uSF: Learning Neural Semantic Field with Uncertainty
Not on the map. Why?
Abstract (arXiv)
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/.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 30 of its 37 references that are in the map. First posted on arXiv 13 Dec 2023.
Builds on
30 of 37 references.
References · 30
- 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
- 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
- 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
- 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
- 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
- 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
- 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
- 2019The Replica Dataset: A Digital Replica of Indoor Spacescited by 885
- 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 735
- 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 732
- 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 728
- 2021In-Place Scene Labelling and Understanding with Implicit Scene Representationcited by 411
18 more
- 2019Deep Evidential Regressioncited by 354
- 2022NoPe-NeRF: Optimising Neural Radiance Field with No Pose Priorcited by 235
- 2023MERF: Memory-Efficient Radiance Fields for Real-time View Synthesis in Unbounded Scenescited by 215
- 2021NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereocited by 191
- 2022ActiveNeRF: Learning where to See with Uncertainty Estimationcited by 124
- 2021NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenescited by 119
- 2023F2-NeRF: Fast Neural Radiance Field Training with Free Camera Trajectoriescited by 118
- 2023NeRF-DS: Neural Radiance Fields for Dynamic Specular Objectscited by 110
- 2023Bayes' Rays: Uncertainty Quantification for Neural Radiance Fieldscited by 90
- 2021Stochastic Neural Radiance Fields: Quantifying Uncertainty in Implicit 3D Representationscited by 80
- 2022Conditional-Flow NeRF: Accurate 3D Modelling with Reliable Uncertainty Quantificationcited by 71
- 2022NeRF-RPN: A general framework for object detection in NeRFscited by 46
- 2023Semantic Ray: Learning a Generalizable Semantic Field with Cross-Reprojection Attentioncited by 29
- 2021Ensemble Quantile Networks: Uncertainty-Aware Reinforcement Learning with Applications in Autonomous Drivingcited by 17
- 2022SteerNeRF: Accelerating NeRF Rendering via Smooth Viewpoint Trajectorycited by 15
- 2023Neural radiance fields in the industrial and robotics domain: applications, research opportunities and use casescited by 10
- 2022HPointLoc: Point-based Indoor Place Recognition using Synthetic RGB-D Imagescited by 7
- 2023MIMO-NeRF: Fast Neural Rendering with Multi-input Multi-output Neural Radiance Fieldscited by 7
Built on by
Citing papers per year: 2025: 1.
1 paper.