uSF: Learning Neural Semantic Field with Uncertainty
This work addresses uncertainty estimation for 3D scene reconstruction in computer vision, but it is incremental as it builds on existing NeRF methods.
The paper tackles the problem of neural radiance fields lacking confidence assessment by proposing uSF, a model that predicts color, semantic labels, and uncertainty, showing improved performance with limited training images.
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/.