Projects sharing features with Neural Renderer

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

GET3D is a generative 3D mesh model and rendering framework designed to synthesize high-quality textured shapes and tetrahedral meshes. It functions as an image-to-3D reconstructor and text-to-3D generator, utilizing a differentiable 3D renderer to produce realistic visual perspectives and material effects. The system enables the creation of 3D assets from single 2D images, point clouds, or descriptive text prompts. It features a latent space interpolator for creating smooth transitions between different 3D objects and supports the independent control of geometry and texture. The project cov

InstantMesh is a neural 3D reconstruction tool and single-image 3D mesh generator. It utilizes a sparse-view large reconstruction model to convert a single two-dimensional image into a three-dimensional object mesh. The system functions as a textured 3D mesh exporter, saving generated objects with either vertex colors or full texture maps for use in external rendering software. The framework covers a range of capabilities including feed-forward geometry inference, single-image depth estimation, and neural radiance fields. It also supports differentiable mesh rendering and workflows for spars

Nerfstudio is a modular development framework for training, visualizing, and exporting three-dimensional scene representations derived from two-dimensional image datasets. It provides a neural scene reconstruction pipeline that converts raw images and camera data into high-fidelity 3D assets and cinematic video using a differentiable volumetric renderer. The system features an interactive web-based visualizer that allows users to monitor training progress and inspect neural scene geometry in real time. It decouples neural network architectures from the training loop through a standardized mod

This project is a PyTorch-based Chinese text classification framework. It provides a transformer-based pipeline designed to categorize Chinese language sequences into predefined labels using deep learning models. The implementation supports both BERT and ERNIE language models for processing and tagging complex Chinese text. These models are used to perform tasks such as sentiment analysis and general text categorization. The system utilizes transformer-based text encoding and attention-weighted sequence pooling to convert raw characters into document vectors. It employs pre-trained model fin

This project is a PyTorch-based framework and implementation suite for the supervised classification of Chinese text. It serves as a deep learning text classifier designed to automate the process of labeling and organizing Chinese language documents into predefined categories. The framework provides a collection of neural network architectures, including TextCNN, Transformer, and FastText. It allows for the selection and prototyping of different model topologies through a modular implementation, enabling the evaluation of various sequence models on specific datasets. The system covers a full

This is a PyTorch object detection framework that implements the Single Shot MultiBox Detector for identifying and localizing multiple objects within images and video. The project provides a neural network architecture designed for single-shot object detection, which predicts bounding boxes and class labels in one pass. The implementation includes a real-time object detector capable of processing live video streams to track and label objects across sequential frames. It also features a complete computer vision training pipeline for preparing image datasets and training model weights. The fra

This project is a PyTorch implementation of the Faster R-CNN architecture for object detection. It provides a framework for identifying multiple object classes and their corresponding bounding boxes within images using a deep learning system. The implementation includes a training pipeline for optimizing models on custom datasets and a utility for converting pretrained weights from external formats into a compatible structure for model initialization. The system covers a two-stage detection pipeline comprising a region proposal network and an ROI pooling layer. It incorporates multi-task los

This project is a PyTorch implementation of the YOLOv3 object detection architecture. It functions as a real-time object detector and computer vision framework designed to identify and locate multiple objects within images using bounding boxes and class labels. The system allows for both the use of pretrained weights for immediate image analysis and the training of custom models using datasets with bounding box annotations. It provides a programmatic interface to integrate detection capabilities directly into other software applications. The framework includes tools for model evaluation to m

This project is an educational implementation of a small-scale generative pre-trained transformer designed to teach the fundamentals of neural network architecture and training. It serves as a reference implementation and tutorial for constructing a text-generating neural network from scratch. The codebase demonstrates the mechanics of tokenization, self-attention, and the construction of a lightweight language model. It focuses on the step-by-step process of building a generative model to illustrate how large language models are constructed. The implementation covers transformer-based archi

This project is a PyTorch implementation of a research architecture designed for high-resolution representation learning. It serves as a computer vision framework focused on precise keypoint detection, human pose estimation, and semantic image segmentation. The implementation provides specialized tools for identifying anatomical landmarks on the human body and predicting facial keypoint coordinates to analyze orientation and alignment. It utilizes a system of multi-resolution parallel streams and repeated multi-scale fusion to maintain high-resolution representations throughout the network.

gpt-fast is a PyTorch transformer inference engine designed for text generation using a native tensor library implementation. It provides a runtime for executing large language models without the need for external C++ extensions. The project implements speculative decoding to accelerate generation by using a small draft model for token prediction and a larger model for verification. It further optimizes performance through a compiled prefill stage and a multi-GPU tensor parallelism library that shards linear layers across multiple graphics processing units. Memory efficiency is managed throu

gpt-fast is a PyTorch transformer inference engine designed for low-latency text generation. It functions as a distributed GPU inference library, a quantized model runner, and a speculative decoding framework. The system utilizes a speculative decoding workflow where a small draft model predicts token sequences for verification by a larger model to accelerate generation. It supports quantized model execution to reduce memory footprint and implements tensor parallelism to split computations across multiple GPUs. The project includes a standardized evaluation harness to measure the accuracy an

GraphTransformerNetworks is a graph neural network framework implemented in PyTorch for learning structural representations and performing classification tasks on complex heterogeneous graphs and relational networks. The project provides automated preprocessing pipelines to transform raw graph datasets into standardized formats, alongside model training, forward passes, and gradient backpropagation executed through dynamic tensor operations. The architecture incorporates self-attention mechanisms applied directly to graph structures to learn contextual representations of nodes and edges ac

Tensor-Puzzles is an educational exercise suite and numerical computing tutorial designed for mastering tensor operations and broadcasting rules within PyTorch. It functions as an implementation trainer where users practice transitioning mathematical formulas into code by reimplementing deep learning mathematical primitives. The project utilizes a constraint-based exercise suite that restricts available library calls to force the use of specific tensor primitives. These challenges are structured as sequential puzzles that require users to solve tasks using a modular implementation pattern, wh

This project is a PyTorch implementation of the EfficientDet architecture designed for real-time object detection. It provides a neural network and inference engine capable of identifying and locating multiple objects within images or video streams. The implementation includes pretrained computer vision models with optimized weights, enabling immediate inference and fine-tuning without the need for training from scratch. The project covers the full pipeline for computer vision model optimization, including custom object detection training and model weight optimization. It incorporates struct

Shap-E is a generative 3D modeling system that creates three-dimensional digital assets from natural language descriptions or two-dimensional images. It functions as a generative model capable of producing three-dimensional implicit functions and assets. The project includes a 3D latent encoder that converts trimeshes and 3D models into latent representations using point clouds and multiview renders. It utilizes an image-to-3D generator to produce assets from synthetic view images and a text-to-3D generator to build shapes from text prompts. The system implements a pipeline involving latent

sam-3d-body is a machine learning framework for 3D human mesh recovery and pose estimation. It utilizes a 3D human mesh recovery model to reconstruct full-body meshes, including the body, hands, and feet, from a single image. The project implements a specialized extension of the Segment Anything Model to guide the extraction and refinement of human body shapes. This integration allows for prompt-guided mesh recovery, where 2D masks and keypoints constrain the inference of 3D pose and shape parameters. The system covers a range of computer vision capabilities, including 3D spatial alignment t

This project is a deep learning computer vision library designed for video action recognition. It provides a framework for training and evaluating neural networks that identify and categorize human activities within recorded footage by processing temporal sequences of frames. The library focuses on the implementation of three-dimensional neural network architectures, specifically utilizing three-dimensional convolutional layers to capture both spatial and temporal patterns. By aggregating features across consecutive frame sequences, the models learn to represent the evolution of actions over

This is an educational implementation that builds a generative pre-trained transformer (GPT) language model from scratch using PyTorch. The project is structured as a step-by-step tutorial, walking through the construction of a decoder-only transformer architecture and its training loop with clean git commits and an accompanying video lecture for a hands-on learning experience. What sets this implementation apart is its focus on practical reproduction: it provides a workflow to train a 124-million-parameter model from scratch in about one hour on cloud GPU hardware, costing under ten dollars.

This project is a pretrained model library for PyTorch, providing a collection of convolutional neural network architectures and weights. It serves as a computer vision model zoo for image classification and feature extraction, offering a framework for transfer learning where pretrained networks are adapted for custom image recognition tasks. The library focuses on transforming images into high-level numerical representations and calculating class probability scores. It includes utilities for downloading and initializing standard architectures such as ResNet, Inception, and Xception. Capabil

This project is a collection of neural network models and geometric tools designed for image feature matching, spatial alignment, and visual localization. It provides a pre-trained neural network model for identifying high-accuracy correspondences between sparse image features without requiring local training. The system utilizes a graph neural network matcher that employs attention mechanisms and message passing to learn spatial relationships between image feature points. It integrates a RANSAC camera pose estimator to filter feature matches and calculate the relative spatial transformation

MathUtilities is a collection of specialized toolkits providing engines for geometry, computer vision, mathematics, physics simulation, and signal processing. It functions as a comprehensive mathematics and physics library focused on linear algebra, numerical optimization, and geometric calculations for technical applications. The project distinguishes itself through a physics simulation toolkit and a 3D geometry engine. These provide capabilities for Verlet integration, iterative inverse kinematics solvers, distance field rendering via volumetric raymarching, and mesh geometry deformation. I

openMVG is a computer vision geometry library and toolkit for multiple view geometry. It serves as a framework for structure from motion and 3D scene reconstruction, providing the tools necessary to recover 3D point clouds and camera poses from collections of 2D images. The library implements both global and incremental structure-from-motion pipelines. It uses geometric algorithms to calculate camera pose estimation and image localization, employing Levenberg-Marquardt bundle adjustment to refine 3D coordinates and camera parameters by minimizing reprojection error. The project covers a broa

pygcn is a PyTorch library and framework for implementing graph convolutional networks. It provides tools for semi-supervised node classification and the generation of node embeddings from graph-structured data. The system converts graph nodes into low-dimensional vectors based on neighborhood patterns and local similarities. It enables the prediction of node labels by leveraging both a small set of labeled examples and the overall graph topology. The library covers relational data analysis and semi-supervised graph learning. It includes computational primitives for message passing, adjacenc

MultiNeRF is a 3D scene reconstruction suite and framework for training Neural Radiance Fields to synthesize novel views from sets of 2D images. It provides a system for generating new perspectives of a scene by optimizing a neural network based on images and camera poses. The toolkit includes research implementations such as Mip-NeRF 360 and Ref-NeRF for high-fidelity volumetric rendering. It features a structure-from-motion pipeline to calculate camera positions and orientations from image datasets to prepare data for training. The project covers a full workflow for volumetric rendering, i

This project is a computer vision system for monocular depth estimation and 3D point cloud generation. It provides a supervised depth learning framework and a depth predictor capable of estimating spatial distance and disparity from single 2D images using pretrained neural networks. The system includes tools to transform 2D depth images into 3D point clouds via pixel coordinate backprojection and converts 3D point cloud data into 2D depth maps. It utilizes a training pipeline that supports model fine-tuning and hyperparameter optimization. The library covers broader capabilities in spatial a