https://mlsanity.com/paper/1912.01865/) (2019)

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

- [LRM: Large Reconstruction Model for Single Image to 3D](https://mlsanity.com/paper/2311.04400/) (2023)
- [GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation](https://mlsanity.com/paper/2403.14621/) (2024)
- [Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformers](https://mlsanity.com/paper/2312.09147/) (2023)
- [Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting](https://mlsanity.com/paper/2401.01339/) (2024)
- [DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Model](https://mlsanity.com/paper/2311.09217/) (2023)
- [Gen2Sim: Scaling up Robot Learning in Simulation with Generative Models](https://mlsanity.com/paper/2310.18308/) (2023)
- [LRM-Zero: Training Large Reconstruction Models with Synthesized Data](https://mlsanity.com/paper/2406.09371/) (2024)
- [TetSphere Splatting: Representing High-Quality Geometry with Lagrangian Volumetric Meshes](https://mlsanity.com/paper/2405.20283/) (2024)
- [NViST: In the Wild New View Synthesis from a Single Image with Transformers](https://mlsanity.com/paper/2312.08568/) (2023)
- [CAD: Photorealistic 3D Generation via Adversarial Distillation](https://mlsanity.com/paper/2312.06663/) (2023)
- [R3D2: Realistic 3D Asset Insertion via Diffusion for Autonomous Driving Simulation](https://mlsanity.com/paper/2506.07826/) (2025)
- [GenMM: Geometrically and Temporally Consistent Multimodal Data Generation for Video and LiDAR](https://mlsanity.com/paper/2406.10722/) (2024)
- [Multi-View Large Reconstruction Model via Geometry-Aware Positional Encoding and Attention](https://mlsanity.com/paper/2406.07648/) (2024)
- [Realistic and Controllable 3D Gaussian-Guided Object Editing for Driving Video Generation](https://mlsanity.com/paper/2508.20471/) (2025)
- [GenAssets: Generating in-the-wild 3D Assets in Latent Space](https://mlsanity.com/paper/2604.23010/) (2026)
- [Car-Studio: Learning Car Radiance Fields from Single-View and Endless In-the-wild Images](https://mlsanity.com/paper/2307.14009/) (2023)
- [G-NeRF: Geometry-enhanced Novel View Synthesis from Single-View Images](https://mlsanity.com/paper/2404.07474/) (2024)
- [Enhancing 2D Representation Learning with a 3D Prior](https://mlsanity.com/paper/2406.02535/) (2024)
- [Asset Harvester: Extracting 3D Assets from Autonomous Driving Logs for Simulation](https://mlsanity.com/paper/2604.18468/) (2026)
- [Inverse Neural Rendering for Explainable Multi-Object Tracking](https://mlsanity.com/paper/2404.12359/) (2024)
- [Unposed-to-3D: Learning Simulation-Ready Vehicles from Real-World Images](https://mlsanity.com/paper/2604.19257/) (2026)
- [3DCarGen: Scalable 3D Car Generation via 3D-consistent Multi-view Synthesis](https://mlsanity.com/paper/2606.24257/) (2026)
- [HumanCrafter: Synergizing Generalizable Human Reconstruction and Semantic 3D Segmentation](https://mlsanity.com/paper/2511.00468/) (2025)
- [MM-TRELLIS: Point-Cloud Guided Multi-Modal 3D Vehicle Generation in Autonomous Driving](https://mlsanity.com/paper/2606.24301/) (2026)
- [HiFiVe: High-Fidelity Vehicle Generation Leveraging Auto-Regressive 2D Generative Priors](https://mlsanity.com/paper/2606.25300/) (2026)

## Abstract (arXiv)

Modeling the 3D world from sensor data for simulation is a scalable way of developing testing and validation environments for robotic learning problems such as autonomous driving. However, manually creating or re-creating real-world-like environments is difficult, expensive, and not scalable. Recent generative model techniques have shown promising progress to address such challenges by learning 3D assets using only plentiful 2D images -- but still suffer limitations as they leverage either human-curated image datasets or renderings from manually-created synthetic 3D environments. In this paper, we introduce GINA-3D, a generative model that uses real-world driving data from camera and LiDAR sensors to create realistic 3D implicit neural assets of diverse vehicles and pedestrians. Compared to the existing image datasets, the real-world driving setting poses new challenges due to occlusions, lighting-variations and long-tail distributions. GINA-3D tackles these challenges by decoupling representation learning and generative modeling into two stages with a learned tri-plane latent structure, inspired by recent advances in generative modeling of images. To evaluate our approach, we construct a large-scale object-centric dataset containing over 1.2M images of vehicles and pedestrians from the Waymo Open Dataset, and a new set of 80K images of long-tail instances such as construction equipment, garbage trucks, and cable cars. We compare our model with existing approaches and demonstrate that it achieves state-of-the-art performance in quality and diversity for both generated images and geometries.