Search Results for author:
Found 4 papers, 3 papers with code
Semantics-aware LiDAR-Only Pseudo Point Cloud Generation for 3D Object Detection
Although LiDAR sensors are crucial for autonomous systems due to providing precise depth information, they struggle with capturing fine object details, especially at a distance, due to sparse and non-uniform data.
Depth- and Semantics-aware Multi-modal Domain Translation: Generating 3D Panoramic Color Images from LiDAR Point Clouds
This work presents a new depth- and semantics-aware conditional generative model, named TITAN-Next, for cross-domain image-to-image translation in a multi-modal setup between LiDAR and camera sensors.
Semantics-aware Multi-modal Domain Translation:From LiDAR Point Clouds to Panoramic Color Images
The framework starts with semantic segmentation of the point cloud, which is initially projected onto a spherical surface.
SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving
In this paper, we introduce SalsaNext for the uncertainty-aware semantic segmentation of a full 3D LiDAR point cloud in real-time.
Ranked #17 on
Robust 3D Semantic Segmentation
on SemanticKITTI-C
