Sanja Fidler is an Associate Professor at University of Toronto, affiliated faculty at the Vector Institute (and was one of the co-founding members) and VP of AI Research at NVIDIA, leading a research lab in Toronto. Prior coming to Toronto, in 2012/2013, she was a Research Assistant Professor at Toyota Technological Institute at Chicago, an academic institute located in the campus of University of Chicago.
Sanja Fidler
Faculty Member
Assistant Professor, Department of Computer Science, University of Toronto
Canada CIFAR Artificial Intelligence Chair
Research Interests
Sanja’s main research interests are in Computer Vision and Machine Learning. She is also interested in the interplay between language and vision.
- Intersection Computer Vision & Graphics
- 3D Vision
- 3D Reconstruction & Synthesis
- Interactive Methods for Image Annotation
Highlights
- Innovation Award (University of Toronto), 2021
- Connaught Innovation Award, 2020
- Early Researcher Award, 2019
- Best paper honorable mention at CVPR’17
- Connaught New Researcher Award, 2018
- Amazon Academic Research Award, 2017
- NVIDIA Pioneer of AI Award, 2016
- Facebook Faculty Award, 2016
- Outstanding reviewer award at ECCV’08, ECCV’12, CVPR’12, CVPR’15
- Professor of the Year, 2014/2015, awarded by the UofT’s Computer Science Student Union
- Best Teaching Assistant, 2007, awarded by University of Ljubljana’s Computer Science Student Union
Publications
f-Domain Adversarial Learning: Theory and Algorithms
2021
EditGAN: High-Precision Semantic Image Editing
2021
Image-level or object-level? a tale of two resampling strategies for long-tailed detection
2021
Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis
2021
ATISS: Autoregressive Transformers for Indoor Scene Synthesis
2021
DIB-R++: Learning to Predict Lighting and Material with a Hybrid Differentiable Renderer
2021
Labeling images using a neural network
2022
Generating labels for synthetic images using one or more neural networks
2022
Object image completion
2022
System and method for generation of an interactive color workspace
2022
Image generation using one or more neural networks
2021
Environment generation using one or more neural networks
2021
Scalable Neural Data Server: A Data Recommender for Transfer Learning
2021
Towards Optimal Strategies for Training Self-Driving Perception Models in Simulation
2021
Method and system for color representation generation
2021
Neural rendering for inverse graphics generation
2021
Unsupervised learning of scene structure for synthetic data generation
2021
Systems, devices and methods for transfer learning with a mixture of experts model
2021
Don’t Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence
2021
Neural network motion controller
2022
Causal Scene BERT: Improving object detection by searching for challenging groups
2021
Align your latents: High-resolution video synthesis with latent diffusion models
2023
Voxformer: Sparse voxel transformer for camera-based 3d semantic scene completion
2023
Trace and pace: Controllable pedestrian animation via guided trajectory diffusion
2025
Neural fields meet explicit geometric representations for inverse rendering of urban scenes
2025
Texfusion: Synthesizing 3d textures with text-guided image diffusion models
2023
Neuralfield-ldm: Scene generation with hierarchical latent diffusion models
2025
Learning physically simulated tennis skills from broadcast videos
2023
Neural kernel surface reconstruction
2023
Neural lidar fields for novel view synthesis
2023
Learning human dynamics in autonomous driving scenarios
2023
Dreamteacher: Pretraining image backbones with deep generative models
2024
End-to-end 3D Tracking with Decoupled Queries
2023
Towards Viewpoint Robustness in Bird’s Eye View Segmentation
2023
Emerging Pixel-level Semantic Knowledge in Diffusion Models
2023