Paper & Code | OpenSynthetics

Datasets
Paper/Code
Learn
Log In / Register

Select Page

Contribute Papers/Code to OpenSynthetics

ML Task

Activity Recognition Anomaly Detection Autonomous Vehicles Batch Normalization Bias Identification Data Augmentation Denoising Depth Estimation Domain Adaptation Face Animation Facial Modeling Facial Recognition Fine-Tuning with Real Data General Human Pose Estimation Image Classification Image Generation Instance Segmentation Label Adaptation Medical Imagery NERF OCR Object Detection Object Recognition Object Tracking Scene Understanding Semantic Segmentation Style Transfer Super-Resolution

Show MoreShow Less

Verticals

A/V AR/VR Digital Human Facial General Home/Office Industrial & Warehouse Robotics Medical Satellite Synthetic Media & Art

Show MoreShow Less

Modality

3D Asset General LiDAR Point Cloud RGB-D Stereo Still Image Video

Show MoreShow Less

Reset

BANMo

3D reconstruction with deformable animations from casual video collections

Speech-Driven Tongue Animation

Automated tongue animations that match recorded speech

Kubric: a scalable dataset generator by Google Research

A data generation pipeline for creating semi-realistic synthetic multi-object videos for ML tasks using PyBullet and Blender.

DIRL

Joint alignment of synthetic and real domains for robotics

FairMOT

Object tracking with strong domain generalization capabilities

Showing all 5 results

Contribute Papers/Code to OpenSynthetics

opensynthetics_logo_blue-black 1

Datasets
Papers/Code
Learn