Toronto Intelligent Systems Lab
Toronto Intelligent Systems Lab
Home
People
Publications
Teaching
Join Us
Paper-Conference
Dissecting Deep RL with High Update Ratios: Combatting Value Divergence
We show that deep reinforcement learning can maintain its ability to learn without resetting network parameters in settings where the …
Marcel Hussing
,
Claas Voelcker
,
Igor Gilitschenski
,
Amir-Massoud Farahmand
,
Eric Eaton
PDF
Cite
When does Self-Prediction help? Understanding Auxiliary Tasks in Reinforcement Learning
We investigate the impact of auxiliary learning tasks such as observation reconstruction and latent self-prediction on the …
Claas Voelcker
,
Tyler Kastner
,
Igor Gilitschenski
,
Amir-Massoud Farahmand
PDF
Cite
Code
LEOD: Label-Efficient Object Detection for Event Cameras
Object detection with event cameras benefits from the sensor’s low latency and high dynamic range. However, it is costly to fully label …
Ziyi Wu
,
Mathias Gehrig
,
Qing Lyu
,
Xudong Liu
,
Igor Gilitschenski
PDF
Cite
Code
Producing and Leveraging Online Map Uncertainty in Trajectory Prediction
High-definition (HD) maps have played an integral role in the development of modern autonomous vehicle (AV) stacks albeit with high …
Xunjiang Gu
,
Guanyu Song
,
Igor Gilitschenski
,
Marco Pavone
,
Boris Ivanovic
PDF
Cite
Code
SPAD: Spatially Aware Multi-View Diffusers
We present SPAD, a novel approach for creating consistent multi-view images from text prompts or single images. To enable multi-view …
Yash Kant
,
Aliaksandr Siarohin
,
Ziyi Wu
,
Michael Vasilkovsky
,
Guocheng Qian
,
Jian Ren
,
Riza Alp Guler
,
Bernard Ghanem
,
Sergey Tulyakov
,
Igor Gilitschenski
PDF
Cite
Code
AvatarOne: Monocular 3D Human Animation
Reconstructing realistic human avatars from monocular videos is a challenge that demands intricate modeling of 3D surface and …
Akash Karthikeyan
,
Robert Ren
,
Yash Kant
,
Igor Gilitschenski
PDF
Cite
Code
Project
iNVS: Repurposing Diffusion Inpainters for Novel View Synthesis
We present a method for generating consistent novel views from a single source image. Our approach focuses on maximizing the reuse of …
Yash Kant
,
Aliaksandr Siarohin
,
Michael Vasilkovsky
,
Riza Alp Guler
,
Jian Ren
,
Sergey Tulyakov
,
Igor Gilitschenski
PDF
Cite
Project
Poster
Slides
Video
DOI
SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models
Object-centric learning aims to represent visual data with a set of object entities (a.k.a. slots), providing structured …
Ziyi Wu
,
Jingyu Hu
,
Wuyue Lu
,
Igor Gilitschenski
,
Animesh Garg
Preprint
PDF
Cite
Code
Project
trajdata: A Unified Interface to Multiple Human Trajectory Datasets
The field of trajectory forecasting has grown significantly in recent years, partially owing to the release of numerous large-scale, …
Boris Ivanovic
,
Guanyu Song
,
Igor Gilitschenski
,
Marco Pavone
PDF
Cite
Code
Geometry Matching for Multi-Embodiment Grasping
Many existing learning-based grasping approaches concentrate on a single embodiment, provide limited generalization to higher DoF …
Maria Attarian
,
Muhammad Adil Asif
,
Jingzhou Liu
,
Ruthrash Hari
,
Animesh Garg
,
Igor Gilitschenski
,
Jonathan Tompson
PDF
Cite
Code
Project
»
Cite
×