# LRM-Zero: Training Large Reconstruction Models with Synthesized Data

arXiv: https://arxiv.org/abs/2406.09371 · HTML: https://mlsanity.com/paper/2406.09371/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- Builds on 87 of its 109 references that are in the map.
- First posted on arXiv 13 Jun 2024.

## Builds on (most cited first, 30 of 87)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [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)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [Plenoxels: Radiance Fields without Neural Networks](https://mlsanity.com/paper/2112.05131/) (2021)
- [pixelNeRF: Neural Radiance Fields from One or Few Images](https://mlsanity.com/paper/2012.02190/) (2020)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [TensoRF: Tensorial Radiance Fields](https://mlsanity.com/paper/2203.09517/) (2022)
- [Efficient Geometry-aware 3D Generative Adversarial Networks](https://mlsanity.com/paper/2112.07945/) (2021)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction](https://mlsanity.com/paper/2111.11215/) (2021)
- [Neural Sparse Voxel Fields](https://mlsanity.com/paper/2007.11571/) (2020)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [LRM: Large Reconstruction Model for Single Image to 3D](https://mlsanity.com/paper/2311.04400/) (2023)
- [MVSNet: Depth Inference for Unstructured Multi-view Stereo](https://mlsanity.com/paper/1804.02505/) (2018)
- [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)
- [Depth-supervised NeRF: Fewer Views and Faster Training for Free](https://mlsanity.com/paper/2107.02791/) (2021)
- [Point-E: A System for Generating 3D Point Clouds from Complex Prompts](https://mlsanity.com/paper/2212.08751/) (2022)

## Built on by (most cited first, 30 of 35)

- [LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias](https://mlsanity.com/paper/2410.17242/) (2024)
- [Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splats](https://mlsanity.com/paper/2410.12781/) (2024)
- [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)
- [SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement](https://mlsanity.com/paper/2408.00653/) (2024)
- [4DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videos](https://mlsanity.com/paper/2506.08015/) (2025)
- [Prometheus: 3D-Aware Latent Diffusion Models for Feed-Forward Text-to-3D Scene Generation](https://mlsanity.com/paper/2412.21117/) (2024)
- [Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey](https://mlsanity.com/paper/2507.14501/) (2025)
- [RelitLRM: Generative Relightable Radiance for Large Reconstruction Models](https://mlsanity.com/paper/2410.06231/) (2024)
- [MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data](https://mlsanity.com/paper/2412.14166/) (2024)
- [DGS-LRM: Real-Time Deformable 3D Gaussian Reconstruction From Monocular Videos](https://mlsanity.com/paper/2506.09997/) (2025)
- [4D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time](https://mlsanity.com/paper/2506.18890/) (2025)
- [Reconstruct, Inpaint, Test-Time Finetune: Dynamic Novel-view Synthesis from Monocular Videos](https://mlsanity.com/paper/2507.12646/) (2025)
- [Flex3D: Feed-Forward 3D Generation with Flexible Reconstruction Model and Input View Curation](https://mlsanity.com/paper/2410.00890/) (2024)
- [MAR-3D: Progressive Masked Auto-regressor for High-Resolution 3D Generation](https://mlsanity.com/paper/2503.20519/) (2025)
- [KFC-W: Generating 3D-Consistent Videos from Unposed Internet Photos](https://mlsanity.com/paper/2411.13549/) (2024)
- [H3R: Hybrid Multi-view Correspondence for Generalizable 3D Reconstruction](https://mlsanity.com/paper/2508.03118/) (2025)
- [Scaling Transformer-Based Novel View Synthesis Models with Token Disentanglement and Synthetic Data](https://mlsanity.com/paper/2509.06950/) (2025)
- [WildRayZer: Self-supervised Large View Synthesis in Dynamic Environments](https://mlsanity.com/paper/2601.10716/) (2026)
- [Fast Spatial Memory with Elastic Test-Time Training](https://mlsanity.com/paper/2604.07350/) (2026)
- [DSplats: 3D Generation by Denoising Splats-Based Multiview Diffusion Models](https://mlsanity.com/paper/2412.09648/) (2024)
- [Twinner: Shining Light on Digital Twins in a Few Snaps](https://mlsanity.com/paper/2503.08382/) (2025)
- [Cue3D: Quantifying the Role of Image Cues in Single-Image 3D Generation](https://mlsanity.com/paper/2511.22121/) (2025)
- [Real-Time Human Frontal View Synthesis from a Single Image](https://mlsanity.com/paper/2603.15433/) (2026)
- [SynFlow: Scaling Up LiDAR Scene Flow Estimation with Synthetic Data](https://mlsanity.com/paper/2604.09411/) (2026)
- [Does Native 3D Texture Generation Necessarily Require 3D Assets for Training?](https://mlsanity.com/paper/2609.34621/) (2026)
- [Semantic-Free Procedural 3D Shapes Are Surprisingly Good Teachers](https://mlsanity.com/paper/2411.17467/) (2024)
- [GenVDM: Generating Vector Displacement Maps From a Single Image](https://mlsanity.com/paper/2503.00605/) (2025)
- [KaoLRM: Repurposing Pre-trained Large Reconstruction Models for Parametric 3D Face Reconstruction](https://mlsanity.com/paper/2601.12736/) (2026)
- [GeoFusionLRM: Geometry-Aware Self-Correction for Consistent 3D Reconstruction](https://mlsanity.com/paper/2602.14119/) (2026)

## Abstract (arXiv)

We present LRM-Zero, a Large Reconstruction Model (LRM) trained entirely on synthesized 3D data, achieving high-quality sparse-view 3D reconstruction. The core of LRM-Zero is our procedural 3D dataset, Zeroverse, which is automatically synthesized from simple primitive shapes with random texturing and augmentations (e.g., height fields, boolean differences, and wireframes). Unlike previous 3D datasets (e.g., Objaverse) which are often captured or crafted by humans to approximate real 3D data, Zeroverse completely ignores realistic global semantics but is rich in complex geometric and texture details that are locally similar to or even more intricate than real objects. We demonstrate that our LRM-Zero, trained with our fully synthesized Zeroverse, can achieve high visual quality in the reconstruction of real-world objects, competitive with models trained on Objaverse. We also analyze several critical design choices of Zeroverse that contribute to LRM-Zero's capability and training stability. Our work demonstrates that 3D reconstruction, one of the core tasks in 3D vision, can potentially be addressed without the semantics of real-world objects. The Zeroverse's procedural synthesis code and interactive visualization are available at: https://desaixie.github.io/lrm-zero/.