Projects sharing features with Sapiens

AlphaPose is a deep learning pose estimation framework and PyTorch computer vision library designed for detecting and tracking human body, face, hand, and foot keypoints in images and videos. It provides a system for skeletal posture estimation and multi-person pose tracking. The project implements tools for three-dimensional human pose reconstruction, generating joint positions and body mesh shapes from two-dimensional image data. It also includes a multi-person pose tracker capable of maintaining the identity of multiple people across consecutive video frames. The framework covers a broad

Gluon-CV is an MXNet computer vision library that provides a comprehensive collection of pre-implemented vision architectures and training pipelines. It serves as a deep learning research toolkit and a model zoo containing state-of-the-art pre-trained weights for image and video analysis. The project includes a specialized human pose estimation library and a model compression toolkit. These tools allow for the pruning and quantization of deep learning models to increase inference speed and facilitate deployment on constrained edge hardware. The library covers a broad range of vision capabili

DeepCTR is a specialized software framework and deep learning model library designed for predicting click-through rates and implementing recommendation systems. It provides a suite of tabular data models and architectures tailored for binary classification and sparse feature processing. The framework includes dedicated toolkits for multi-task learning and sequential interest modeling. It allows for the simultaneous estimation of multiple related targets through shared-bottom and gated expert neural networks, while capturing evolving user behavior using attention mechanisms and transformers.

This project is a research framework and toolkit designed for training large-scale vision transformers and multimodal language models. It provides a comprehensive suite for vision-language pretraining, enabling the development of models that map images and text into shared latent spaces. The framework is distinguished by its capabilities in high-fidelity image generation and multimodal research, utilizing normalizing flows and variational autoencoders to produce images from text prompts or class labels. It supports the development of both generative and contrastive models, allowing for a wide

This is an image segmentation framework and masking toolkit for constructing binary and multi-class neural network architectures. It serves as a deep learning encoder wrapper that integrates pre-trained convolutional neural network architectures into semantic segmentation models. The library enables the use of pre-trained backbones to isolate complex patterns and leverages transfer learning to accelerate training. It provides a collection of overlap-based loss functions and precision metrics specifically designed to evaluate and refine the accuracy of image masks. The toolkit covers the full

PaddleDetection is an object detection framework designed for the end-to-end development, training, and deployment of computer vision models. It provides a comprehensive library of modular neural network architectures and pipelines that support object detection, instance segmentation, and multi-object tracking tasks. The project distinguishes itself through a configuration-driven approach that decouples model components like backbones and heads, allowing for the flexible assembly of custom vision workflows. It incorporates advanced techniques such as anchor-free detection logic, joint detecti

HigherHRNet is a deep learning framework designed for bottom-up human pose estimation. It functions as a computer vision keypoint detector that identifies and tracks human body joints by utilizing high-resolution feature pyramids and scale-aware representation learning. The project distinguishes itself through a bottom-up approach, which identifies individual body parts across an entire image before clustering them into distinct human skeletons. This methodology is supported by multi-resolution feature fusion, which maintains high-resolution representations throughout the network by repeatedl

MiDaS is a PyTorch computer vision library and monocular depth estimation model designed to predict scene depth from single images. It functions as a scene depth predictor that computes distance maps to determine object proximity to the camera. The project enables zero-shot depth transfer, allowing the model to be applied to new datasets or environments without additional training data. It focuses on relative depth regression to predict scale-invariant depth maps. The library includes a real-time depth visualizer for capturing live camera feeds and displaying corresponding depth maps. It als

This project is a self-supervised vision foundation model based on a vision transformer architecture. It is designed to learn dense visual representations from unlabeled images, serving as a general-purpose backbone for a wide variety of downstream vision tasks. The system is distinguished by its use of self-distillation and masked image modeling to extract semantic and geometric features. It also incorporates an image-text alignment model that maps visual embeddings to textual descriptions, enabling zero-shot image recognition, zero-shot segmentation, and cross-modal retrieval. The project

This project is a PyTorch vision transformer framework designed for self-supervised learning. It implements a model that trains visual representations using a momentum teacher and self-distillation without the need for labeled data. The library functions as an image feature extractor and visual attention visualizer, allowing for the generation of high-dimensional vectors and the rendering of self-attention maps as heatmaps or videos to analyze model focus. It provides comprehensive tools for downstream vision evaluation, including linear probe classification, k-nearest neighbor categorizatio

DeiT is a PyTorch vision transformer framework designed for image classification. It implements a transformer-based architecture that processes images as sequences of flattened patches using self-attention layers and position-aware sequence modeling instead of convolutional filters. The project focuses on data-efficient training through a knowledge distillation framework. This system allows a student model to mimic the soft labels of a high-performance teacher model to improve accuracy and generalization, particularly when training on smaller datasets. The library covers the full development

The Intel RealSense SDK is a software development kit providing drivers and libraries for interfacing with depth cameras to capture color, depth, and infrared data streams. It includes a depth camera driver for device discovery and sensor configuration, a stereo vision library for computing depth maps and aligning frames, and a 3D point cloud generator to transform depth and infrared frames into spatial representations. The SDK distinguishes itself through on-chip depth calculation and stereo calibration, using internal vision processors to reduce host CPU load. It supports hardware-level str

This project is a speech recognition and translation engine that utilizes a sequence-to-sequence transformer architecture to convert audio into text. It is built upon a weakly supervised learning framework, which leverages large-scale, unlabelled audio-transcript data to create generalized speech representations capable of performing simultaneous transcription, language identification, and translation. The system distinguishes itself through a unified multi-task modeling approach that shares token sequences across different objectives, allowing it to handle diverse languages and vocabularies

Swin-Transformer is a deep learning framework designed for training and deploying hierarchical vision transformer models. It serves as a research library and toolkit for computer vision tasks, providing the infrastructure to build models that replace standard convolution operations with sliding window self-attention mechanisms. By utilizing a multi-scale feature hierarchy, the framework enables the processing of visual data at varying resolutions and spatial scales. The project distinguishes itself through its implementation of shifted window partitioning, which facilitates global information

This project is a research library and toolkit for deep learning computer vision, focused on implementing transformer and mixer-based architectures for image classification. It processes visual data by converting images into sequences of patches, allowing standard attention mechanisms to capture global dependencies without relying on traditional convolutional operations. The framework distinguishes itself through its support for multimodal embedding analysis, which maps images and text into a shared latent vector space. This capability enables zero-shot classification and cross-modal retrieva

OpenPose is a real-time pose estimation engine designed to detect and track human body, face, hand, and foot landmarks. It functions as a multi-person motion tracker, identifying the spatial coordinates of multiple individuals simultaneously within video streams or static images. Beyond two-dimensional detection, the software acts as a three-dimensional kinematics processor, reconstructing spatial movement data from single or multiple synchronized camera perspectives. The system distinguishes itself through a bottom-up approach that utilizes part-affinity fields to associate body parts across

DAIN is a video frame synthesis engine and AI video upsampling tool designed to increase video playback smoothness. It functions as a computer vision model that synthesizes intermediate frames between existing images to transform low frame rate video into high frame rate content. The system utilizes depth-aware video frame interpolation to predict the motion of pixels between consecutive images. By analyzing spatial depth via depth maps, the tool generates new frames that account for occlusions and overlapping objects to create slow motion effects. The framework incorporates optical flow int

PointNet++ is a deep learning framework designed for processing and classifying 3D point cloud data. It utilizes a hierarchical feature learning architecture to extract geometric patterns from sampled 3D point sets. The framework implements a variety of 3D analysis tools, including a point cloud classifier for categorizing objects based on spatial coordinates and surface normals, a semantic scene segmenter for labeling surfaces in large-scale environments, and a tool for 3D object part segmentation. The system covers a broad range of capabilities including geometric feature extraction, 3D da

Depth-Anything is a monocular depth estimation foundation model that produces dense per-pixel depth maps from a single RGB image. It is built on a DINOv2 Vision Transformer encoder backbone and trained on 62 million unlabeled images using a teacher-student pseudo-labeling framework, enabling robust generalization across diverse scenes without task-specific training. The model outputs both relative depth maps, which capture the ordering of scene points, and metric depth maps with real-world units after fine-tuning on datasets like NYUv2 or KITTI. The project distinguishes itself through its ab

This project is a distributed machine learning platform and sparse deep learning framework designed for training and serving models with high-dimensional sparse data. It functions as an online model serving infrastructure and recommendation system engine, enabling real-time item retrieval and scoring using deep tree matching and neural networks. The system distinguishes itself through a multi-task learning framework that optimizes multiple objective functions within a shared representation space. It features a specialized online serving infrastructure that supports dynamic model hot-loading a

SegFormer is a semantic segmentation framework and transformer-based model designed for pixel-level image classification. It provides a deep learning architecture that assigns class labels to pixels using a hierarchical transformer encoder and a multi-layer perceptron decoder. The framework utilizes a hierarchical transformer encoder to process multi-scale features through a pyramid of blocks and an all-MLP decoder to aggregate these features without complex attention mechanisms. It incorporates overlap patch embedding to preserve local continuity and sequential self-attention reduction to ma

This is a PyTorch library and framework for self-supervised vision learning. It provides an implementation of masked autoencoders and vision transformers designed to learn image representations by reconstructing masked image patches from unlabeled data. The project features a distributed training pipeline that scales workloads across multiple GPU nodes. This infrastructure includes multi-node orchestration and gradient accumulation to manage large batch sizes and coordinate resource requests across clusters. The toolkit covers a complete workflow from self-supervised masked pre-training to d

PointNet is a deep learning architecture designed to process and classify raw 3D point clouds directly without voxelization. It provides a system for 3D object classification, semantic segmentation frameworks for partitioning clouds into categories, and tools for visualizing 3D shapes. The project utilizes a transform network to align point clouds into a canonical coordinate space and employs symmetric-function-based aggregation to condense point-wise features into global vectors regardless of point order. It also features a multi-scale grouping architecture to extract hierarchical geometric

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

x-transformers is a PyTorch library and research toolkit for building transformer architectures. It provides a modular framework for implementing experimental transformer research, including a suite of advanced attention mechanisms, long-sequence modeling tools, and a framework for vision transformers. The project is distinguished by its focus on memory-efficient and high-performance components, such as Flash Attention with tiled kernels and multi-query attention. It also implements specialized methods for extending context windows, including sequence recurrence and rotary positional embeddin

This is a machine learning framework for treating diverse natural language processing tasks as a unified text-to-text problem. It provides a toolkit for pre-training and fine-tuning large-scale transformer models, utilizing a system where both inputs and outputs are formatted as raw text sequences. The framework is distinguished by its distributed training system, which uses mesh-based strategies to scale model weights and training batches across multiple TPU cores. It supports multi-task learning by combining diverse datasets into a single training stream using configurable mixture rates, al

ComfyUI-3D-Pack is a suite of custom nodes for ComfyUI that enables 3D asset generation and rendering within a node-based workflow. It provides a set of tools for reconstructing textured three-dimensional meshes and volumetric scenes from single images, multi-view images, or text prompts. The system includes a Gaussian splatting generator for creating high-fidelity volumetric 3D scene representations and a multi-view image generator to produce consistent image sets for reconstruction. It also features a single image 3D mesh tool to build geometry from a single 2D source. The toolset covers 3