Wang Pengfei's repositories
3D-GMPDCNN
Some code of the implements of Geological Modeling Using 3D Pixel-Adaptive and Deformable Convolutional Neural Network
Adaptive-Control-Oriented-Meta-Learning
Adaptive control-oriented meta-learning for nonlinear systems
AirSim
Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research
blainder-range-scanner
BlAInder range scanner is a Blender add-on to simulate Lidar and Sonar measurements. The result can be saved as annotated 2D image or 3D point cloud.
deep-video-mvs
Code for "DeepVideoMVS: Multi-View Stereo on Video with Recurrent Spatio-Temporal Fusion" (CVPR 2021)
fovperi
Biologically inspired deep learning model for efficient foveal-peripheral vision
gpu-ray-surface-intersection-in-cuda
A GPU-based ray-surface intersection test implemented in CUDA
JL-DCF-pytorch
Code of JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detection(CVPR2020)
matryodshka
Main repo for ECCV 2020 paper MatryODShka: Real-time 6DoF Video View Synthesis using Multi-Sphere Images. visual.cs.brown.edu/matryodshka
nanoflownet
Code and trained networks of the paper "NanoFlowNet: Real-time Dense Optical Flow on a Nano Quadcopter"
NeuralRecon
Code for "NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video", CVPR 2021 oral
Object_Detection_Tracking
Out-of-the-box code and models for CMU's object detection and tracking system for multi-camera surveillance videos. Speed optimized Faster-RCNN model. Tensorflow based. Also supports EfficientDet. WACVW'20
omnimvs_pytorch
An unofficial PyTorch implementation of ICCV 2019 paper "OmniMVS: End-to-End Learning for Omnidirectional Stereo Matching"
OWOD
(CVPR 2021 Oral) Open World Object Detection
packnet-sfm
TRI-ML Monocular Depth Estimation Repository
RetinaTrack
The pytorch implement of the retina track original paper link: https://arxiv.org/abs/2003.13870
SSfM
SfM for sphere images in the ERP format within the framework of ColMap
StableLLVE
Learning Temporal Consistency for Low Light Video Enhancement from Single Images (CVPR2021)
SurroundDepth
SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation
syndata-generation
Code used to generate synthetic scenes and bounding box annotations for object detection. This was used to generate data used in the Cut, Paste and Learn paper
uncertain_depth
depth estimation with error propagation
WoodScape
The repository containing tools and information about the WoodScape dataset.