# OpenNeRF: Open Set 3D Neural Scene Segmentation with Pixel-Wise Features and Rendered Novel Views

arXiv: https://arxiv.org/abs/2404.03650 · HTML: https://mlsanity.com/paper/2404.03650/

## Key facts

- Cited by 69 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 40 of its 48 references that are in the map.
- First posted on arXiv 4 Apr 2024.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 30 of 40)

- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://mlsanity.com/paper/2106.10689/) (2021)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [Volume Rendering of Neural Implicit Surfaces](https://mlsanity.com/paper/2106.12052/) (2021)
- [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)
- [UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction](https://mlsanity.com/paper/2104.10078/) (2021)
- [Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI](https://mlsanity.com/paper/2109.08238/) (2021)
- [NICE-SLAM: Neural Implicit Scalable Encoding for SLAM](https://mlsanity.com/paper/2112.12130/) (2021)
- [Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP](https://mlsanity.com/paper/2210.04150/) (2022)
- [OpenScene: 3D Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2211.15654/) (2022)
- [LERF: Language Embedded Radiance Fields](https://mlsanity.com/paper/2303.09553/) (2023)
- [DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting](https://mlsanity.com/paper/2112.01518/) (2021)
- [Scaling Open-Vocabulary Image Segmentation with Image-Level Labels](https://mlsanity.com/paper/2112.12143/) (2021)
- [MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction](https://mlsanity.com/paper/2206.00665/) (2022)
- [ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data](https://mlsanity.com/paper/2111.08897/) (2021)
- [In-Place Scene Labelling and Understanding with Implicit Scene Representation](https://mlsanity.com/paper/2103.15875/) (2021)
- [Joint 2D-3D-Semantic Data for Indoor Scene Understanding](https://mlsanity.com/paper/1702.01105/) (2017)
- [Decomposing NeRF for Editing via Feature Field Distillation](https://mlsanity.com/paper/2205.15585/) (2022)
- [CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields](https://mlsanity.com/paper/2112.05139/) (2021)
- [ConceptFusion: Open-set Multimodal 3D Mapping](https://mlsanity.com/paper/2302.07241/) (2023)
- [OpenMask3D: Open-Vocabulary 3D Instance Segmentation](https://mlsanity.com/paper/2306.13631/) (2023)
- [Language-Grounded Indoor 3D Semantic Segmentation in the Wild](https://mlsanity.com/paper/2204.07761/) (2022)
- [Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation](https://mlsanity.com/paper/2205.04334/) (2022)

## Built on by (most cited first, 30 of 69)

- [Improving 2D Feature Representations by 3D-Aware Fine-Tuning](https://mlsanity.com/paper/2407.20229/) (2024)
- [LoopSplat: Loop Closure by Registering 3D Gaussian Splats](https://mlsanity.com/paper/2408.10154/) (2024)
- [Open-Vocabulary Functional 3D Scene Graphs for Real-World Indoor Spaces](https://mlsanity.com/paper/2503.19199/) (2025)
- [Dr. Splat: Directly Referring 3D Gaussian Splatting via Direct Language Embedding Registration](https://mlsanity.com/paper/2502.16652/) (2025)
- [SuperGSeg: Open-Vocabulary 3D Segmentation with Structured Super-Gaussians](https://mlsanity.com/paper/2412.10231/) (2024)
- [Search3D: Hierarchical Open-Vocabulary 3D Segmentation](https://mlsanity.com/paper/2409.18431/) (2024)
- [3D Vision-Language Gaussian Splatting](https://mlsanity.com/paper/2410.07577/) (2024)
- [AnyUp: Universal Feature Upsampling](https://mlsanity.com/paper/2510.12764/) (2025)
- [SplatTalk: 3D VQA with Gaussian Splatting](https://mlsanity.com/paper/2503.06271/) (2025)
- [FunGraph: Functionality Aware 3D Scene Graphs for Language-Prompted Scene Interaction](https://mlsanity.com/paper/2503.07909/) (2025)
- [OpenSplat3D: Open-Vocabulary 3D Instance Segmentation using Gaussian Splatting](https://mlsanity.com/paper/2506.07697/) (2025)
- [Multiplayer Interactive World Models with Representation Autoencoders](https://mlsanity.com/paper/2607.05352/) (2026)
- [P2P-Bridge: Diffusion Bridges for 3D Point Cloud Denoising](https://mlsanity.com/paper/2408.16325/) (2024)
- [Functionality understanding and segmentation in 3D scenes](https://mlsanity.com/paper/2411.16310/) (2024)
- [RelationField: Relate Anything in Radiance Fields](https://mlsanity.com/paper/2412.13652/) (2024)
- [Spot-Compose: A Framework for Open-Vocabulary Object Retrieval and Drawer Manipulation in Point Clouds](https://mlsanity.com/paper/2404.12440/) (2024)
- [Trace3D: Consistent Segmentation Lifting via Gaussian Instance Tracing](https://mlsanity.com/paper/2508.03227/) (2025)
- [Rethinking Open-Vocabulary Segmentation of Radiance Fields in 3D Space](https://mlsanity.com/paper/2408.07416/) (2024)
- [Open-Vocabulary Online Semantic Mapping for SLAM](https://mlsanity.com/paper/2411.15043/) (2024)
- [IAAO: Interactive Affordance Learning for Articulated Objects in 3D Environments](https://mlsanity.com/paper/2504.06827/) (2025)
- [Ov3R: Open-Vocabulary Semantic 3D Reconstruction from RGB Videos](https://mlsanity.com/paper/2507.22052/) (2025)
- [PE3R: Perception-Efficient 3D Reconstruction](https://mlsanity.com/paper/2503.07507/) (2025)
- [Visibility-Aware Language Aggregation for Open-Vocabulary Segmentation in 3D Gaussian Splatting](https://mlsanity.com/paper/2509.05515/) (2025)
- [COS3D: Collaborative Open-Vocabulary 3D Segmentation](https://mlsanity.com/paper/2510.20238/) (2025)
- [Unified Semantic Transformer for 3D Scene Understanding](https://mlsanity.com/paper/2512.14364/) (2025)
- [ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding](https://mlsanity.com/paper/2410.13924/) (2024)
- [OpenDAS: Open-Vocabulary Domain Adaptation for 2D and 3D Segmentation](https://mlsanity.com/paper/2405.20141/) (2024)
- [Multimodal Spatial Language Maps for Robot Navigation and Manipulation](https://mlsanity.com/paper/2506.06862/) (2025)
- [ReLaGS: Relational Language Gaussian Splatting](https://mlsanity.com/paper/2603.17605/) (2026)
- [OpenHype: Hyperbolic Embeddings for Hierarchical Open-Vocabulary Radiance Fields](https://mlsanity.com/paper/2510.21441/) (2025)

## Abstract (arXiv)

Large visual-language models (VLMs), like CLIP, enable open-set image segmentation to segment arbitrary concepts from an image in a zero-shot manner. This goes beyond the traditional closed-set assumption, i.e., where models can only segment classes from a pre-defined training set. More recently, first works on open-set segmentation in 3D scenes have appeared in the literature. These methods are heavily influenced by closed-set 3D convolutional approaches that process point clouds or polygon meshes. However, these 3D scene representations do not align well with the image-based nature of the visual-language models. Indeed, point cloud and 3D meshes typically have a lower resolution than images and the reconstructed 3D scene geometry might not project well to the underlying 2D image sequences used to compute pixel-aligned CLIP features. To address these challenges, we propose OpenNeRF which naturally operates on posed images and directly encodes the VLM features within the NeRF. This is similar in spirit to LERF, however our work shows that using pixel-wise VLM features (instead of global CLIP features) results in an overall less complex architecture without the need for additional DINO regularization. Our OpenNeRF further leverages NeRF's ability to render novel views and extract open-set VLM features from areas that are not well observed in the initial posed images. For 3D point cloud segmentation on the Replica dataset, OpenNeRF outperforms recent open-vocabulary methods such as LERF and OpenScene by at least +4.9 mIoU.