# GeoLRM: Geometry-Aware Large Reconstruction Model for High-Quality 3D Gaussian Generation

arXiv: https://arxiv.org/abs/2406.15333 · HTML: https://mlsanity.com/paper/2406.15333/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- Builds on 74 of its 86 references that are in the map.
- First posted on arXiv 21 Jun 2024.

## Builds on (most cited first, 30 of 74)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (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)
- [Plenoxels: Radiance Fields without Neural Networks](https://mlsanity.com/paper/2112.05131/) (2021)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [Zero-1-to-3: Zero-shot One Image to 3D Object](https://mlsanity.com/paper/2303.11328/) (2023)
- [Root Mean Square Layer Normalization](https://mlsanity.com/paper/1910.07467/) (2019)
- [Magic3D: High-Resolution Text-to-3D Content Creation](https://mlsanity.com/paper/2211.10440/) (2022)
- [TensoRF: Tensorial Radiance Fields](https://mlsanity.com/paper/2203.09517/) (2022)
- [ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation](https://mlsanity.com/paper/2305.16213/) (2023)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [Efficient Geometry-aware 3D Generative Adversarial Networks](https://mlsanity.com/paper/2112.07945/) (2021)
- [Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction](https://mlsanity.com/paper/2111.11215/) (2021)
- [Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning](https://mlsanity.com/paper/1702.03118/) (2017)
- [MVDream: Multi-view Diffusion for 3D Generation](https://mlsanity.com/paper/2308.16512/) (2023)
- [NeRF++: Analyzing and Improving Neural Radiance Fields](https://mlsanity.com/paper/2010.07492/) (2020)
- [LRM: Large Reconstruction Model for Single Image to 3D](https://mlsanity.com/paper/2311.04400/) (2023)
- [DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation](https://mlsanity.com/paper/2309.16653/) (2023)
- [GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields](https://mlsanity.com/paper/2011.12100/) (2020)
- [Objaverse-XL: A Universe of 10M+ 3D Objects](https://mlsanity.com/paper/2307.05663/) (2023)
- [LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation](https://mlsanity.com/paper/2402.05054/) (2024)

## Built on by (most cited first, 30 of 36)

- [3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion](https://mlsanity.com/paper/2409.12957/) (2024)
- [EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generation](https://mlsanity.com/paper/2409.18114/) (2024)
- [DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning](https://mlsanity.com/paper/2503.15265/) (2025)
- [GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial Understanding](https://mlsanity.com/paper/2412.13193/) (2024)
- [FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstruction](https://mlsanity.com/paper/2412.09573/) (2024)
- [ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understanding](https://mlsanity.com/paper/2506.01853/) (2025)
- [Omni-Scene: Omni-Gaussian Representation for Ego-Centric Sparse-View Scene Reconstruction](https://mlsanity.com/paper/2412.06273/) (2024)
- [Momentum-GS: Momentum Gaussian Self-Distillation for High-Quality Large Scene Reconstruction](https://mlsanity.com/paper/2412.04887/) (2024)
- [Generative Densification: Learning to Densify Gaussians for High-Fidelity Generalizable 3D Reconstruction](https://mlsanity.com/paper/2412.06234/) (2024)
- [Nautilus: Locality-aware Autoencoder for Scalable Mesh Generation](https://mlsanity.com/paper/2501.14317/) (2025)
- [DROID-Splat: Combining end-to-end SLAM with 3D Gaussian Splatting](https://mlsanity.com/paper/2411.17660/) (2024)
- [Flex3D: Feed-Forward 3D Generation with Flexible Reconstruction Model and Input View Curation](https://mlsanity.com/paper/2410.00890/) (2024)
- [MeshRipple: Structured Autoregressive Generation of Artist-Meshes](https://mlsanity.com/paper/2512.07514/) (2025)
- [Learning-based 3D Reconstruction in Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2503.14537/) (2025)
- [NovelGS: Consistent Novel-view Denoising via Large Gaussian Reconstruction Model](https://mlsanity.com/paper/2411.16779/) (2024)
- [Sharp-It: A Multi-view to Multi-view Diffusion Model for 3D Synthesis and Manipulation](https://mlsanity.com/paper/2412.02631/) (2024)
- [StdGEN: Semantic-Decomposed 3D Character Generation from Single Images](https://mlsanity.com/paper/2411.05738/) (2024)
- [Holistic Large-Scale Scene Reconstruction via Mixed Gaussian Splatting](https://mlsanity.com/paper/2505.23280/) (2025)
- [H3R: Hybrid Multi-view Correspondence for Generalizable 3D Reconstruction](https://mlsanity.com/paper/2508.03118/) (2025)
- [UniGS: Modeling Unitary 3D Gaussians for Novel View Synthesis from Sparse-view Images](https://mlsanity.com/paper/2410.13195/) (2024)
- [Collaborative Multi-Modal Coding for High-Quality 3D Generation](https://mlsanity.com/paper/2508.15228/) (2025)
- [GaussianLens: Localized High-Resolution Reconstruction via On-Demand Gaussian Densification](https://mlsanity.com/paper/2509.25603/) (2025)
- [AlignCVC: Aligning Cross-View Consistency for Single-Image-to-3D Generation](https://mlsanity.com/paper/2506.23150/) (2025)
- [Complete Gaussian Splats from a Single Image with Denoising Diffusion Models](https://mlsanity.com/paper/2508.21542/) (2025)
- [Large Material Gaussian Model for Relightable 3D Generation](https://mlsanity.com/paper/2509.22112/) (2025)
- [GP-4DGS: Probabilistic 4D Gaussian Splatting from Monocular Video via Variational Gaussian Processes](https://mlsanity.com/paper/2604.02915/) (2026)
- [PBR3DGen: A VLM-guided Mesh Generation with High-quality PBR Texture](https://mlsanity.com/paper/2503.11368/) (2025)
- [Coca-Splat: Collaborative Optimization for Camera Parameters and 3D Gaussians](https://mlsanity.com/paper/2504.00639/) (2025)
- [StdGEN++: A Comprehensive System for Semantic-Decomposed 3D Character Generation](https://mlsanity.com/paper/2601.07660/) (2026)
- [OCH3R: Object-Centric Holistic 3D Reconstruction](https://mlsanity.com/paper/2605.13018/) (2026)

## Abstract (arXiv)

In this work, we introduce the Geometry-Aware Large Reconstruction Model (GeoLRM), an approach which can predict high-quality assets with 512k Gaussians and 21 input images in only 11 GB GPU memory. Previous works neglect the inherent sparsity of 3D structure and do not utilize explicit geometric relationships between 3D and 2D images. This limits these methods to a low-resolution representation and makes it difficult to scale up to the dense views for better quality. GeoLRM tackles these issues by incorporating a novel 3D-aware transformer structure that directly processes 3D points and uses deformable cross-attention mechanisms to effectively integrate image features into 3D representations. We implement this solution through a two-stage pipeline: initially, a lightweight proposal network generates a sparse set of 3D anchor points from the posed image inputs; subsequently, a specialized reconstruction transformer refines the geometry and retrieves textural details. Extensive experimental results demonstrate that GeoLRM significantly outperforms existing models, especially for dense view inputs. We also demonstrate the practical applicability of our model with 3D generation tasks, showcasing its versatility and potential for broader adoption in real-world applications. The project page: https://linshan-bin.github.io/GeoLRM/.