# Large Spatial Model: End-to-end Unposed Images to Semantic 3D

arXiv: https://arxiv.org/abs/2410.18956 · HTML: https://mlsanity.com/paper/2410.18956/

## Key facts

- Cited by 73 papers in the map (data through 14 Oct 2026).
- Builds on 57 of its 72 references that are in the map.
- First posted on arXiv 24 Oct 2024.

## Builds on (most cited first, 30 of 57)

- [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)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [The Replica Dataset: A Digital Replica of Indoor Spaces](https://mlsanity.com/paper/1906.05797/) (2019)
- [MVSNet: Depth Inference for Unstructured Multi-view Stereo](https://mlsanity.com/paper/1804.02505/) (2018)
- [ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes](https://mlsanity.com/paper/2308.11417/) (2023)
- [PCT: Point cloud transformer](https://mlsanity.com/paper/2012.09688/) (2020)
- [Language-driven Semantic Segmentation](https://mlsanity.com/paper/2201.03546/) (2022)
- [IBRNet: Learning Multi-View Image-Based Rendering](https://mlsanity.com/paper/2102.13090/) (2021)
- [DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras](https://mlsanity.com/paper/2108.10869/) (2021)
- [pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction](https://mlsanity.com/paper/2312.12337/) (2023)
- [Point Transformer V3: Simpler, Faster, Stronger](https://mlsanity.com/paper/2312.10035/) (2023)
- [Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching](https://mlsanity.com/paper/1912.06378/) (2019)
- [In-Place Scene Labelling and Understanding with Implicit Scene Representation](https://mlsanity.com/paper/2103.15875/) (2021)
- [Gaussian Splatting SLAM](https://mlsanity.com/paper/2312.06741/) (2023)
- [LangSplat: 3D Language Gaussian Splatting](https://mlsanity.com/paper/2312.16084/) (2023)
- [Decomposing NeRF for Editing via Feature Field Distillation](https://mlsanity.com/paper/2205.15585/) (2022)
- [Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields](https://mlsanity.com/paper/2312.03203/) (2023)
- [Splatter Image: Ultra-Fast Single-View 3D Reconstruction](https://mlsanity.com/paper/2312.13150/) (2023)
- [DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes](https://mlsanity.com/paper/2312.07920/) (2023)
- [NoPe-NeRF: Optimising Neural Radiance Field with No Pose Prior](https://mlsanity.com/paper/2212.07388/) (2022)

## Built on by (most cited first, 30 of 73)

- [VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction](https://mlsanity.com/paper/2505.20279/) (2025)
- [VLM4D: Towards Spatiotemporal Awareness in Vision Language Models](https://mlsanity.com/paper/2508.02095/) (2025)
- [Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations](https://mlsanity.com/paper/2510.23607/) (2025)
- [Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction](https://mlsanity.com/paper/2411.14384/) (2024)
- [PreF3R: Pose-Free Feed-Forward 3D Gaussian Splatting from Variable-length Image Sequence](https://mlsanity.com/paper/2411.16877/) (2024)
- [IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction](https://mlsanity.com/paper/2510.22706/) (2025)
- [Feat2GS: Probing Visual Foundation Models with Gaussian Splatting](https://mlsanity.com/paper/2412.09606/) (2024)
- [Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey](https://mlsanity.com/paper/2507.14501/) (2025)
- [Uni3R: Unified 3D Reconstruction and Semantic Understanding via Generalizable Gaussian Splatting from Unposed Multi-View Images](https://mlsanity.com/paper/2508.03643/) (2025)
- [SplatTalk: 3D VQA with Gaussian Splatting](https://mlsanity.com/paper/2503.06271/) (2025)
- [C3G: Learning Compact 3D Representations with 2K Gaussians](https://mlsanity.com/paper/2512.04021/) (2025)
- [A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation](https://mlsanity.com/paper/2508.09977/) (2025)
- [SplatFormer: Point Transformer for Robust 3D Gaussian Splatting](https://mlsanity.com/paper/2411.06390/) (2024)
- [SIU3R: Simultaneous Scene Understanding and 3D Reconstruction Beyond Feature Alignment](https://mlsanity.com/paper/2507.02705/) (2025)
- [UniForward: Unified 3D Scene and Semantic Field Reconstruction via Feed-Forward Gaussian Splatting from Only Sparse-View Images](https://mlsanity.com/paper/2506.09378/) (2025)
- [SemanticSplat: Feed-Forward 3D Scene Understanding with Language-Aware Gaussian Fields](https://mlsanity.com/paper/2506.09565/) (2025)
- [Towards Cross-View Point Correspondence in Vision-Language Models](https://mlsanity.com/paper/2512.04686/) (2025)
- [Feature4X: Bridging Any Monocular Video to 4D Agentic AI with Versatile Gaussian Feature Fields](https://mlsanity.com/paper/2503.20776/) (2025)
- [SpatialSplat: Efficient Semantic 3D from Sparse Unposed Images](https://mlsanity.com/paper/2505.23044/) (2025)
- [CF3: Compact and Fast 3D Feature Fields](https://mlsanity.com/paper/2508.05254/) (2025)
- [Can Video Diffusion Model Reconstruct 4D Geometry?](https://mlsanity.com/paper/2503.21082/) (2025)
- [PE3R: Perception-Efficient 3D Reconstruction](https://mlsanity.com/paper/2503.07507/) (2025)
- [Sparfels: Fast Reconstruction from Sparse Unposed Imagery](https://mlsanity.com/paper/2505.02178/) (2025)
- [PanoSplatt3R: Leveraging Perspective Pretraining for Generalized Unposed Wide-Baseline Panorama Reconstruction](https://mlsanity.com/paper/2507.21960/) (2025)
- [VGGT-X: When VGGT Meets Dense Novel View Synthesis](https://mlsanity.com/paper/2509.25191/) (2025)
- [Understanding Multi-View Transformers](https://mlsanity.com/paper/2510.24907/) (2025)
- [Unified Semantic Transformer for 3D Scene Understanding](https://mlsanity.com/paper/2512.14364/) (2025)
- [Digital Twin Generation from Visual Data: A Survey](https://mlsanity.com/paper/2504.13159/) (2025)
- [E3D-Bench: A Benchmark for End-to-End 3D Geometric Foundation Models](https://mlsanity.com/paper/2506.01933/) (2025)
- [SAB3R: Semantic-Augmented Backbone in 3D Reconstruction](https://mlsanity.com/paper/2506.02112/) (2025)

## Abstract (arXiv)

Reconstructing and understanding 3D structures from a limited number of images is a well-established problem in computer vision. Traditional methods usually break this task into multiple subtasks, each requiring complex transformations between different data representations. For instance, dense reconstruction through Structure-from-Motion (SfM) involves converting images into key points, optimizing camera parameters, and estimating structures. Afterward, accurate sparse reconstructions are required for further dense modeling, which is subsequently fed into task-specific neural networks. This multi-step process results in considerable processing time and increased engineering complexity. In this work, we present the Large Spatial Model (LSM), which processes unposed RGB images directly into semantic radiance fields. LSM simultaneously estimates geometry, appearance, and semantics in a single feed-forward operation, and it can generate versatile label maps by interacting with language at novel viewpoints. Leveraging a Transformer-based architecture, LSM integrates global geometry through pixel-aligned point maps. To enhance spatial attribute regression, we incorporate local context aggregation with multi-scale fusion, improving the accuracy of fine local details. To tackle the scarcity of labeled 3D semantic data and enable natural language-driven scene manipulation, we incorporate a pre-trained 2D language-based segmentation model into a 3D-consistent semantic feature field. An efficient decoder then parameterizes a set of semantic anisotropic Gaussians, facilitating supervised end-to-end learning. Extensive experiments across various tasks show that LSM unifies multiple 3D vision tasks directly from unposed images, achieving real-time semantic 3D reconstruction for the first time.