vobecant

POP3D

Source code for NeurIPS paper "POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images"

DriveAndSegment

DummyNet

Official implementation of paper "Artificial Dummies for Urban Dataset Augmentation"

CSP_modified

pedestrian_insertion

project2arxiv

Convert you Tex project to an arXiv version.

readme-md-generator

📄 CLI that generates beautiful README.md files

3D-Reconstruction

Use Python in Google Colab to generate 3D reconstruction of objects using AliceVision Meshroom

BipedalWalker-v3

Data-driven Project based on BipedalWalker-v3 of OpenAi

CTUstyle3

Macros for student's theses at CTU in Prague, using OpTeX

dino

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

efficientnet

Implementation of EfficientNet model. Keras and TensorFlow Keras.

Mask2Former-1

Code release for "Masked-attention Mask Transformer for Universal Image Segmentation"

npfl114

Materials for the Deep Learning -- ÚFAL course NPFL114

ovseg

Pedestron

[Pedestron] Pedestrian Detection: The Elephant In The Room. On ArXiv 2020

PersFormer_3DLane

[ECCV2022 oral] Perspective Transformer on 3D Lane Detection

PiCIE

PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in clustering (CVPR2021)

pix2pixHD__rnd_insertion

Pix2pixHD modified for my purposes.

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

RobotCarDataset-Scraper

Downloads files matching patterns from the Oxford Robotcar Dataset website

segmentation_models

Segmentation models with pretrained backbones. Keras and TensorFlow Keras.

Unsupervised-Semantic-Segmentation

v4

Fourth iteration of my personal website

vobecant.github.io

personal webpage

xmuda

Cross-Modal Unsupervised Domain Adaptationfor 3D Semantic Segmentation

yolov3_WannaSeeU