VASC Seminar
Jean-François Lalonde
Professor
Université Lava

Towards editable indoor lighting estimation

Newell-Simon Hall 3305

Abstract:  Combining virtual and real visual elements into a single, realistic image requires the accurate estimation of the lighting conditions of the real scene. In recent years, several approaches of increasing complexity---ranging from simple encoder-decoder architecture to more sophisticated volumetric neural rendering---have been proposed. While the quality of automatic estimates has increased, they have the unfortunate downside [...]

PhD Thesis Proposal
PhD Student
Robotics Institute,
Carnegie Mellon University

Causal Robot Learning for Manipulation

Abstract: Two decades into the third age of AI, the rise of deep learning has yielded two seemingly disparate realities. In one, massive accomplishments have been achieved in deep reinforcement learning, protein folding, and large language models. Yet, in the other, the promises of deep learning to empower robots that operate robustly in real-world environments [...]

Faculty Events

RI Faculty Business Meeting

Newell-Simon Hall 4305

Meeting for RI Faculty. Discussions include various department topics, policies, and procedures. Generally meets weekly.

VASC Seminar
Project Scientist
Robotics Institute,
Carnegie Mellon University

Computational imaging with multiply scattered photons

Newell-Simon Hall 3305

Abstract:  Computational imaging has advanced to a point where the next significant milestone is to image in the presence of multiply-scattered light. Though traditionally treated as noise, multiply-scattered light carries information that can enable previously impossible imaging capabilities, such as imaging around corners and deep inside tissue. The combinatorial complexity of multiply-scattered light transport makes [...]

PhD Thesis Proposal
PhD Student
Robotics Institute,
Carnegie Mellon University

Dense Reconstruction of Dynamic Structures from Monocular RGB Videos

NSH 4305

Abstract: We study the problem of 3D reconstruction of {\em generic} and {\em deformable} objects and scenes from {\em casually-taken} RGB videos, to create a system for capturing the dynamic 3D world. Being able to reconstruct dynamic structures from casual videos allows one to create avatars and motion references for arbitrary objects without specialized devices, [...]

PhD Speaking Qualifier
PhD Student
Robotics Institute,
Carnegie Mellon University

Differentiable Collision Detection

NSH 4305

Abstract: Collision detection between objects is critical for simulation, control, and learning for robotic systems. However, existing collision detection routines are inherently non-differentiable, limiting their applications in gradient-based optimization tools. In this talk, I present DCOL: a fast and fully differentiable collision-detection framework that reasons about collisions between a set of composable and highly expressive [...]

RI Seminar
Ankur Mehta
Assistant Professor & Samueli Fellow
Electrical & Computer Engineering, UCLA

Towards $1 robots

1305 Newell Simon Hall

Abstract: Robots are pretty great -- they can make some hard tasks easy, some dangerous tasks safe, or some unthinkable tasks possible.  And they're just plain fun to boot.  But how many robots have you interacted with recently?  And where do you think that puts you compared to the rest of the world's people? In [...]

VASC Seminar
Wei-Chiu Ma
PhD Candidate
MIT

Mental models for 3D modeling and generation

Newell-Simon Hall 3305

Abstract:  Humans have extraordinary capabilities of comprehending and reasoning about our 3D visual world. One particular reason is that when looking at an object or a scene, not only can we see the visible surface, but we can also hallucinate the invisible parts - the amodal structure, appearance, affordance, etc. We have accumulated thousands of [...]

PhD Speaking Qualifier
PhD Student
Robotics Institute,
Carnegie Mellon University

On Interaction, Imitation, and Causation

GHC 6501

Abstract: A standard critique of machine learning models (especially neural networks) is that they pick up on spurious correlations rather than causal relationships and are therefore brittle in the face of distribution shift. Solving this problem in full generality is impossible (i.e. there might be no good way to distinguish between the two). However, if [...]