6 papers
Structure-Centric Robust Monocular Depth Estimation via Knowledge Distillation
Runze Chen, Haiyong Luo, Fang Zhao +4
Monocular depth estimation, enabled by self-supervised learning, is a key technique for 3D perception in computer vision. However, it faces significant challenges in real-world sce…
The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimation
Lingdong Kong, Yaru Niu, Shaoyuan Xie +39
Accurate depth estimation under out-of-distribution (OoD) scenarios, such as adverse weather conditions, sensor failure, and noise contamination, is desirable for safety-critical a…
Map-Free Visual Relocalization Enhanced by Instance Knowledge and Depth Knowledge
Mingyu Xiao, Runze Chen, Haiyong Luo +3
Map-free relocalization technology is crucial for applications in autonomous navigation and augmented reality, but relying on pre-built maps is often impractical. It faces signific…
CSS: Overcoming Pose and Scene Challenges in Crowd-Sourced 3D Gaussian Splatting
Runze Chen, Mingyu Xiao, Haiyong Luo +5
We introduce Crowd-Sourced Splatting (CSS), a novel 3D Gaussian Splatting (3DGS) pipeline designed to overcome the challenges of pose-free scene reconstruction using crowd-sourced…
A Light-weight Deep Human Activity Recognition Algorithm Using Multi-knowledge Distillation
Runze Chen, Haiyong Luo, Fang Zhao +3
Inertial sensor-based human activity recognition (HAR) is the base of many human-centered mobile applications. Deep learning-based fine-grained HAR models enable accurate classific…
OccupancyDETR: Using DETR for Mixed Dense-sparse 3D Occupancy Prediction
Yupeng Jia, Jie He, Runze Chen +2
Visual-based 3D semantic occupancy perception is a key technology for robotics, including autonomous vehicles, offering an enhanced understanding of the environment by 3D. This app…