Search Results for author:
Found 11 papers, 8 papers with code
Salient Sparse Visual Odometry With Pose-Only Supervision
Visual Odometry (VO) is vital for the navigation of autonomous systems, providing accurate position and orientation estimates at reasonable costs.
A Review and A Robust Framework of Data-Efficient 3D Scene Parsing with Traditional/Learned 3D Descriptors
To the best of our knowledge, there exists no unified framework that simultaneously solves the downstream high-level understanding tasks including both segmentation and detection, especially when labels are extremely limited.
A Data-efficient Framework for Robotics Large-scale LiDAR Scene Parsing
More importantly, we innovatively propose to learn to merge the over-divided clusters based on the local low-level geometric property similarities and the learned high-level feature similarities supervised by weak labels.
Generalized Label-Efficient 3D Scene Parsing via Hierarchical Feature Aligned Pre-Training and Region-Aware Fine-tuning
Deep neural network models have achieved remarkable progress in 3D scene understanding while trained in the closed-set setting and with full labels.
3D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Clouds
In addition, we design a domain randomization technique that alternatively randomizes the geometry styles of point clouds and aggregates their embeddings, ultimately leading to a generalizable model that can improve 3DSS under various adverse weather effectively.
SVCNet: Scribble-based Video Colorization Network with Temporal Aggregation
It addresses three common issues in the scribble-based video colorization area: colorization vividness, temporal consistency, and color bleeding.
Generalized 3D Self-supervised Learning Framework via Prompted Foreground-Aware Feature Contrast
The second is that we prevent over-discrimination between 3D segments/objects and encourage grouped foreground-to-background distinctions at the segment level with adaptive feature learning in a Siamese correspondence network, which adaptively learns feature correlations within and across point cloud views effectively.
Learning-Based Defect Recognitions for Autonomous UAV Inspections
We have summarized the existing crack detection and segmentation datasets and established the largest existing benchmark dataset on the internet for crack detection and segmentation, which is open-sourced for the research community.
Semi-Supervised Confidence-Level-based Contrastive Discrimination for Class-Imbalanced Semantic Segmentation
First and foremost, to make the model operate in a semi-supervised manner, we proposed the confidence-level-based contrastive learning to achieve instance discrimination in an explicit manner, and make the low-confidence low-quality features align with the high-confidence counterparts.
Transformer-CNN Cohort: Semi-supervised Semantic Segmentation by the Best of Both Students
To this end, we propose class-aware feature consistency distillation (CFCD) that first leverages the outputs of each student as the pseudo labels and generates class-aware feature (CF) maps for knowledge transfer between the two students.
FG-Net: Fast Large-Scale LiDAR Point Clouds Understanding Network Leveraging Correlated Feature Mining and Geometric-Aware Modelling
This work presents FG-Net, a general deep learning framework for large-scale point clouds understanding without voxelizations, which achieves accurate and real-time performance with a single NVIDIA GTX 1080 GPU.
Ranked #1 on
Semantic Segmentation
on Semantic3D
