# NeurNCD: Novel Class Discovery via Implicit Neural Representation

arXiv: https://arxiv.org/abs/2506.06412 · HTML: https://mlsanity.com/paper/2506.06412/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 42 references that are in the map.
- First posted on arXiv 6 Jun 2025.

## Builds on (most cited first, 19 of 19)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [The Replica Dataset: A Digital Replica of Indoor Spaces](https://mlsanity.com/paper/1906.05797/) (2019)
- [Open3D: A Modern Library for 3D Data Processing](https://mlsanity.com/paper/1801.09847/) (2018)
- [In-Place Scene Labelling and Understanding with Implicit Scene Representation](https://mlsanity.com/paper/2103.15875/) (2021)
- [Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughs](https://mlsanity.com/paper/2112.10703/) (2021)
- [Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentation](https://mlsanity.com/paper/2203.15224/) (2022)
- [Efficient RGB-D Semantic Segmentation for Indoor Scene Analysis](https://mlsanity.com/paper/2011.06961/) (2020)
- [Indoor Semantic Segmentation using depth information](https://mlsanity.com/paper/1301.3572/) (2013)
- [CTNet: Context-based Tandem Network for Semantic Segmentation](https://mlsanity.com/paper/2104.09805/) (2021)
- [Novel Class Discovery in Semantic Segmentation](https://mlsanity.com/paper/2112.01900/) (2021)
- [StructNeRF: Neural Radiance Fields for Indoor Scenes with Structural Hints](https://mlsanity.com/paper/2209.05277/) (2022)
- [DoF-NeRF: Depth-of-Field Meets Neural Radiance Fields](https://mlsanity.com/paper/2208.00945/) (2022)
- [Incremental Object Database: Building 3D Models from Multiple Partial Observations](https://mlsanity.com/paper/1808.00760/) (2018)
- [Incremental Class Discovery for Semantic Segmentation with RGBD Sensing](https://mlsanity.com/paper/1907.10008/) (2019)
- [Fast and Accurate Semantic Mapping through Geometric-based Incremental Segmentation](https://mlsanity.com/paper/1803.02784/) (2018)
- [Continual Adaptation of Semantic Segmentation using Complementary 2D-3D Data Representations](https://mlsanity.com/paper/2111.02156/) (2021)
- [AGRNav: Efficient and Energy-Saving Autonomous Navigation for Air-Ground Robots in Occlusion-Prone Environments](https://mlsanity.com/paper/2403.11607/) (2024)
- [SCIM: Simultaneous Clustering, Inference, and Mapping for Open-World Semantic Scene Understanding](https://mlsanity.com/paper/2206.10670/) (2022)

## Abstract (arXiv)

Discovering novel classes in open-world settings is crucial for real-world applications. Traditional explicit representations, such as object descriptors or 3D segmentation maps, are constrained by their discrete, hole-prone, and noisy nature, which hinders accurate novel class discovery. To address these challenges, we introduce NeurNCD, the first versatile and data-efficient framework for novel class discovery that employs the meticulously designed Embedding-NeRF model combined with KL divergence as a substitute for traditional explicit 3D segmentation maps to aggregate semantic embedding and entropy in visual embedding space. NeurNCD also integrates several key components, including feature query, feature modulation and clustering, facilitating efficient feature augmentation and information exchange between the pre-trained semantic segmentation network and implicit neural representations. As a result, our framework achieves superior segmentation performance in both open and closed-world settings without relying on densely labelled datasets for supervised training or human interaction to generate sparse label supervision. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art approaches on the NYUv2 and Replica datasets.