Open source IFC library and geometry engine

Official mirror of Blender

Open CASCADE Technology (OCCT) is an open-source software development platform for 3D CAD, CAM, CAE.

A python parametric CAD scripting framework based on OCCT

Official mirror of libredwg. With CI hooks and nightly releases. PR's ok

Python interface to DXF

3D computer vision incuding SLAM，VSALM，Deep Learning，Structured light，Stereo，Three-dimensional reconstruction，Computer vision，Machine Learning and so on

[ACM MM 25] Official repo of "RemoteSAM: Towards Segment Anything for Earth Observation"

Repository for SEN12MS related codes and utilities

[ISPRS2025] SkyEyeGPT: Unifying Remote Sensing Vision-Language Tasks via Instruction Tuning with Large Language Model

GlobalBuildingAtlas: an open global and complete dataset of building polygons, heights and LoD1 3D models

[NeurIPS'25] One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-Resolution

[ICLR 2023 & IJCV 2025] SeaFormer: Squeeze-enhanced Axial Transformer

[AAAI2026 Oral🌟] Towards Open Vocabulary Semantic Segmentation In Remote Sensing.

PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

[NeurIPS 2025 Oral] Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think

We design an effective Relation-Aware Global Attention (RGA) module for CNNs to globally infer the attention.

NeurIPS 2025 Spotlight; ICLR2024 Spotlight; CVPR 2024; EMNLP 2024

A scalable manifold learning (SUDE) method that can cope with large-scale and high-dimensional data in an efficient manner

The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…

LLMs-from-scratch项目中文翻译

Lumina-DiMOO - An Open-Sourced Multi-Modal Large Diffusion Language Model

Official repo for Adaptive Rectangular Convolution

Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024

[CVPR 2025 Oral] SegEarth-OV: Towards Training-Free Open-Vocabulary Segmentation for Remote Sensing Images

SSL-YOLO is a project that employs an auto-supervised approach to pretrain the backbone of the YOLOv8 model using contrastive representation learning, for Few-Shot Object Detection.