Skip to content

Luigi Freda

Robotics & Computer Vision Engineer, PhD

  • Home
  • Research
  • Publications
  • Projects
  • News
  • Blog
  • Teaching
  • Software
  • Links
Computer VisionDeep LearningMachine LearningPerceptionPosts

Hand-Crafted Features or Learned Local Features?

8 April 2017 luigi

In this post, Torsten Sattler presents his upcoming CVPR 2017 paper “Comparative Evaluation of Hand-Crafted and Learned Local Features”

 

You can find the paper and supplementary material at
http://people.inf.ethz.ch/sattlert/publications/Schoenberger2017CVPR.pdf
http://people.inf.ethz.ch/sattlert/publications/Schoenberger2017CVPR-supp.pdf

  • Optimization – why momentum really works
  • CNN-SLAM: Real-time dense monocular SLAM with learned depth prediction

You May Also Like

Stereo ORB-SLAM2 in the EuRoC MAV Dataset

23 April 2016 luigi

Optimization – why momentum really works

4 April 2017 luigi

PLVS code released

30 October 2023 luigi

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.

News About Me

  • RSS 2025 Workshop: Unifying Visual SLAM – From Fragmented Datasets to Scalable, Real-World Solutions
  • A new release of pySLAM is here. Loop-closing, volumetric integration, depth prediction and more improvements.
  • pyslam v2.1 is available
  • PLVS code released
  • slamplay is ready!

Blog

  • The next computer? Your glasses
  • A new release of pySLAM is here. Loop-closing, volumetric integration, depth prediction and more improvements.
  • PLVS code released
  • slamplay is ready!
  • 3DMR – 3D Multi-Robot Exploration with a Two-Level Coordination Strategy and Prioritization

Tags

2D to 3D 3D reconstruction augmented reality business CNN computer vision data analysis dataset deep learning disaster robotics drones energy features gps image processig inertial lidar machine learning mapping math multi-robot NN open source perception place recognition robotics self-driving car sensor-based motion planning sensors SLAM TRADR UGVs USAR visual localization visual servoing VR

Tweets

Retweet on Twitter Luigi Freda Retweeted
franorajic Frano Rajič @franorajic ·
29 Aug

1/4 🚀 We’re excited to release MVTracker (ICCV 2025 Oral), the first data-driven multi-view 3D point tracker. MVTracker tracks arbitrary 3D points across multiple cameras, handling occlusions and varied camera setups without per-sequence optimization.

Reply on Twitter 1961406140526256353 Retweet on Twitter 1961406140526256353 48 Like on Twitter 1961406140526256353 335 Twitter 1961406140526256353
Retweet on Twitter Luigi Freda Retweeted
almorgand Alexandre Morgand @almorgand ·
28 Aug

"Pixie: Physics from Pixels"

TL;DR: NeRF, GS w/ physics; neural network mapping pretrained visual features (i.e., CLIP) to dense material fields of physical properties in a single forward pass, enabling real‑time physics simulations.

Reply on Twitter 1961076683093524561 Retweet on Twitter 1961076683093524561 13 Like on Twitter 1961076683093524561 96 Twitter 1961076683093524561
Load More

Meta

  • Log in
  • Entries RSS
Copyright © 2025 Luigi Freda. All rights reserved.
Theme: ColorMag by ThemeGrill. Powered by WordPress.