hobincar
Follow
Stars
A unified interface to many trajectory forecasting datasets.
🔥🔥🔥Latest Papers, Codes and Datasets on Vid-LLMs.
[CVPR 2024] Real-Time Open-Vocabulary Object Detection
VisionLLaMA: A Unified LLaMA Backbone for Vision Tasks
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
Get up and running with Llama 3.1, Mistral, Gemma 2, and other large language models.
A JAX-based simulator for autonomous driving research.
SAM-PT: Extending SAM to zero-shot video segmentation with point-based tracking.
[CVPR'23] Universal Instance Perception as Object Discovery and Retrieval
DVIS: Decoupled Video Instance Segmentation Framework
Next-generation Video instance recognition framework on top of Detectron2 which supports InstMove (CVPR 2023), SeqFormer(ECCV Oral), and IDOL(ECCV Oral))
The official implementation of the CVPR2023 paper titled “Neural Map Prior for Autonomous Driving”.
[ICLR'23 Spotlight] MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction
A general map auto annotation framework based on MapTR, with high flexibility in terms of spatial scale and element type
A curated list of video object segmentation (vos) papers, datasets, and projects.
A list of video object segmentation (VOS) papers
Mid-Level Rust Bindings to the C API for Microsoft's ONNX Runtime
Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything
[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"
SAM with text prompt
A Python package for segmenting geospatial data with the Segment Anything Model (SAM)
[CVPR'23 Best Paper Award] Planning-oriented Autonomous Driving
The open-source tool for building high-quality datasets and computer vision models