aycatakmaz

AffordanceNet

ARKitScenes

behave-dataset

code to access BEHAVE dataset

compass

Repository containing the code of "Learning to Orient Surfaces by Self-supervised Spherical CNNs".

Deep-SAD-PyTorch

A PyTorch implementation of Deep SAD, a deep Semi-supervised Anomaly Detection method.

ExPGAN

ExPGAN: Segmentation Guided Image Outpainting

wsvd_dataset_loader

Loader for WSVD dataset (+ eliminating invalid/deleted youtube videos from the video id list)

Human3D

We propose the first multi-human body-part segmentation model, called Human3D 🧑‍🤝‍🧑, that directly operates on 3D scenes. In an extensive analysis, we validate the benefits of training on synthetic data on multiple baselines and tasks.

SyntheticHumanDataset

This repo contains the code to generate synthetic human-scene interaction dataset used for Human3D 🧑‍🤝‍🧑, accepted at ICCV 2023.

openmask3d

aycatakmaz/wsvd_dataset_loader

Loader for WSVD dataset (+ eliminating invalid/deleted youtube videos from the video id list)

aycatakmaz/AffordanceNet

aycatakmaz/ARKitScenes

aycatakmaz/behave-dataset

code to access BEHAVE dataset

aycatakmaz/compass

Repository containing the code of "Learning to Orient Surfaces by Self-supervised Spherical CNNs".

aycatakmaz/Deep-SAD-PyTorch

A PyTorch implementation of Deep SAD, a deep Semi-supervised Anomaly Detection method.

aycatakmaz/H3DNet

aycatakmaz/imvotenet

ImVoteNet: Boosting 3D Object Detection in Point Clouds With Image Votes

aycatakmaz/imvotenet-1

aycatakmaz/Mask2Former

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

aycatakmaz/md2-nrd

[ICCV 2019] Monocular depth estimation from a single image

aycatakmaz/MLCVNet

[CVPR 2020] MLCVNet: Multi-Level Context VoteNet for 3D Object Detection

aycatakmaz/MlspAestheticScorePredictor

aycatakmaz/mmaction2

OpenMMLab's Next Generation Action Understanding Toolbox and Benchmark

aycatakmaz/movienet-tools

Tools for movie and video research

aycatakmaz/nerf-pytorch

A PyTorch implementation of NeRF (Neural Radiance Fields) that reproduces the results.

aycatakmaz/packnet-sfm

TRI-ML Monocular Depth Estimation Repository

aycatakmaz/panoptic-reconstruction

(WIP) Official implementation of the NeurIPS 2021 paper "Panoptic 3D Scene Reconstruction from a Single RGB Image"

aycatakmaz/Point-Transformers

Point Transformers

aycatakmaz/PointGroup

PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation

aycatakmaz/PoinTr

[ICCV 2021 Oral] PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers

aycatakmaz/RandLA-Net-pytorch

:four_leaf_clover: Pytorch Implementation of RandLA-Net (https://arxiv.org/abs/1911.11236)

aycatakmaz/ROCA

Official code for ROCA: Robust CAD Model Retrieval and Alignment from a Single Image (CVPR 2022)

aycatakmaz/s2cnn

Spherical CNNs

aycatakmaz/simkinect

Simulating Kinect Noise: adding noise to clean depth-maps rendered with a graphics engine.

aycatakmaz/SoftGroup

[CVPR 2022 Oral] SoftGroup for Instance Segmentation on 3D Point Clouds

aycatakmaz/starter-academic

aycatakmaz/vitrivr-ng

Vitrivr NG is a web-based user interface for searching and browsing mixed multimedia collections. It provides the user with the ability to use cineast's retrieval capabilities.

aycatakmaz/votenet

Deep Hough Voting for 3D Object Detection in Point Clouds

aycatakmaz/where2act

Where2Act: From Pixels to Actions for Articulated 3D Objects