Just5D
Follow
Stars
Official code for paper "InstantSfM: Fully Sparse and Parallel Structure-from-Motion"
a open framework for blind navigation based on esp32
C++ implementations of PP-OCRv3 and PP-OCRv5 using ncnn for inference.
Detect Anything via Next Point Prediction (Based on Qwen2.5-VL-3B)
ncnn android piper the fast and local neural text-to-speech engine
Code for the paper "Benchmarking pig detection and tracking under diverse and challenging conditions"
This study presents the development and validation of AI models for both nodule detection and cancer classification tasks. This benchmarking across multiple datasets establishes the DLCSD as a reli…
[DEIMv2] Real Time Object Detection Meets DINOv3
[AAAI 2025] GigaGS: Scaling up Planar-Based 3D Gaussians for Large Scene Surface Reconstruction
Prior-guided Gaussian Splatting framework for robust and complete 3D building reconstruction using LoD2 semantic models.
A tool for aligning 3D mesh models to SfM-based coordinates and generating per-view depth and normal maps using raycasting.
MapAnything: Universal Feed-Forward Metric 3D Reconstruction
Official implementation of "LangMamba: A Language-driven Mamba Framework for Low-dose CT Denoising with Vision-language Models" .
[CVPR 2025] ScaleLSD: Scalable Deep Line Segment Detection Streamlined
DT-LSD: Deformable Transformer-based Line Segment Detection [WACV 2025]
IntegraPose, an open-source toolkit for training single, end-to-end models that perform simultaneous behavioral classification and keypoint estimation. IntegraPose leverages YOLO-Pose architectures…
This project provides a complete pipeline to pre-train the backbone of a custom YOLOv11 pose estimation model using knowledge distillation from a powerful DINOv3 vision foundation model.
LIV-Eye: A Low-Cost LiDAR-Inertial-Visual Fusion 3D Sensor for Robotics and Embodied AI.
FAST-LIVO2: Fast, Direct LiDAR-Inertial-Visual Odometry
A Robust Approach for LiDAR-Inertial Odometry Without Sensor-Specific Modelling