REV-INR: Regularized Evidential Implicit Neural Representation for Uncertainty-Aware Volume Visualization

2026-01-25

AI Summary

This work addresses the challenge of quantifying predictive uncertainty in traditional implicit neural representations (INRs), which hinders reliable assessment in volume data reconstruction and visualization. To this end, we propose a regularized evidential implicit neural representation by integrating evidential deep learning into the INR framework for the first time. Our method simultaneously outputs the reconstructed volume data values along with both aleatoric and epistemic uncertainties at the coordinate level within a single forward pass. This approach achieves accurate joint uncertainty estimation while preserving high-fidelity reconstruction quality and the fastest inference speed among comparable methods. Consequently, it significantly enhances model interpretability and the trustworthiness of visualizations derived from uncertain reconstructions.

Technology Category

• Reasoning under Uncertainty: Uncertainty Representations
• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Representation Learning for Vision

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Applications of Implicit Neural Representations (INRs) have emerged as a promising deep learning approach for compactly representing large volumetric datasets. These models can act as surrogates for volume data, enabling efficient storage and on-demand reconstruction via model predictions. However, conventional deterministic INRs only provide value predictions without insights into the model's prediction uncertainty or the impact of inherent noisiness in the data. This limitation can lead to unreliable data interpretation and visualization due to prediction inaccuracies in the reconstructed volume. Identifying erroneous results extracted from model-predicted data may be infeasible, as raw data may be unavailable due to its large size. To address this challenge, we introduce REV-INR, Regularized Evidential Implicit Neural Representation, which learns to predict data values accurately along with the associated coordinate-level data uncertainty and model uncertainty using only a single forward pass of the trained REV-INR during inference. By comprehensively comparing and contrasting REV-INR with existing well-established deep uncertainty estimation methods, we show that REV-INR achieves the best volume reconstruction quality with robust data (aleatoric) and model (epistemic) uncertainty estimates using the fastest inference time. Consequently, we demonstrate that REV-INR facilitates assessment of the reliability and trustworthiness of the extracted isosurfaces and volume visualization results, enabling analyses to be solely driven by model-predicted data.

Problem

• Implicit Neural Representation
• Uncertainty Quantification
• Volume Visualization
• Aleatoric Uncertainty
• Epistemic Uncertainty

Innovation

• Implicit Neural Representation
• Uncertainty Quantification
• Evidential Deep Learning
• Volume Visualization
• Aleatoric and Epistemic Uncertainty