5 papers · 1 filter
RadarSplat: Radar Gaussian Splatting for High-Fidelity Data Synthesis and 3D Reconstruction of Autonomous Driving Scenes
Pou-Chun Kung, Skanda Harisha, Ram Vasudevan +2
High-Fidelity 3D scene reconstruction plays a crucial role in autonomous driving by enabling novel data generation from existing datasets. This allows simulating safety-critical sc…
These Magic Moments: Differentiable Uncertainty Quantification of Radiance Field Models
Parker Ewen, Hao Chen, Seth Isaacson +3
This paper introduces a novel approach to uncertainty quantification for radiance fields by leveraging higher-order moments of the rendering equation. Uncertainty quantification is…
Sensor Transfer: Learning Optimal Sensor Effect Image Augmentation for Sim-to-Real Domain Adaptation
Alexandra Carlson, Katherine A. Skinner, Ram Vasudevan +1
Performance on benchmark datasets has drastically improved with advances in deep learning. Still, cross-dataset generalization performance remains relatively low due to the domain…
DispSegNet: Leveraging Semantics for End-to-End Learning of Disparity Estimation from Stereo Imagery
Junming Zhang, Katherine A. Skinner, Ram Vasudevan +1
Recent work has shown that convolutional neural networks (CNNs) can be applied successfully in disparity estimation, but these methods still suffer from errors in regions of low-te…
Modeling Camera Effects to Improve Visual Learning from Synthetic Data
Alexandra Carlson, Katherine A. Skinner, Ram Vasudevan +1
Recent work has focused on generating synthetic imagery to increase the size and variability of training data for learning visual tasks in urban scenes. This includes increasing th…