546 citations · 1.3k across the 25 of their papers we have counts for
27 papers
Kick Back & Relax: Learning to Reconstruct the World by Watching SlowTV
Jaime Spencer, Chris Russell, Simon Hadfield +1
Self-supervised monocular depth estimation (SS-MDE) has the potential to scale to vast quantities of data. Unfortunately, existing approaches limit themselves to the automotive dom…
Learning Adaptive Neighborhoods for Graph Neural Networks
Avishkar Saha, Oscar Mendez, Chris Russell +1
Graph convolutional networks (GCNs) enable end-to-end learning on graph structured data. However, many works assume a given graph structure. When the input graph is noisy or unavai…
The Second Monocular Depth Estimation Challenge
Jaime Spencer, C. Stella Qian, Michaela Trescakova +40
This paper discusses the results for the second edition of the Monocular Depth Estimation Challenge (MDEC). This edition was open to methods using any form of supervision, includin…
Image retrieval outperforms diffusion models on data augmentation
Max F. Burg, Florian Wenzel, Dominik Zietlow +4
Many approaches have been proposed to use diffusion models to augment training datasets for downstream tasks, such as classification. However, diffusion models are themselves train…
Novel View Synthesis of Humans using Differentiable Rendering
Guillaume Rochette, Chris Russell, Richard Bowden
We present a new approach for synthesizing novel views of people in new poses. Our novel differentiable renderer enables the synthesis of highly realistic images from any viewpoint…
Efficient fair PCA for fair representation learning
Matthäus Kleindessner, Michele Donini, Chris Russell +1
We revisit the problem of fair principal component analysis (PCA), where the goal is to learn the best low-rank linear approximation of the data that obfuscates demographic informa…
The Monocular Depth Estimation Challenge
Jaime Spencer, C. Stella Qian, Chris Russell +16
This paper summarizes the results of the first Monocular Depth Estimation Challenge (MDEC) organized at WACV2023. This challenge evaluated the progress of self-supervised monocular…
Deconstructing Self-Supervised Monocular Reconstruction: The Design Decisions that Matter
Jaime Spencer, Chris Russell, Simon Hadfield +1
This paper presents an open and comprehensive framework to systematically evaluate state-of-the-art contributions to self-supervised monocular depth estimation. This includes pretr…
Pixel-level Correspondence for Self-Supervised Learning from Video
Yash Sharma, Yi Zhu, Chris Russell +1
While self-supervised learning has enabled effective representation learning in the absence of labels, for vision, video remains a relatively untapped source of supervision. To add…
Assaying Out-Of-Distribution Generalization in Transfer Learning
Florian Wenzel, Andrea Dittadi, Peter Vincent Gehler +9
Since out-of-distribution generalization is a generally ill-posed problem, various proxy targets (e.g., calibration, adversarial robustness, algorithmic corruptions, invariance acr…
"The Pedestrian next to the Lamppost" Adaptive Object Graphs for Better Instantaneous Mapping
Avishkar Saha, Oscar Mendez, Chris Russell +1
Estimating a semantically segmented bird's-eye-view (BEV) map from a single image has become a popular technique for autonomous control and navigation. However, they show an increa…
Leveling Down in Computer Vision: Pareto Inefficiencies in Fair Deep Classifiers
Dominik Zietlow, Michael Lohaus, Guha Balakrishnan +4
Algorithmic fairness is frequently motivated in terms of a trade-off in which overall performance is decreased so as to improve performance on disadvantaged groups where the algori…
Human Pose Manipulation and Novel View Synthesis using Differentiable Rendering
Guillaume Rochette, Chris Russell, Richard Bowden
We present a new approach for synthesizing novel views of people in new poses. Our novel differentiable renderer enables the synthesis of highly realistic images from any viewpoint…
Translating Images into Maps
Avishkar Saha, Oscar Mendez Maldonado, Chris Russell +1
We approach instantaneous mapping, converting images to a top-down view of the world, as a translation problem. We show how a novel form of transformer network can be used to map f…
Visual Representation Learning Does Not Generalize Strongly Within the Same Domain
Lukas Schott, Julius von Kügelgen, Frederik Träuble +6
An important component for generalization in machine learning is to uncover underlying latent factors of variation as well as the mechanism through which each factor acts in the wo…
Explaining Classifiers using Adversarial Perturbations on the Perceptual Ball
Andrew Elliott, Stephen Law, Chris Russell
We present a simple regularization of adversarial perturbations based upon the perceptual loss. While the resulting perturbations remain imperceptible to the human eye, they differ…
Weakly-Supervised 3D Pose Estimation from a Single Image using Multi-View Consistency
Guillaume Rochette, Chris Russell, Richard Bowden
We present a novel data-driven regularizer for weakly-supervised learning of 3D human pose estimation that eliminates the drift problem that affects existing approaches. We do this…
U4D: Unsupervised 4D Dynamic Scene Understanding
Armin Mustafa, Chris Russell, Adrian Hilton
We introduce the first approach to solve the challenging problem of unsupervised 4D visual scene understanding for complex dynamic scenes with multiple interacting people from mult…
Rethinking Pose in 3D: Multi-stage Refinement and Recovery for Markerless Motion Capture
Denis Tome, Matteo Toso, Lourdes Agapito +1
We propose a CNN-based approach for multi-camera markerless motion capture of the human body. Unlike existing methods that first perform pose estimation on individual cameras and g…
Worst-case Optimal Submodular Extensions for Marginal Estimation
Pankaj Pansari, Chris Russell, M. Pawan Kumar
Submodular extensions of an energy function can be used to efficiently compute approximate marginals via variational inference. The accuracy of the marginals depends crucially on t…
Better Together: Joint Reasoning for Non-rigid 3D Reconstruction with Specularities and Shading
Qi Liu-Yin, Rui Yu, Lourdes Agapito +2
We demonstrate the use of shape-from-shading (SfS) to improve both the quality and the robustness of 3D reconstruction of dynamic objects captured by a single camera. Unlike previo…
VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning
Akash Srivastava, Lazar Valkov, Chris Russell +2
Deep generative models provide powerful tools for distributions over complicated manifolds, such as those of natural images. But many of these methods, including generative adversa…
Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image
Denis Tome, Chris Russell, Lourdes Agapito
We propose a unified formulation for the problem of 3D human pose estimation from a single raw RGB image that reasons jointly about 2D joint estimation and 3D pose reconstruction t…
Solving Jigsaw Puzzles with Linear Programming
Rui Yu, Chris Russell, Lourdes Agapito
We propose a novel Linear Program (LP) based formula- tion for solving jigsaw puzzles. We formulate jigsaw solving as a set of successive global convex relaxations of the stan- dar…