# GOV-NeSF: Generalizable Open-Vocabulary Neural Semantic Fields

arXiv: https://arxiv.org/abs/2404.00931 · HTML: https://mlsanity.com/paper/2404.00931/

## Key facts

- Cited by 8 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 49 of its 58 references that are in the map.
- First posted on arXiv 1 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 49)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (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)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [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)
- [pixelNeRF: Neural Radiance Fields from One or Few Images](https://mlsanity.com/paper/2012.02190/) (2020)
- [3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation](https://mlsanity.com/paper/1606.06650/) (2016)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [The Replica Dataset: A Digital Replica of Indoor Spaces](https://mlsanity.com/paper/1906.05797/) (2019)
- [OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework](https://mlsanity.com/paper/2202.03052/) (2022)
- [MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo](https://mlsanity.com/paper/2103.15595/) (2021)
- [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)
- [FILIP: Fine-grained Interactive Language-Image Pre-Training](https://mlsanity.com/paper/2111.07783/) (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)
- [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)
- [Point-NeRF: Point-based Neural Radiance Fields](https://mlsanity.com/paper/2201.08845/) (2022)
- [Scaling Open-Vocabulary Image Segmentation with Image-Level Labels](https://mlsanity.com/paper/2112.12143/) (2021)

## Built on by (most cited first, 8 of 8)

- [VCR-GauS: View Consistent Depth-Normal Regularizer for Gaussian Surface Reconstruction](https://mlsanity.com/paper/2406.05774/) (2024)
- [NeRFs in Robotics: A Survey](https://mlsanity.com/paper/2405.01333/) (2024)
- [FreeSplat++: Generalizable 3D Gaussian Splatting for Efficient Indoor Scene Reconstruction](https://mlsanity.com/paper/2503.22986/) (2025)
- [econSG: Efficient and Multi-view Consistent Open-Vocabulary 3D Semantic Gaussians](https://mlsanity.com/paper/2504.06003/) (2025)
- [RAZER: Robust Accelerated Zero-Shot 3D Open-Vocabulary Panoptic Reconstruction with Spatio-Temporal Aggregation](https://mlsanity.com/paper/2505.15373/) (2025)
- [The Semantic Lifecycle in Embodied AI: Acquisition, Representation and Storage via Foundation Models](https://mlsanity.com/paper/2601.08876/) (2026)
- [UniFField: A Generalizable Unified Neural Feature Field for Visual, Semantic, and Spatial Uncertainties in Any Scene](https://mlsanity.com/paper/2510.06754/) (2025)
- [Robust Dreamer: Deviation-Aware Latent Gaussian Memory for Action-Controlled AR Video Generation](https://mlsanity.com/paper/2605.30855/) (2026)

## Abstract (arXiv)

Recent advancements in vision-language foundation models have significantly enhanced open-vocabulary 3D scene understanding. However, the generalizability of existing methods is constrained due to their framework designs and their reliance on 3D data. We address this limitation by introducing Generalizable Open-Vocabulary Neural Semantic Fields (GOV-NeSF), a novel approach offering a generalizable implicit representation of 3D scenes with open-vocabulary semantics. We aggregate the geometry-aware features using a cost volume, and propose a Multi-view Joint Fusion module to aggregate multi-view features through a cross-view attention mechanism, which effectively predicts view-specific blending weights for both colors and open-vocabulary features. Remarkably, our GOV-NeSF exhibits state-of-the-art performance in both 2D and 3D open-vocabulary semantic segmentation, eliminating the need for ground truth semantic labels or depth priors, and effectively generalize across scenes and datasets without fine-tuning.