# OV-NeRF: Open-vocabulary Neural Radiance Fields with Vision and Language Foundation Models for 3D Semantic Understanding

arXiv: https://arxiv.org/abs/2402.04648 · HTML: https://mlsanity.com/paper/2402.04648/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 62 references that are in the map.
- First posted on arXiv 7 Feb 2024.

## Builds on (most cited first, 30 of 43)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [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)
- [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)
- [pixelNeRF: Neural Radiance Fields from One or Few Images](https://mlsanity.com/paper/2012.02190/) (2020)
- [TensoRF: Tensorial Radiance Fields](https://mlsanity.com/paper/2203.09517/) (2022)
- [Nerfies: Deformable Neural Radiance Fields](https://mlsanity.com/paper/2011.12948/) (2020)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [The Replica Dataset: A Digital Replica of Indoor Spaces](https://mlsanity.com/paper/1906.05797/) (2019)
- [Language-driven Semantic Segmentation](https://mlsanity.com/paper/2201.03546/) (2022)
- [Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields](https://mlsanity.com/paper/2304.06706/) (2023)
- [RegionCLIP: Region-based Language-Image Pretraining](https://mlsanity.com/paper/2112.09106/) (2021)
- [Extract Free Dense Labels from CLIP](https://mlsanity.com/paper/2112.01071/) (2021)
- [Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP](https://mlsanity.com/paper/2210.04150/) (2022)
- [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)
- [Segment Anything in High Quality](https://mlsanity.com/paper/2306.01567/) (2023)
- [Decomposing NeRF for Editing via Feature Field Distillation](https://mlsanity.com/paper/2205.15585/) (2022)
- [Visual Language Maps for Robot Navigation](https://mlsanity.com/paper/2210.05714/) (2022)
- [Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges](https://mlsanity.com/paper/1902.07830/) (2019)
- [ConceptFusion: Open-set Multimodal 3D Mapping](https://mlsanity.com/paper/2302.07241/) (2023)
- [Side Adapter Network for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2302.12242/) (2023)
- [Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP](https://mlsanity.com/paper/2308.02487/) (2023)
- [A Simple Framework for Open-Vocabulary Segmentation and Detection](https://mlsanity.com/paper/2303.08131/) (2023)
- [Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image Representations](https://mlsanity.com/paper/2209.03494/) (2022)

## Built on by (most cited first, 22 of 22)

- [OpenGaussian: Towards Point-Level 3D Gaussian-based Open Vocabulary Understanding](https://mlsanity.com/paper/2406.02058/) (2024)
- [Semantic Gaussians: Open-Vocabulary Scene Understanding with 3D Gaussian Splatting](https://mlsanity.com/paper/2403.15624/) (2024)
- [3D Gaussian Splatting: Survey, Technologies, Challenges, and Opportunities](https://mlsanity.com/paper/2407.17418/) (2024)
- [GOI: Find 3D Gaussians of Interest with an Optimizable Open-vocabulary Semantic-space Hyperplane](https://mlsanity.com/paper/2405.17596/) (2024)
- [Beyond Bare Queries: Open-Vocabulary Object Grounding with 3D Scene Graph](https://mlsanity.com/paper/2406.07113/) (2024)
- [LoopSparseGS: Loop Based Sparse-View Friendly Gaussian Splatting](https://mlsanity.com/paper/2408.00254/) (2024)
- [CLIP-GS: CLIP-Informed Gaussian Splatting for View-Consistent 3D Indoor Semantic Understanding](https://mlsanity.com/paper/2404.14249/) (2024)
- [SemanticSplat: Feed-Forward 3D Scene Understanding with Language-Aware Gaussian Fields](https://mlsanity.com/paper/2506.09565/) (2025)
- [Training-Free Hierarchical Scene Understanding for Gaussian Splatting with Superpoint Graphs](https://mlsanity.com/paper/2504.13153/) (2025)
- [FindAnything: Open-Vocabulary and Object-Centric Mapping for Robot Exploration in Any Environment](https://mlsanity.com/paper/2504.08603/) (2025)
- [Foundation Models Secretly Understand Neural Network Weights: Enhancing Hypernetwork Architectures with Foundation Models](https://mlsanity.com/paper/2503.00838/) (2025)
- [OpenObj: Open-Vocabulary Object-Level Neural Radiance Fields with Fine-Grained Understanding](https://mlsanity.com/paper/2406.08009/) (2024)
- [OpenGS-Fusion: Open-Vocabulary Dense Mapping with Hybrid 3D Gaussian Splatting for Refined Object-Level Understanding](https://mlsanity.com/paper/2508.01150/) (2025)
- [Vision-Language Memory for Spatial Reasoning](https://mlsanity.com/paper/2511.20644/) (2025)
- [4DLangVGGT: 4D Language-Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2512.05060/) (2025)
- [econSG: Efficient and Multi-view Consistent Open-Vocabulary 3D Semantic Gaussians](https://mlsanity.com/paper/2504.06003/) (2025)
- [LEGO-SLAM: Language-Embedded Gaussian Optimization SLAM](https://mlsanity.com/paper/2511.16144/) (2025)
- [SPC-GS: Gaussian Splatting with Semantic-Prompt Consistency for Indoor Open-World Free-view Synthesis from Sparse Inputs](https://mlsanity.com/paper/2503.12535/) (2025)
- [Bridging 3D Gaussians and Semantic Occupancy for Comprehensive Open-Vocabulary Scene Understanding from Unposed Images](https://mlsanity.com/paper/2607.01633/) (2026)
- [Robust Salient Object Detection on Compressed Images Using Convolutional Neural Networks](https://mlsanity.com/paper/2409.13464/) (2024)
- [Voxel-Aggregated Feature Synthesis: Efficient Dense Mapping for Simulated 3D Reasoning](https://mlsanity.com/paper/2411.10616/) (2024)
- [First Shape, Then Meaning: Efficient Geometry and Semantics Learning for Indoor Reconstruction](https://mlsanity.com/paper/2605.03463/) (2026)

## Abstract (arXiv)

The development of Neural Radiance Fields (NeRFs) has provided a potent representation for encapsulating the geometric and appearance characteristics of 3D scenes. Enhancing the capabilities of NeRFs in open-vocabulary 3D semantic perception tasks has been a recent focus. However, current methods that extract semantics directly from Contrastive Language-Image Pretraining (CLIP) for semantic field learning encounter difficulties due to noisy and view-inconsistent semantics provided by CLIP. To tackle these limitations, we propose OV-NeRF, which exploits the potential of pre-trained vision and language foundation models to enhance semantic field learning through proposed single-view and cross-view strategies. First, from the single-view perspective, we introduce Region Semantic Ranking (RSR) regularization by leveraging 2D mask proposals derived from Segment Anything (SAM) to rectify the noisy semantics of each training view, facilitating accurate semantic field learning. Second, from the cross-view perspective, we propose a Cross-view Self-enhancement (CSE) strategy to address the challenge raised by view-inconsistent semantics. Rather than invariably utilizing the 2D inconsistent semantics from CLIP, CSE leverages the 3D consistent semantics generated from the well-trained semantic field itself for semantic field training, aiming to reduce ambiguity and enhance overall semantic consistency across different views. Extensive experiments validate our OV-NeRF outperforms current state-of-the-art methods, achieving a significant improvement of 20.31% and 18.42% in mIoU metric on Replica and ScanNet, respectively. Furthermore, our approach exhibits consistent superior results across various CLIP configurations, further verifying its robustness. Project page: https://github.com/pcl3dv/OV-NeRF.