-
@lirmm (PhD), RSM team
- Montpellier, France
-
18:33
(UTC +02:00) - in/puglisialessandro
- https://alepuglisi.github.io/
- https://sketchfab.com/AlessandroPuglisi
Lists (21)
Sort Name ascending (A-Z)
3️⃣D Tools
📐3D Reconstruction
3DGS-NeRF
🧠 ML, RL, CV
Calibration
💻 software
courses
👁️ 🔌 MotorCV
hardware control with openCV, visual control🦁 Bio-Logging
🔩 HW-drivers
🌊 Underwater Robot
processing
🤖 ROS2 resources
useful resources for ros2🦾 Robotics and Programming
Semantic
sensors
🐚 Oyster Sim
🧭 SLAM
🎧 Sonar Acoustics
🫧 Underwater Models
📈 Web Sie
Stars
[CVPR'25] DroneSplat: 3D Gaussian Splatting for Robust 3D Reconstruction from In-the-Wild Drone Imagery
[ACM MM 2024] GS3LAM: Gaussian Semantic Splatting SLAM
The implementation of "In-Place Scene Labelling and Understanding with Implicit Scene Representation" [ICCV 2021].
[ECCV 2024] SGS-SLAM: Semantic Gaussian Splatting For Neural Dense SLAM
The source code of GSsplat, a generalizable Gaussian Splatting method for semantic and color synthesis.
[TCSVT 2026] Official implemetation of the paper "Semantic Gaussians: Open-Vocabulary Scene Understanding with 3D Gaussian Splatting".
The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…
MB-System is an open source software package for the processing and display of bathymetry and backscatter imagery data derived from multibeam, interferometry, and sidescan sonars.
GLIM: versatile and extensible point cloud-based 3D localization and mapping framework
Reproducible evaluation of NeRF and 3DGS methods
[CVPR 2024 Highlight] Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields
The official implementation of Segment Any 3D GAussians (AAAI-25)
RViz 2 plugin for live 2D plotting of ROS 2 topic data directly inside RViz.
This code is an extended version of YOLO_ORB_SLAM3, which adds the functionality of creating dense point cloud maps.
Efficient PyTorch Hessian eigendecomposition tools!
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
Website for the University of Michigan Field Robotics Group's AI4Shipwrecks dataset
Code for paper "VkSplat: High-Performance 3DGS Training in Vulkan Compute"
[CVPR 2025] MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors
Reimplementation of LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory