# SemanticSplat: Feed-Forward 3D Scene Understanding with Language-Aware Gaussian Fields

arXiv: https://arxiv.org/abs/2506.09565 · HTML: https://mlsanity.com/paper/2506.09565/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 56 references that are in the map.
- First posted on arXiv 11 Jun 2025.

## Builds on (most cited first, 30 of 46)

- [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)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [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)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation](https://mlsanity.com/paper/2402.05054/) (2024)
- [Language-driven Semantic Segmentation](https://mlsanity.com/paper/2201.03546/) (2022)
- [pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction](https://mlsanity.com/paper/2312.12337/) (2023)
- [MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images](https://mlsanity.com/paper/2403.14627/) (2024)
- [LERF: Language Embedded Radiance Fields](https://mlsanity.com/paper/2303.09553/) (2023)
- [In-Place Scene Labelling and Understanding with Implicit Scene Representation](https://mlsanity.com/paper/2103.15875/) (2021)
- [LangSplat: 3D Language Gaussian Splatting](https://mlsanity.com/paper/2312.16084/) (2023)
- [Gaussian Grouping: Segment and Edit Anything in 3D Scenes](https://mlsanity.com/paper/2312.00732/) (2023)
- [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)
- [GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting](https://mlsanity.com/paper/2404.19702/) (2024)
- [GMFlow: Learning Optical Flow via Global Matching](https://mlsanity.com/paper/2111.13680/) (2021)
- [GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation](https://mlsanity.com/paper/2403.14621/) (2024)
- [Unifying Flow, Stereo and Depth Estimation](https://mlsanity.com/paper/2211.05783/) (2022)
- [Language Embedded 3D Gaussians for Open-Vocabulary Scene Understanding](https://mlsanity.com/paper/2311.18482/) (2023)
- [Panoptic Lifting for 3D Scene Understanding with Neural Fields](https://mlsanity.com/paper/2212.09802/) (2022)
- [Segment Any 3D Gaussians](https://mlsanity.com/paper/2312.00860/) (2023)
- [Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation](https://mlsanity.com/paper/2308.07931/) (2023)

## Built on by (most cited first, 14 of 14)

- [A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation](https://mlsanity.com/paper/2508.09977/) (2025)
- [Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective](https://mlsanity.com/paper/2604.14025/) (2026)
- [FLEG: Feed-Forward Language Embedded Gaussian Splatting from Any Views via Compact Semantic Representation](https://mlsanity.com/paper/2512.17541/) (2025)
- [SLARM: Streaming and Language-Aligned Reconstruction Model for Dynamic Scenes](https://mlsanity.com/paper/2603.22893/) (2026)
- [FF3R: Feedforward Feature 3D Reconstruction from Unconstrained views](https://mlsanity.com/paper/2604.09862/) (2026)
- [LangFlash: Feed-forward 3D Language Gaussian Splatting from Sparse Unposed Images](https://mlsanity.com/paper/2605.23287/) (2026)
- [Aesthetic Camera Viewpoint Suggestion with 3D Aesthetic Field](https://mlsanity.com/paper/2602.20363/) (2026)
- [EmbodiedSplat: Online Feed-Forward Semantic 3DGS for Open-Vocabulary 3D Scene Understanding](https://mlsanity.com/paper/2603.04254/) (2026)
- [Learning 3D Representations for Spatial Intelligence from Unposed Multi-View Images](https://mlsanity.com/paper/2604.10573/) (2026)
- [TrianguLang: Geometry-Aware Semantic Consensus for Pose-Free 3D Localization](https://mlsanity.com/paper/2603.08096/) (2026)
- [GS4City: Hierarchical Semantic Gaussian Splatting via City-Model Priors](https://mlsanity.com/paper/2604.11401/) (2026)
- [E3DGS: Unified Geometric-Photometric Equivariance for 3D Gaussian Splatting via Color-as-Geometry Embedding](https://mlsanity.com/paper/2607.15536/) (2026)
- [GroupForward: Building Referable 3D Scenes via Instance-Grouped Feed-Forward Gaussian Splatting](https://mlsanity.com/paper/2608.17535/) (2026)
- [DDMS: Discriminative Distillation of Multi-view Foundational Features into Single-view Models](https://mlsanity.com/paper/2608.23850/) (2026)

## Abstract (arXiv)

Holistic 3D scene understanding, which jointly models geometry, appearance, and semantics, is crucial for applications like augmented reality and robotic interaction. Existing feed-forward 3D scene understanding methods (e.g., LSM) are limited to extracting language-based semantics from scenes, failing to achieve holistic scene comprehension. Additionally, they suffer from low-quality geometry reconstruction and noisy artifacts. In contrast, per-scene optimization methods rely on dense input views, which reduces practicality and increases complexity during deployment. In this paper, we propose SemanticSplat, a feed-forward semantic-aware 3D reconstruction method, which unifies 3D Gaussians with latent semantic attributes for joint geometry-appearance-semantics modeling. To predict the semantic anisotropic Gaussians, SemanticSplat fuses diverse feature fields (e.g., LSeg, SAM) with a cost volume representation that stores cross-view feature similarities, enhancing coherent and accurate scene comprehension. Leveraging a two-stage distillation framework, SemanticSplat reconstructs a holistic multi-modal semantic feature field from sparse-view images. Experiments demonstrate the effectiveness of our method for 3D scene understanding tasks like promptable and open-vocabulary segmentation. Video results are available at https://semanticsplat.github.io.