Projects sharing features with DensePose

Relativ is an open-source project for the development of custom virtual reality hardware, encompassing the mechanical design, electronics, and software interfaces required to build a headset from scratch. It provides the frameworks necessary for assembling devices using open-source electronics and firmware. The project integrates custom hardware with SteamVR through driver-based configurations, mapping device identifiers and display viewports to ensure rendered images align with physical secondary displays. It employs a combination of microcontroller-based inertial measurement unit polling fo

MMPose is a PyTorch-based pose estimation toolbox and deep learning training pipeline designed for detecting 2D and 3D keypoints on humans, animals, and faces. It serves as a computer vision model zoo and a framework for both 2D pose estimation and 3D pose lifting. The project is distinguished by its modular architecture and extensibility, employing a registry-based system and hierarchical configurations to allow for custom algorithm integration and model pipeline customization. It supports diverse estimation paradigms, including top-down, bottom-up, and two-stage pose lifting workflows. The

Darknet is a low-level neural network engine and framework written in C. It is designed for training and deploying deep learning models, with a primary focus on convolutional neural networks. The project serves as a CUDA accelerated deep learning library that offloads heavy mathematical operations to NVIDIA graphics hardware. This acceleration is used to increase processing speed and reduce execution time during the training of large networks. The engine supports a range of activities including deep learning research, image recognition development, and the training of convolutional neural ne

This project provides a collection of visual guides, technical documentation, and animation generation tools designed to explain the mathematical mechanics of neural network layer operations. It serves as an educational resource for understanding the architecture and data mapping processes involved in deep learning. The toolset distinguishes itself by programmatically generating visual representations of standard, transposed, and dilated convolution layers. By utilizing a declarative configuration model, it maps mathematical parameters—such as kernel sizes, strides, and padding—to coordinate-

This project is a neural network image classifier and a set of tools for building and training convolutional neural networks to recognize and categorize images. It serves as a machine learning educational guide, providing a practical resource for learning neural network fundamentals through an onboarding process. The system includes a dedicated workflow for pretrained model fine-tuning, allowing existing network weights to be adapted to new image categories. This is supported by a transfer learning pipeline that replaces final classification layers and adjusts weights through targeted retrain

Caffe is a high-performance deep learning framework and convolutional neural network library designed for training and deploying neural networks. It functions as a GPU-accelerated machine learning engine with a core implemented in C++ to enable high-throughput tensor operations. The project utilizes a declarative configuration system where model architectures and hyperparameters are defined in external text files, separating the network design from the execution code. It includes a model serialization system to export trained weights and topologies into binary files for efficient deployment a

DeepLabCut is a deep learning toolkit for markerless 2D and 3D animal pose estimation. It functions as a motion tracking system that identifies anatomical keypoints on animals in video sequences without the need for physical markers. The framework utilizes transfer learning and a library of pre-trained weights to accelerate the training of networks for different species. It supports multi-individual identity tracking to maintain unique identities across video sequences and offers real-time pose detection for live video feeds. The system covers a broad range of computer vision capabilities, i

VideoPose3D is a machine learning framework designed for 3D human pose estimation. It functions as a motion reconstruction tool that predicts 3D joint positions from 2D video sequences using a temporal convolutional network to process body movement over time. The project includes a semi-supervised learning pipeline that improves pose accuracy by combining labeled datasets with unlabeled video data and projection consistency loss. It also features a video pose visualizer capable of rendering 3D skeleton reconstructions and 2D keypoints as overlays on original footage. The framework covers the

SAM 3D Objects is a promptable foundation model that recovers 3D objects and human meshes from single images. It converts masked objects in a single photograph into full 3D models with pose, shape, texture, and layout, while also producing complete 3D human body meshes from the same input. The system integrates promptable segmentation to isolate objects and humans before reconstruction, then aligns the independently reconstructed 3D elements into a shared coordinate space. This enables scene-level understanding where multiple 3D reconstructions from the same image coexist in a common coordina

DeepLearningZeroToAll is a comprehensive educational resource and implementation collection focused on deep learning and machine learning. It provides a structured learning path using TensorFlow to move from foundational linear models to complex neural network architectures. The project is distinguished by its practical implementations of various network types, including multilayer perceptrons for logic problems, convolutional neural networks for spatial data and image recognition, and recurrent neural networks using LSTM cells for time-series forecasting and character sequence prediction. It

This project is a machine learning data pipeline designed to automate the collection, curation, and preparation of large-scale image datasets. It functions as an image dataset scraper and computer vision curator, providing the necessary infrastructure to aggregate categorized files from web sources and organize them into structured directories for model development. The system distinguishes itself through a batch-processing architecture that integrates data acquisition with automated integrity validation. By scanning files to remove corrupted or invalid images and applying deterministic parti

This project is a TensorFlow-based supervised text categorizer designed for Chinese natural language processing. It utilizes a hybrid neural network architecture that combines convolutional and recurrent layers to map raw Chinese text to predefined categories. The system integrates convolutional neural networks for local feature extraction and recurrent neural networks for analyzing sequential dependencies. It employs character-level tokenization and word embeddings to represent text as numerical tensors. The implementation covers the end-to-end machine learning pipeline, including text prep

FreeMoCap is an open-source markerless motion capture system that reconstructs 3D human pose from video. It uses a multi-camera setup with ChArUco board calibration to accurately triangulate body landmarks, and it also supports single-camera recording for simpler captures. The system outputs skeleton joint data and generates interactive Jupyter notebooks for each recording, enabling users to explore and analyse motion data directly. Built around hardware-synchronised video capture and MediaPipe-based 2D pose detection, FreeMoCap supports both calibrated multi-camera recording and real-time 2D

This is a comprehensive educational curriculum designed to teach machine learning fundamentals using the Python programming language. It provides a structured course covering the implementation and theory of supervised learning, unsupervised learning, and deep learning. The curriculum is delivered through interactive notebooks that combine executable code with technical tutorials. It includes dedicated guides for building neural network architectures, implementing classification and regression models, and utilizing clustering techniques for pattern discovery in unlabeled data. The materials

This project is a machine learning educational archive and technical documentation collection. It serves as a deep learning tutorial series and implementation guide, providing theoretical explanations and practical walkthroughs for constructing and optimizing neural networks. The content focuses on the design and construction of diverse model architectures, including convolutional neural networks, Long Short-Term Memory networks, and generative adversarial networks. It details specific implementation patterns for autoencoders, sentiment analysis models, and various classification approaches.

Dream Textures is a Stable Diffusion integration for Blender that provides tools for text-to-image generation, depth projection, and node-based processing within a 3D environment. It functions as an AI texture generator capable of producing image textures and concept art from text prompts and scene renders. The system features a depth-to-image projection tool that maps generated imagery onto 3D models using depth data for spatial alignment. It also includes a node-based AI image processor for creating procedural visual effects and a dedicated toolset for AI-assisted inpainting and outpainting

Neural Doodle is a collection of neural network tools designed for image upscaling, texture synthesis, and semantic-guided style transfer between visual inputs. It provides a semantic style transfer engine and an example-based image upscaler that increase image resolution by referencing visual details from a target style example. The project includes a neural texture synthesizer for creating seamless bitmap textures and repeating patterns from a single input style image. It also functions as an image generation tool capable of transforming simple sketches and photos into detailed artwork. Th

This project is a computer vision framework designed for the detection, identification, and tracking of human subjects within video streams. It provides an integrated system for locating individuals, generating biometric models from image datasets, and maintaining identity labels across consecutive video frames. The system distinguishes itself through its ability to maintain identity persistence across multiple camera feeds. By utilizing deep learning inference to extract feature vector embeddings and applying motion prediction algorithms, it links unique identity signatures across disparate

Depth-Anything-3 is a collection of core model implementations for depth prediction, multi-view geometry estimation, and RGB-D spatial pipelines. It includes a monocular depth estimation model for predicting depth maps from single images or video, and a 3D Gaussian splatting generator that predicts parameters to synthesize high-fidelity novel views of a scene. The project provides a multi-view geometry estimator for calculating spatially consistent depth and camera poses across synchronized visual inputs. It also functions as a visual SLAM enhancement tool designed to reduce drift and improve

openMVS is a multi-view stereo library and photogrammetry pipeline used for 3D scene reconstruction. It transforms Structure from Motion data—specifically camera poses and sparse point clouds—into detailed 3D models consisting of dense point clouds and textured meshes. The project provides a sequence of processing stages to densify point clouds, generate 3D surface meshes, and apply photorealistic textures. It uses multi-view texture blending to map accurate colors onto reconstructed geometry and employs iterative refinement to optimize mesh details. The system includes capabilities for impo

Caffe is a high-performance deep learning framework designed for training and deploying deep neural networks. It functions as a machine learning engine and a convolutional neural network library, providing a C++ backend to accelerate computations on both GPUs and CPUs. The system includes a specialized toolset for computer vision, enabling tasks such as object detection, semantic segmentation, and large-scale image retrieval. It supports the deployment of pre-trained models for image and scene recognition, as well as the ability to fine-tune neural network weights for specialized tasks. The

This project provides a collection of practical machine learning code examples, including implementations for supervised, unsupervised, and reinforcement learning algorithms. It features deep learning model implementations for convolutional, recurrent, and generative architectures, alongside specific examples of reinforcement learning agents that maximize rewards in simulated environments. The repository includes dedicated data preprocessing pipelines for sanitization, feature scaling, and dimensionality reduction. It also provides implementations for a wide range of specific models, such as

This project is a collection of structured study notes and notebooks serving as an educational resource for deep learning and neural network fundamentals. It provides a technical reference for implementing machine learning theory, covering everything from basic network design to the construction of advanced architectures. The material specifically focuses on the implementation of convolutional neural networks for computer vision and sequence models for natural language processing. It includes detailed guidance on building object detection systems, face recognition, and speech transcription mo

This project is a static educational website and comprehensive curriculum focused on computer vision and deep learning. It serves as a public repository of instructional materials, lecture notes, and technical guides specifically detailing convolutional neural networks and visual recognition. The site is developed using static-site generation to host course documentation and student project directories. It provides structured academic resources that guide learners through image classification, generative modeling, and the implementation of various neural network architectures. The curriculum

This project is a 3D visual localization framework designed to determine a camera's exact position and orientation by matching 2D image features against a 3D reference model. It includes a structure-from-motion pipeline to reconstruct 3D scene geometry from unordered image sets, creating the necessary spatial maps for localization. The system employs a hierarchical coarse-to-fine localization approach. This process begins with a global-descriptor image retrieval system to identify candidate reference images from a large database and progresses through local feature matching to final 3D model

Code release for ConvNeXt model