uSF: Learning Neural Semantic Field with Uncertainty

2023/12/13 by Vsevolod Skorokhodov, Skorokhodov, Vsevolod, Darya Drozdova +3 · 1 citation
Computer Science · #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Medical Image Segmentation Techniques

paper · pdf · doi:10.48550/arxiv.2312.08012

openalex publication_date 2023/12/13 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Recently, there has been an increased interest in NeRF methods which reconstruct differentiable representation of three-dimensional scenes. One of the main limitations of such methods is their inability to assess the confidence of the model in its predictions. In this paper, we propose a new neural network model for the formation of extended vector representations, called uSF, which allows the model to predict not only color and semantic label of each point, but also estimate the corresponding values of uncertainty. We show that with a small number of images available for training, a model quantifying uncertainty performs better than a model without such functionality. Code of the uSF approach is publicly available at https://github.com/sevashasla/usf/.

Cited by

• M3DMap: Object-aware Multimodal 3D Mapping for Dynamic Environments

Related

• Uncertainty Quantification and Resource-Demanding Computer Vision Applications of Deep Learning
• UniFField: A Generalizable Unified Neural Feature Field for Visual, Semantic, and Spatial Uncertainties in Any Scene
• Nonparametric Uncertainty Quantification for Single Deterministic Neural Network
• Uncertainty-Aware Deep Neural Representations for Visual Analysis of Vector Field Data
• Optimistic and Pessimistic Neural Networks for Scene and Object Recognition