Gaussian Splatting from VGGSfM and Mast3r, and their comparison

VGGSfM: Visual Geometry Grounded Deep Structure From Motion

[RA-L 2024] Fusing deep dense bundle adjustment (DBA) with multi-sensor factor graph optimization.

Any-Feature V-SLAM is an automated visual SLAM library for Monocular cameras capable of switching to a chosen type of feature effortlessly and without manual intervention.

Examples and tutorials on using SOTA computer vision models and techniques. Learn everything from old-school ResNet, through YOLO and object-detection transformers like DETR, to the latest models l…

Spatio-Temporal Metric-Semantic SLAM

a novel real-time model in semantic segmentation

AnyLoc: Universal Visual Place Recognition (RA-L 2023)

The official repository of our ICRA 2024 paper "Stereo-NEC: Enhancing Stereo Visual-Inertial SLAM Initialization with Normal Epipolar Constraints".

[ECCV 2024] Scene as Gaussians for Vision-Based 3D Semantic Occupancy Prediction

[ECCV 2024] MVSGaussian: Fast Generalizable Gaussian Splatting Reconstruction from Multi-View Stereo

Official Repo For "Fast-Poly"

(ICCV 2023) Large Selective Kernel Network for Remote Sensing Object Detection

LSKNet for Remote Sensing Segmentation. This Repo is Based on UNetFormer official GitHub.

Visual Object Tracking

Performance benchmarking for NVIDIA-accelerated Isaac ROS packages

Official implementation of the paper “MagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street Scenes”

Calibrated and Complementary Transformer for RGB-Infrared Object Detection

SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representation

Multi-UAV mission planner for damage zone mapping

Image augmentation for machine learning experiments.

DISO: Direct Imaging Sonar Odometry

ICRA2024 Paper List

Code for near-shore thermal water segmentation on UAVs. Datasets for network training included.

Official implementation of the prototype TinySeg framework presented in the paper "TinySeg: Model Optimizing Framework for Image Segmentation on Tiny Embedded Systems".

RepViT: Revisiting Mobile CNN From ViT Perspective [CVPR 2024] and RepViT-SAM: Towards Real-Time Segmenting Anything

The official repo for [NeurIPS'23] "SAMRS: Scaling-up Remote Sensing Segmentation Dataset with Segment Anything Model"

The official repo for [JSTARS'24] "MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining"

DepthFM: Fast Monocular Depth Estimation with Flow Matching