celesius
Follow
Stars
SuperMap is a living spatial memory for embodied AI — it perceives the world, remembers its evolution, and supports reasoning and action.
Masked Depth Modeling for Spatial Perception
Augmented Monte Carlo Localization - Humanoid Robot
pySLAM is a hybrid Python/C++ Visual SLAM pipeline supporting monocular, stereo, and RGB-D cameras. It provides a broad set of modern local and global feature extractors, multiple loop-closure stra…
This is a ComfyUI plug-in for bytedance/DreamID-V
Spatially-Enhanced Recurrent Units (SRU) - PyTorch Implementation
Reference PyTorch implementation and models for DINOv3
[TPAMI 2026 & NeurIPS 2025] Pixel-Perfect Depth
Real-time Depth Estimation for Jetson Orin
[ICML 2024] 3D-VLA: A 3D Vision-Language-Action Generative World Model
State-of-the-art 2D and 3D Face Analysis Project
LIO-SAM: Tightly-coupled Lidar Inertial Odometry via Smoothing and Mapping
An open source library for face detection in images. The face detection speed can reach 1000FPS.
Hierarchical Reasoning Model Official Release
celesius / HRM
Forked from sapientinc/HRMHierarchical Reasoning Model Official Release
Fisheye or Normal Camera Intrinsic and Extrinsic Calibration. Surround Camera Bird Eye View Generator.
[IEEE RA-L'25] NavRL: Learning Safe Flight in Dynamic Environments (NVIDIA Isaac/Python/ROS1/ROS2)
[RSS 2025] ROMAN: a view-invariant global localization method that matches objects from different robot views for reliable pose estimation even when a scene is observed from opposite views
[ICRA 2025 Best Paper] MAC-VO: Metrics-aware Covariance for Learning-based Stereo Visual Odometry
Motion imitation with deep reinforcement learning.
Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with support for Gymnasium/Gym, NVIDIA Isaac Lab, MuJoCo Playground and other environments
AMP implementation with minimal changes on legged_gym and rsl_rl
Add-on for Blender, provides importing robots from URDF format
Official Repository for "DrEureka: Language Model Guided Sim-To-Real Transfer" (RSS 2024)