Stars
Mask3D predicts accurate 3D semantic instances achieving state-of-the-art on ScanNet, ScanNet200, S3DIS and STPLS3D.
[CVPR2024] OneFormer3D: One Transformer for Unified Point Cloud Segmentation
[ICLR 2025] Point-SAM: Promptable 3D Segmentation Model for Point Clouds
A comprehensive list of papers using large language/multi-modal models for Robotics/RL, including papers, codes, and related websites
[Lumina Embodied AI Community] 具身智能技术指南 Embodied-AI-Guide
This is a repository for listing papers on scene graph generation and application.
A curated list of state-of-the-art research in embodied AI, focusing on vision-language-action (VLA) models, vision-language navigation (VLN), and related multimodal learning approaches.
Lumina Robotics Talent Call | Lumina社区具身智能招贤榜 | A list for Embodied AI / Robotics Jobs (PhD, RA, intern, full-time, etc
OmniGibson: a platform for accelerating Embodied AI research built upon NVIDIA's Omniverse engine. Join our Discord for support: https://discord.gg/bccR5vGFEx
[ICLR 2025, Oral] EmbodiedSAM: Online Segment Any 3D Thing in Real Time
A flexible, high-performance 3D simulator for Embodied AI research.
ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation
Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything
Official implementation of ECCV24 paper "SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding"
This repo contains a curative list of scene change detection(SCD), including papers, videos, codes, and related websites.
本项目将《动手学深度学习》(Dive into Deep Learning)原书中的MXNet实现改为PyTorch实现。
《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。
Dynamic 3D Gaussian Scene Graphs for Environment Adaptation
SAPIEN Manipulation Skill Framework, an open source GPU parallelized robotics simulator and benchmark, led by Hillbot, Inc.
Language-Grounded Dynamic Scene Graphs for Interactive Object Search with Mobile Manipulation. Project website: http://moma-llm.cs.uni-freiburg.de
[CoRL 2024] RoboEXP: Action-Conditioned Scene Graph via Interactive Exploration for Robotic Manipulation
A Simulation Environment to train Robots in Large Realistic Interactive Scenes
This is a curated list for Information Bottleneck Principle, in memory of Professor Naftali Tishby.
A Robust and Versatile Monocular Visual-Inertial State Estimator