Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

PaddleFormers is an easy-to-use library of pre-trained large language model zoo based on PaddlePaddle.

Easy-to-use and powerful LLM and SLM library with awesome model zoo.

A collaboration friendly studio for NeRFs

The official repository for ERNIE 4.5 and ERNIEKit – its industrial-grade development toolkit based on PaddlePaddle.

Officially maintained, supported by PaddlePaddle, including CV, NLP, Speech, Rec, TS, big models and so on.

All-in-One Development Tool based on PaddlePaddle

High-performance Inference and Deployment Toolkit for LLMs and VLMs based on PaddlePaddle

A pytorch CUDA extension implementation of instant-ngp (sdf and nerf), with a GUI.

SECOND for KITTI/NuScenes object detection

FSL-Mate: A collection of resources for few-shot learning (FSL).

A project demonstrating Lidar related AI solutions, including three GPU accelerated Lidar/camera DL networks (PointPillars, CenterPoint, BEVFusion) and the related libs (cuPCL, 3D SparseConvolution…

PaddleSlim is an open-source library for deep model compression and architecture search.

World's first general purpose 3D object detection codebse.

Rank 1st in the leaderboard of SemanticKITTI semantic segmentation (both single-scan and multi-scan) (Nov. 2020) (CVPR2021 Oral)

Neural Surface reconstruction based on Instant-NGP. Efficient and customizable boilerplate for your research projects. Train NeuS in 10min!

SemanticKITTI API for visualizing dataset, processing data, and evaluating results.

🚀 RocketQA, dense retrieval for information retrieval and question answering, including both Chinese and English state-of-the-art models.

[NeurIPS2021] Code Release of K-Net: Towards Unified Image Segmentation

[ECCV 2022] PillarNet: Real-Time and High-Performance Pillar-based 3D Object Detection

LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs (CVPR 2023)