Robin Karlsson's repositories
perspective_mapping
Demonstration of applying direct and inverse perspective mapping to generate a top-down camera view
predictive-world-models
Code accompanying the paper "Predictive World Models from Real-World Partial Observations" (MOST 2023)
mmdetection3d
OpenMMLab's next-generation platform for general 3D object detection.
pc-accumulation-lib
Library for temporal accumulation of semantic point clouds generated from image and lidar senor data
alpha_precision_and_recall
Computes the Alpha Precision and Recall metric for evaluating sample quality and diversity of generative models.
conditional-vae
Conditional VAE experiment code in PyTorch Lightning
osqp_cpp_interface
Native C++ interface for the OSQP solver
variational_bayes_models
Library implementing the linear and logistic variational Bayes models as formulated in PRML and other sources
bayesian-perception-demo
A collection of examples demonstrating the elegance and merits of representing model output and priors as probabilistic distributions, which can be integrated in a principled way using Bayes' theorem.
filtering-algorithms
A collection of filtering algorithms implemented as Jupyter notebooks
gmap-road-bev-generator
Google Maps Road BEV Generator
graph-search-algorithms
Collection of graph search algorithms and auxiliary functions
lat_var_bev_pred_model
Latent variable BEV prediction model
mmdetection
OpenMMLab Detection Toolbox and Benchmark
mmsegmentation
OpenMMLab Semantic Segmentation Toolbox and Benchmark.
packnet-sfm
TRI-ML Monocular Depth Estimation Repository
PiCIE
PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in clustering (CVPR2021)
Pseudo_Lidar_V2
(ICLR) Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving
pytorch-CycleGAN-and-pix2pix
Image-to-Image Translation in PyTorch
pytorch-tutorial
PyTorch Tutorial for Deep Learning Researchers
rainfall_modeling_open_fix
Code to reproduce results in the paper 'Probabilistic Rainfall Estimation from Automotive Lidar'
rloss
Regularized Losses (rloss) for Weakly-supervised CNN Segmentation
road_lane_network_graph_open
Code to reproduce results in the paper "Learning a Model for Inferring a Spatial Road Lane Network Graph using Self-Supervision" (ITSC 2021)
STEGO
Unsupervised Semantic Segmentation by Distilling Feature Correspondences
vbmm
Variational inference for Gaussian mixture models
vision
Datasets, Transforms and Models specific to Computer Vision
ViT-Adapter
[ICLR 2023 Spotlight] Vision Transformer Adapter for Dense Predictions