Gu Wang's repositories
IRLS_using_DL_frameworks
IRLS(Iterative re-weighted least square) for Logistic Regression, implemented using tensorflow2.0/pytorch
3D-Aware-Ellipses-for-Visual-Localization
3D-Aware Ellipse Prediction for Object-Based Camera Pose Estimation
flat_anneal_scheduler.pytorch
A (warmup) (cyclic) flat and anneal learning rate scheduler in pytorch
ai2thor
An open-source platform for Visual AI.
awesome-6d-object
Awesome work on object 6 DoF pose estimation and 3D reconstruction
BlenderProc
A procedural blender pipeline to generate images for deep learning
bop_toolkit
A Python toolkit of the BOP benchmark for 6D object pose estimation.
CAPTRA
Official PyTorch implementation of CAPTRA: CAtegory-level Pose Tracking for Rigid and Articulated Objects from Point Clouds
CIA-SSD
CIA-SSD: Confident IoU-Aware Single Stage Object Detector From Point Cloud, AAAI 2021.
contact_graspnet
Efficient 6-DoF Grasp Generation in Cluttered Scenes
cov-weighting
Implementation for our WACV 2021 paper "Multi-Loss Weighting with Coefficient of Variations"
giraffe
This repository will contain the code for the CVPR 2021 paper "GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields"
implicit_depth
RGB-D Local Implicit Function for Depth Completion of Transparent Objects
kornia
Open Source Differentiable Computer Vision Library for PyTorch
ManhattanSLAM
A Planar RGB-D SLAM which utilizes Manhattan World structure to provide optimal camera pose trajectory while also providing a sparse reconstruction containing points, lines and planes, and a dense surfel-based reconstruction.
manipulathor
ManipulaTHOR, a framework that facilitates visual manipulation of objects using a robotic arm
MaskFormer
Per-Pixel Classification is Not All You Need for Semantic Segmentation
mmcv
OpenMMLab Computer Vision Foundation
Pointformer
Repository of 3D Object Detection with Pointformer (CVPR2021)
pyrender
Easy-to-use glTF 2.0-compliant OpenGL renderer for visualization of 3D scenes.
thuthesis
LaTeX Thesis Template for Tsinghua University
uORF
Unsupervised Discovery of Object Radiance Fields
YOLOX
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported.