waterbearbee's repositories
shift-dev
SHIFT Dataset DevKit - CVPR2022
UniAD
Goal-oriented Autonomous Driving
multinerf
A Code Release for Mip-NeRF 360, Ref-NeRF, and RawNeRF
BEVFusion
Offical PyTorch implementation of "BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework"
Awesome-Transformer-Attention
An ultimately comprehensive paper list of Vision Transformer/Attention, including papers, codes, and related websites
Monocular-Depth-Estimation-Toolbox
Monocular Depth Estimation Toolbox based on MMSegmentation.
MiDaS
Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2020"
MonoScene
MonoScene: Monocular 3D Semantic Scene Completion. CVPR 2022
deep-learning-localization-mapping
A collection of deep learning based localization models
MPL-pytorch
Unofficial PyTorch implementation of "Meta Pseudo Labels"
mmdeploy
OpenMMLab Model Deployment Framework
ML_Decoder
Official PyTorch implementation of "ML-Decoder: Scalable and Versatile Classification Head" (2021)
sg-risk-assessment
This repo includes the source code and dataset information for reproducing the results of our paper (https://arxiv.org/abs/2009.06435)
VisSatSatelliteStereo
This is the python interface for adapted COLMAP; you can run both SfM and MVS.
sfm-disambiguation-colmap
Making Structure-from-Motion (COLMAP) more robust to symmetries and duplicated structures
VTE
video trajectory estimation
Topo-boundary
A public available dataset for road boundary detection in aerial images
LVI-SAM
LVI-SAM: Tightly-coupled Lidar-Visual-Inertial Odometry via Smoothing and Mapping
multi-scene-pose-transformer
Multi-Scene Camera Pose Regression with Transformers
roadscene2vec
A Tool for Extracting and Embedding Road Scene-Graphs
Visual-Odometry
This project implements visual odometry to estimate the trajectory of a self-driving car.
models
Models and examples built with TensorFlow
qd-3dt
Official implementation of Monocular Quasi-Dense 3D Object Tracking
DA-RetinaNet
Official Detectron2 implementation of DA-RetinaNet of our Image and Vision Computing 2021 work 'An unsupervised domain adaptation scheme for single-stage artwork recognition in cultural sites'
AlignPS
Code for CVPR 2021 paper: Anchor-Free Person Search
FRSKD
Official implementation for (Refine Myself by Teaching Myself : Feature Refinement via Self-Knowledge Distillation, CVPR-2021)