Lists (4)
Stars
Llama中文社区，实时汇总最新Llama学习资料，构建最好的中文Llama大模型开源生态，完全开源可商用
ICRA2025: OpenGS-SLAM: Open-Set Dense Semantic SLAM with 3D Gaussian Splatting for Object-Level Scene Understanding
[NeurIPS 2024] DG-SLAM: Robust Dynamic Gaussian Splatting SLAM with Hybrid Pose Optimization
This is a repository for listing papers on scene graph generation and application.
[T-RO 2025] SG-Reg: Generalizable and Efficient Scene Graph Registration
🌳 [ICRA'25] Hier-SLAM: Semantic Gaussian Splatting SLAM with Hierarchical Categorical Representation
[ICLR 2025 (Oral 📢) ] Our OpenYOLO3D model achieves state-of-the-art performance in Open Vocabulary 3D Instance Segmentation on ScanNet200 and Replica datasets with up ∼16x speedup compared to the …
SpatialLM: Large Language Model for Spatial Understanding
HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model
Leveraging Semantic Graphs for Efficient and Robust LiDAR SLAM
[CVPR 2024] 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering
Frontier Multimodal Foundation Models for Image and Video Understanding
[ICRA 2025] ELite: Ephemerality meets LiDAR-based Lifelong Mapping
[IROS '24] Volumetric Mapping with Panoptic Refinement using Kernel Density Estimation for Mobile Robots
[ICRA 2024 Oral] Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation
[RA-L] Lost & Found dynamically tracks object poses from egocentric videos while updating a scene graph, enabling richer semantic 3D understanding for robotic downstream tasks.
A flexible submap-based framework towards spatio-temporally consistent volumetric mapping and scene understanding.
Official implementation of the paper "HUGSIM: A Real-Time, Photo-Realistic and Closed-Loop Simulator for Autonomous Driving"
Vision-Language Navigation Benchmark in Isaac Lab
Integrate the DeepSeek API into popular softwares
(Supports DeepSeek R1) An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models.