PhD Speaking Qualifier
PhD Student
Robotics Institute,
Carnegie Mellon University

When to use CNNs for Inverse Problems in Vision

NSH 4201

Abstract: Reconstruction tasks in computer vision aim fundamentally to recover an undetermined signal from a set of noisy measurements. Examples include super-resolution, image denoising, and non-rigid structure from motion\cite{Kong_2019}, all of which have seen recent advancements through deep learning. However, earlier work made extensive use of sparse signal reconstruction frameworks (e.g. convolutional sparse coding). While [...]

RI Seminar
Sam Burden
Assistant Professor
Electrical & Computer Engineering, University of Washington

Toward telelocomotion: human sensorimotor control of contact-rich robot dynamics

1305 Newell Simon Hall

Abstract: Human interaction with the physical world is increasingly mediated by automation -- planes assist pilots, cars assist drivers, and robots assist surgeons. Such semi-autonomous machines will eventually pervade our world, doing dull and dirty work, assisting the elderly and disabled, and responding to disasters. Recent results (e.g. from the DARPA Robotics Challenge) demonstrate that, [...]

Faculty Events

2020 RI Faculty Dinner

Pittsburgh Golf Club 5280 Northumberland Street, Pittsburgh, PA, United States

Invitation with information will be emailed to invitees.

RI Seminar
Hadas Kress-Gazit
Associate Professor
College of Engineering, Cornell University

Formal Synthesis for Robots

Abstract: In this talk I will describe how formal methods such as synthesis – automatically creating a system from a formal specification – can be leveraged to design robots, explain and provide guarantees for their behavior, and even identify skills they might be missing. I will discuss the benefits and challenges of synthesis techniques and [...]

VASC Seminar
Thiemo Alldieck
PhD Candidate
Facebook Reality Labs

Reconstructing 3D Human Avatars from Monocular Images

GHC 6501

Abstract:  Statistical 3D human body models have helped us to better understand human shape and motion and already enabled exciting new applications. However, if we want to learn detailed, personalized, and clothed models of human shape, motion, and dynamics, we require new approaches that learn from ubiquitous data such as plain RGB-images and video. I [...]

PhD Thesis Proposal
Robotics Institute,
Carnegie Mellon University

Learning Dense 3D Object Reconstruction without Geometric Supervision

GHC 6501

Abstract: Geometric alignment across visual data has been the fundamental issue for effective and efficient computer vision algorithms. The established pixel correspondences between images indirectly infer the underlying 3D geometry, physically or semantically. While this builds the foundation of classical multi-view 3D reconstruction algorithms such as Structure from Motion (SfM) and Simultaneous Localization and Mapping [...]

RI Seminar
Assistant Professor
Robotics Institute,
Carnegie Mellon University

Extreme Motions in Biological and Engineered Systems

1305 Newell Simon Hall

Abstract: Dr. Temel’s work mainly focuses on understanding the dynamics and energetics of extreme motions in small-scale natural and synthetic systems. Small-scale biological systems achieve extraordinary accelerations, speeds, and forces that can be repeated with minimal costs throughout the life of the organism. Zeynep uses analytical and computational models as well as physical prototypes to learn about these systems, test [...]

VASC Seminar
Adriana Kovashka
Assistant Professor
University of Pittsburgh

Reasoning about complex media from weak multi-modal supervision

GHC 6501

Abstract:  In a world of abundant information targeting multiple senses, and increasingly powerful media, we need new mechanisms to model content. Techniques for representing individual channels, such as visual data or textual data, have greatly improved, and some techniques exist to model the relationship between channels that are “mirror images” of each other and contain [...]

RI Event
Omry Yadan
Research Engineer
Facebook AI Research

Vision Tool Seminar: Hydra

3305 Newell-Simon Hall

Abstract: Hydra is an open-source Python framework developed at FAIR that aims to reduce the amount of boilerplate code in research and other complex applications. The key feature is the ability to dynamically create a hierarchical configuration by composition and override it through config files and the command line. The name Hydra comes from its [...]

RI Seminar
Raquel Urtasun
Chief Scientist & Head
Uber Advanced Technologies Group Toronto

CANCELLED

CIC Building Room 1201