Lists (1)
Stars
[CVPR 2025] Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass
GenZ-ICP: SOTA robust LiDAR odometry (IEEE RA-L 2025)
Fisheye-Calib-Adapter: An Easy Tool for Fisheye Camera Model Conversion
A geometry-shader-based, global CUDA sorted high-performance 3D Gaussian Splatting rasterizer. Can achieve a 5-10x speedup in rendering compared to the vanialla diff-gaussian-rasterization.
Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive arch…
Agent Framework / shim to use Pydantic with LLMs
Immutable development environments for PyTorch powered by Visual Studio Code Dev Containers
[TMECH'2024] Official codes of ”PALoc: Advancing SLAM Benchmarking with Prior-Assisted 6-DoF Trajectory Generation and Uncertainty Estimation“
For an education purpose, from-scratch, single-file, python-only pose-graph optimization implementation
Public code release associated with SceneScript.
Python code to fuse multiple RGB-D images into a TSDF voxel volume.
Code for "CMRNet: Camera to LiDAR-Map Registration" (ITSC 2019)
ai-forever / gigachain
Forked from langchain-ai/langchain⚡ Набор решений для разработки LLM-приложений на русском языке с поддержкой GigaChat ⚡
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
Flexible and powerful framework for managing multiple AI agents and handling complex conversations
[NeurIPS'24] NeuRodin: A Two-stage Framework for High-Fidelity Neural Surface Reconstruction
[3DV 2025, Oral] LoopSplat: Loop Closure by Registering 3D Gaussian Splats
yu-i-i / overleaf-cep
Forked from overleaf/overleafA web-based collaborative LaTeX editor (CE extended with free premium features)
Free LDAP and OAuth2 Authentication and Authorisation for Sharelatex / Overleaf (Community Edition)
Official code of the paper LABRAD-OR: Lightweight Memory Scene Graphs for Accurate Bimodal Reasoning in Dynamic Operating Rooms accepted at MICCAI 2023.
HyDE: Precise Zero-Shot Dense Retrieval without Relevance Labels
This is an implementation of the paper: Searching for Best Practices in Retrieval-Augmented Generation (EMNLP2024)
The Open Source Memory Layer For Autonomous Agents
[CVPR 2024] Code for HiKER-SGG: Hierarchical Knowledge Enhanced Robust Scene Graph Generation
[CVPR 2024] Memory-based Adapters for Online 3D Scene Perception
Python library to work with ConceptNet offline without the need for PostgreSQL
Semantic cache for LLMs. Fully integrated with LangChain and llama_index.