Search Results for author:
Found 4 papers, 2 papers with code
MSI-NeRF: Linking Omni-Depth with View Synthesis through Multi-Sphere Image aided Generalizable Neural Radiance Field
We first construct a multi-sphere image as a cost volume through feature extraction and warping of the input images.
Hierarchical Adaptive Voxel-guided Sampling for Real-time Applications in Large-scale Point Clouds
While point-based neural architectures have demonstrated their efficacy, the time-consuming sampler currently prevents them from performing real-time reasoning on scene-level point clouds.
Active Implicit Object Reconstruction using Uncertainty-guided Next-Best-View Optimization
To evaluate view uncertainty, we employ a sampling-based approach that directly extracts entropy from the reconstructed occupancy probability field as our measure of view information gain.
Det6D: A Ground-Aware Full-Pose 3D Object Detector for Improving Terrain Robustness
Current methods suffer from performance degradation in this case due to difficulty correctly detecting objects on sloped terrain.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
