Jesse Dill — accepted AI-conference papers

2026

Uncertainty-driven 3D Gaussian Splatting Active Mapping via Anisotropic Visibility Field

Shangjie Xue, Jesse Dill, Dhruv Ahuja, Frank Dellaert, Panagiotis Tsiotras, Danfei Xu

CVPR 2026

We present Gaussian Splatting Anisotropic Visibility Field (GAVIS), a novel framework for uncertainty quantification and active mapping in 3DGS. Our key insight is that regions unseen from the training views yield unreliable predictions from the 3DGS. To address this, we introduce a principled and e

Cited by 0 Source ↗code ↗Scholar ↗

2024

Neural Visibility Field for Uncertainty-Driven Active Mapping

Shangjie Xue, Jesse Dill, Pranay Mathur, Frank Dellaert, Panagiotis Tsiotra, Danfei Xu

CVPR 2024poster

This paper presents Neural Visibility Field (NVF) a novel uncertainty quantification method for Neural Radiance Fields (NeRF) applied to active mapping. Our key insight is that regions not visible in the training views lead to inherently unreliable color predictions by NeRF at this region resulting…

Cited by 4 Source ↗PDF ↗Scholar ↗