12 citations · 29 across the 13 of their papers we have counts for
4 papers · 1 filter
SGIFormer: Semantic-guided and Geometric-enhanced Interleaving Transformer for 3D Instance Segmentation
Lei Yao, Yi Wang, Moyun Liu +1
In recent years, transformer-based models have exhibited considerable potential in point cloud instance segmentation. Despite the promising performance achieved by existing methods…
Multiple Prior Representation Learning for Self-Supervised Monocular Depth Estimation via Hybrid Transformer
Guodong Sun, Junjie Liu, Mingxuan Liu +2
Self-supervised monocular depth estimation aims to infer depth information without relying on labeled data. However, the lack of labeled information poses a significant challenge t…
Efficient Visual Fault Detection for Freight Train via Neural Architecture Search with Data Volume Robustness
Yang Zhang, Mingying Li, Huilin Pan +2
Deep learning-based fault detection methods have achieved significant success. In visual fault detection of freight trains, there exists a large characteristic difference between i…
A Concise but High-performing Network for Image Guided Depth Completion in Autonomous Driving
Moyun Liu, Bing Chen, Youping Chen +4
Depth completion is a crucial task in autonomous driving, aiming to convert a sparse depth map into a dense depth prediction. Due to its potentially rich semantic information, RGB…