First publicly accessible labeled multi-modal perception dataset for autonomous maritime navigation, focusing on in-water obstacles within the aquatic environment

Official repository for USVTrack dataset

Code for CoGF-Depth: A Convolution Guided Fusion Model for Monocular Depth Estimation

Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.

[ECCV 2022 Oral] OpenLane: Large-scale Realistic 3D Lane Dataset

Stitching and fusion of 4 pairs of on-board surround view fisheye image sequences, odometer estimation and output of large pixel maps.

[AAAI 2026] Empowering DINO Representations for Underwater Instance Segmentation via Aligner and Prompter

ACCO:Is Discretization Fusion All You Need for Collaborative Perception?

[ICCV 2025] RoCo-Sim: Enhancing Roadside Collaborative Perception through Foreground Simulation

[ICLR2024] HEAL: An Extensible Framework for Open Heterogeneous Collaborative Perception ➡️ All You Need for Multi-Modality Collaborative Perception!

谷歌推出25天AI Agents课程，作为 2025 年最昂贵圣诞节礼物！

Zero-shot Object Counting with Good Exemplars[ECCV 2024]

Official code for ECCV 2024 Robust Zero-Shot Crowd Counting and Localization With Adaptive Resolution SAM

Effortless data labeling with AI support from Segment Anything and other awesome models.

Reference PyTorch implementation and models for DINOv3

Ethereal Style for Zotero

Jupyter notebook tutorials for MMSegmentation

LSNet: See Large, Focus Small [CVPR 2025]

[CVPR 2025] Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Video

RK3588 IMX296 camera driver, using V4L2 to replace GStream to directly acquire images.

RK3588 camera image acquisition, object detection and image display

rk3588 various solutions for reading camera and video files

Matrix multiplication on the NPU inside RK3588

opencv调用jetson/rk3588 mpp硬解码，重写了open与read函数，支持h264/h265