Name: Silva rebacca
Type: User
Company: The Chinese University of Hong Kong
Bio: I am a Ph.D. student of The Chinese University of Hong Kong. I am interested in 3D vision, computer graphics, and artificial intelligence.
Location: The Chinese University of Hong Kong
Silva rebacca's Projects
AdelaiDet is an open source toolbox for multiple instance-level detection and recognition tasks.
BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentation (CVPR 2021)
[CVPR 2023] Exploring High-Quality Pseudo Masks for Weakly Supervised Instance Segmentation
Official PyTorch code for "BAM: Bottleneck Attention Module (BMVC2018)" and "CBAM: Convolutional Block Attention Module (ECCV2018)"
Code for our CVPR2021 paper coordinate attention
:fire: :muscle: Crack-Detection-and-Segmentation-Dataset-for-UAV-Inspection
This repository contains the codes for computing crack kinematics using a binary mask that represents a segmented crack. The methodoly hereby implementes was presented in the paper "Determing crack kinematics from imaged crack patterns" by Pantoja-Rosero et., al.
This repository contains code and dataset for the task crack segmentation using two architectures UNet_VGG16, UNet_Resnet and DenseNet-Tiramusu
CS-Net (MICCAI 2019) and CS2-Net (MedIA 2020)
深度学习500问,以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述,以帮助自己及有需要的读者。 全书分为18个章节,50余万字。由于水平有限,书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作,联系[email protected] 版权所有,违权必究 Tan 2018.06
Implementation of the paper "DeepLSD: Line Segment Detection and Refinement with Deep Image Gradients"
PyTorch Implementation of DeepWindows
FCN implementation on ECP(Ecole Centrale Paris) facades dataset, PyTorch
Joint Topology-preserving and Feature-refinement Network for Curvilinear Structure Segmentation (ICCV21)
Learning Continuous Image Representation with Local Implicit Image Function, in CVPR 2021 (Oral)
Line3D++ - Multi-View Stereo using Line Segments
A novel local intensity order transformation for robust curvilinear object segmentation(TIP)
This repository contains the codes for computing geometrical digital twins as LOD3 models for buildings using a structure from motion and semantic segmentation. The methodoly hereby implementes was presented in the paper "Generating LOD3 building models from structure-from-motion and semantic segmentation" by Pantoja-Rosero et., al.
This is the official repository for our recent work: PIDNet
PointNet and PointNet++ implemented by pytorch (pure python) and on ModelNet, ShapeNet and S3DIS.
Reconstructing compact building models from point clouds using deep implicit fields [ISPRS 2022]
Polygonal Surface Reconstruction from Point Clouds
A CV toolkit for my papers.
Implementation of the CVPR paper "Scan2LoD3: Reconstructing semantic 3D building models at LoD3 using ray casting and Bayesian networks"