259 citations · 519 across the 30 of their papers we have counts for
31 papers
A Model-Based Solution to the Offline Multi-Agent Reinforcement Learning Coordination Problem
Paul Barde, Jakob Foerster, Derek Nowrouzezahrai +1
Training multiple agents to coordinate is an essential problem with applications in robotics, game theory, economics, and social sciences. However, most existing Multi-Agent Reinfo…
MeshDiffusion: Score-based Generative 3D Mesh Modeling
Zhen Liu, Yao Feng, Michael J. Black +3
We consider the task of generating realistic 3D shapes, which is useful for a variety of applications such as automatic scene generation and physical simulation. Compared to other…
Neural Shadow Mapping
Sayantan Datta, Derek Nowrouzezahrai, Christoph Schied +1
We present a neural extension of basic shadow mapping for fast, high quality hard and soft shadows. We compare favorably to fast pre-filtering shadow mapping, all while producing v…
Visual Question Answering From Another Perspective: CLEVR Mental Rotation Tests
Christopher Beckham, Martin Weiss, Florian Golemo +3
Different types of mental rotation tests have been used extensively in psychology to understand human visual reasoning and perception. Understanding what an object or visual scene…
Attention-based Neural Cellular Automata
Mattie Tesfaldet, Derek Nowrouzezahrai, Christopher Pal
Recent extensions of Cellular Automata (CA) have incorporated key ideas from modern deep learning, dramatically extending their capabilities and catalyzing a new family of Neural C…
Learning Neural Implicit Representations with Surface Signal Parameterizations
Yanran Guan, Andrei Chubarau, Ruby Rao +1
Neural implicit surface representations have recently emerged as popular alternative to explicit 3D object encodings, such as polygonal meshes, tabulated points, or voxels. While s…
Learning Latent Structural Causal Models
Jithendaraa Subramanian, Yashas Annadani, Ivaxi Sheth +5
Causal learning has long concerned itself with the accurate recovery of underlying causal mechanisms. Such causal modelling enables better explanations of out-of-distribution data.…
Uncertainty-Driven Active Vision for Implicit Scene Reconstruction
Edward J. Smith, Michal Drozdzal, Derek Nowrouzezahrai +2
Multi-view implicit scene reconstruction methods have become increasingly popular due to their ability to represent complex scene details. Recent efforts have been devoted to impro…
Latent Variable Models for Bayesian Causal Discovery
Jithendaraa Subramanian, Yashas Annadani, Ivaxi Sheth +3
Learning predictors that do not rely on spurious correlations involves building causal representations. However, learning such a representation is very challenging. We, therefore,…
Kubric: A scalable dataset generator
Klaus Greff, Francois Belletti, Lucas Beyer +32
Data is the driving force of machine learning, with the amount and quality of training data often being more important for the performance of a system than architecture and trainin…
Overcoming challenges in leveraging GANs for few-shot data augmentation
Christopher Beckham, Issam Laradji, Pau Rodriguez +3
In this paper, we explore the use of GAN-based few-shot data augmentation as a method to improve few-shot classification performance. We perform an exploration into how a GAN can b…
Learning to Guide and to Be Guided in the Architect-Builder Problem
Paul Barde, Tristan Karch, Derek Nowrouzezahrai +3
We are interested in interactive agents that learn to coordinate, namely, a -- which performs actions but ignores the goal of the task, i.e. has no access to rewards -- a…
SSR: Semi-supervised Soft Rasterizer for single-view 2D to 3D Reconstruction
Issam Laradji, Pau Rodríguez, David Vazquez +1
Recent work has made significant progress in learning object meshes with weak supervision. Soft Rasterization methods have achieved accurate 3D reconstruction from 2D images with v…
Dynamic Diffuse Global Illumination Resampling
Zander Majercik, Thomas Müller, Alexander Keller +2
Interactive global illumination remains a challenge in radiometrically- and geometrically-complex scenes. Specialized sampling strategies are effective for specular and near-specul…
gradSim: Differentiable simulation for system identification and visuomotor control
Krishna Murthy Jatavallabhula, Miles Macklin, Florian Golemo +11
We consider the problem of estimating an object's physical properties such as mass, friction, and elasticity directly from video sequences. Such a system identification problem is…
Countering Racial Bias in Computer Graphics Research
Theodore Kim, Holly Rushmeier, Julie Dorsey +4
Current computer graphics research practices contain racial biases that have resulted in investigations into "skin" and "hair" that focus on the hegemonic visual features of Europe…
Robust Motion In-betweening
Félix G. Harvey, Mike Yurick, Derek Nowrouzezahrai +1
In this work we present a novel, robust transition generation technique that can serve as a new tool for 3D animators, based on adversarial recurrent neural networks. The system sy…
Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes
Towaki Takikawa, Joey Litalien, Kangxue Yin +6
Neural signed distance functions (SDFs) are emerging as an effective representation for 3D shapes. State-of-the-art methods typically encode the SDF with a large, fixed-size neural…
Affinity LCFCN: Learning to Segment Fish with Weak Supervision
Issam Laradji, Alzayat Saleh, Pau Rodriguez +3
Aquaculture industries rely on the availability of accurate fish body measurements, e.g., length, width and mass. Manual methods that rely on physical tools like rulers are time an…
Regularized Inverse Reinforcement Learning
Wonseok Jeon, Chen-Yang Su, Paul Barde +3
Inverse Reinforcement Learning (IRL) aims to facilitate a learner's ability to imitate expert behavior by acquiring reward functions that explain the expert's decisions. Regularize…
On the Effectiveness of Weight-Encoded Neural Implicit 3D Shapes
Thomas Davies, Derek Nowrouzezahrai, Alec Jacobson
A neural implicit outputs a number indicating whether the given query point in space is inside, outside, or on a surface. Many prior works have focused on _latent-encoded_ neural i…
A Weakly Supervised Region-Based Active Learning Method for COVID-19 Segmentation in CT Images
Issam Laradji, Pau Rodriguez, Frederic Branchaud-Charron +5
One of the key challenges in the battle against the Coronavirus (COVID-19) pandemic is to detect and quantify the severity of the disease in a timely manner. Computed tomographies…
A Weakly Supervised Consistency-based Learning Method for COVID-19 Segmentation in CT Images
Issam Laradji, Pau Rodriguez, Oscar Mañas +6
Coronavirus Disease 2019 (COVID-19) has spread aggressively across the world causing an existential health crisis. Thus, having a system that automatically detects COVID-19 in tomo…
Surprisal-Triggered Conditional Computation with Neural Networks
Loren Lugosch, Derek Nowrouzezahrai, Brett H. Meyer
Autoregressive neural network models have been used successfully for sequence generation, feature extraction, and hypothesis scoring. This paper presents yet another use for these…