Drone-assisted Road Gaussian Splatting with Cross-view Uncertainty
Robust and realistic rendering for large-scale road scenes is essential in autonomous
driving simulation. Recently, 3D Gaussian Splatting (3D-GS) has made groundbreaking …
driving simulation. Recently, 3D Gaussian Splatting (3D-GS) has made groundbreaking …
NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild
Abstract Neural Radiance Fields (NeRFs) have shown remarkable success in synthesizing
photorealistic views from multi-view images of static scenes but face challenges in dynamic …
photorealistic views from multi-view images of static scenes but face challenges in dynamic …
Next Best Sense: Guiding Vision and Touch with FisherRF for 3D Gaussian Splatting
We propose a framework for active next best view and touch selection for robotic
manipulators using 3D Gaussian Splatting (3DGS). 3DGS is emerging as a useful explicit …
manipulators using 3D Gaussian Splatting (3DGS). 3DGS is emerging as a useful explicit …
Bayesian uncertainty analysis for underwater 3D reconstruction with neural radiance fields
Neural radiance fields (NeRFs) are a deep learning technique that generates novel views of
3D scenes from multi-view images. As an extension of NeRFs, SeaThru-NeRF mitigates the …
3D scenes from multi-view images. As an extension of NeRFs, SeaThru-NeRF mitigates the …
Uncertainty Quantification of Neural Reflectance Fields for Underwater Scenes
Neural radiance fields and neural reflectance fields are novel deep learning methods for
generating novel views of 3D scenes from 2D images. To extend the neural scene …
generating novel views of 3D scenes from 2D images. To extend the neural scene …
Modeling uncertainty for Gaussian Splatting
We present Stochastic Gaussian Splatting (SGS): the first framework for uncertainty
estimation using Gaussian Splatting (GS). GS recently advanced the novel-view synthesis …
estimation using Gaussian Splatting (GS). GS recently advanced the novel-view synthesis …
See-Then-Grasp: Object Full 3D Reconstruction via Two-Stage Active Robotic Reconstruction Using Single Manipulator
Y Hong, J Kim, G Cha, E Kim, K Lee - Applied Sciences, 2025 - mdpi.com
In this paper, we propose an active robotic 3D reconstruction methodology for achieving full
object 3D reconstruction. Existing robotic 3D reconstruction approaches often struggle to …
object 3D reconstruction. Existing robotic 3D reconstruction approaches often struggle to …