A Self-Driving Fleet Arrives in Pittsburgh This Month – Uber Steps on the Accelerator
Uber is definitely stepping on the accelerator… “Starting later this month, Uber will allow customers in downtown Pittsburgh to summon
Read more
Luigi Freda
Computer Vision, AI, Robotics Engineer, PhD
computer vision
Direct Sparse Odometry
A new exciting work from the Computer Vision Group of TUM. “DSO is a novel direct and sparse formulation for
Read more
Event Camera SLAM
The slamcore start-up is pioneering breaktrough new algorithms for accurate and robust real-time event camera motion tracking and scene reconstruction
Read more
Hierarchical Progressive Multiview Stereo
Progressive multiview stero is an implementation of an algorihm taking a sparse 3D model (result of structure from motion software)
Read more
High-Performance and Tunable Stereo Reconstruction
In this work, Researchers of MIT present an high-performance and tunable stereo disparity estimation method. It succeeds to reach a
Read more
Robotic Laundry
How about asking your robot to make a complete laundry cycle?…PR2 seems almost there. See more on this page.
Read more
Deep Reinforcement Learning: from Pong Pixels to a Learned Player
Here you can find a fantastic post on reinforcement learning by Andrej Karpathy. The Author explains how it is possible
Read more
Probabilistic Volumetric Reconstruction using Ray Potentials
From the webpage of the project “This paper presents a novel probabilistic foundation for volumetric 3-d reconstruction. We formulate the problem as
Read more
Active Volumetric 3D Reconstruction
A new open-source library has been released by the Robotics and Perception Group of Davide Scaramuzza. Technical details of the
Read more
Itseez Acquired by Intel
OpenCV originated at Intel, and is now back at Intel. People wonder about the possibility that OpenCV can stop beeing
Read more
Google Tensor Processing Units (TPUs)
Google revealed the TPU (Tensor Processing Unit), a custom ASIC designed and built specifically for machine learning applications.
Read more
Hyper-Reality
“Hyper-Reality (total runtime approx 6 minutes) is a concept film by Keiichi Matsuda. It presents a provocative and kaleidoscopic new
Read more
Spatiotemporal Bundle Adjustment for Dynamic 3D Reconstruction
An interesting work from CMU. A spatiotemporal cost function is defined in order to jointly estimates both the spatiotemporal camera
Read more
Google New Plan: Map the Interior World in 3-D
Everyone knows about Google Map and use it. But now the internet giant has a bigger target: it wants to digitally map
Read more