Automatic differentiation (AD) is a technique for computing the derivative of a function represented by a program.
1 code implementation • 22 Nov 2022 • Alberto Cattaneo, Daniel Justus, Harry Mellor, Douglas Orr, Jerome Maloberti, Zhenying Liu, Thorin Farnsworth, Andrew Fitzgibbon, Blazej Banaszewski, Carlo Luschi
We present the award-winning submission to the WikiKG90Mv2 track of OGB-LSC@NeurIPS 2022.
To represent people in mixed reality applications for collaboration and communication, we need to generate realistic and faithful avatar poses.
We show in this paper that the variation in sequence lengths in common NLP datasets is such that up to 50% of all tokens can be padding.
We introduce an automatic, end-to-end method for recovering the 3D pose and shape of dogs from monocular internet images.
In this paper we introduce the first scalable training technique for 3D generative models from 2D data which utilizes an off-the-shelf non-differentiable renderer.
We present a system to recover the 3D shape and motion of a wide variety of quadrupeds from video.
However, it is important for the success of algorithmic differentiation that such `simple' objective functions are handled efficiently, as so many problems in computer vision and machine learning are of this form.
We present a system for the automatic differentiation of a higher-order functional array-processing language.
We show that such a combination is beneficial because the unlabeled data acts as a data-driven form of regularization, allowing generative models trained on few labeled samples to reach the performance of fully-supervised generative models trained on much larger datasets.
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.
We present a novel strategy to shrink and constrain a 3D model, represented as a smooth spline-like surface, within the visual hull of an object observed from one or multiple views.
Variable Projection (VarPro) is a framework to solve optimization problems efficiently by optimally eliminating a subset of the unknowns.
We present new methods for simultaneously estimating camera geometry and time shift from video sequences from multiple unsynchronized cameras.
We present a fast, practical method for personalizing a hand shape basis to an individual user's detailed hand shape using only a small set of depth images.
Matrix factorization (or low-rank matrix completion) with missing data is a key computation in many computer vision and machine learning tasks, and is also related to a broader class of nonlinear optimization problems such as bundle adjustment.
In this paper, we show how to perform model-based object tracking which allows to reconstruct the object's depth at an order of magnitude higher frame-rate through simple modifications to an off-the-shelf depth camera.
Modern structure from motion (SfM) remains dependent on point features to recover camera positions, meaning that reconstruction is severely hampered in low-texture environments, for example scanning a plain coffee cup on an uncluttered table.
Our method supports online model correction, without needing to reprocess or store any input depth data.
We represent the observed surface using Loop subdivision of a control mesh that is deformed by our learned parametric shape and pose model.
Recent advances in camera relocalization use predictions from a regression forest to guide the camera pose optimization procedure.
We formulate this problem as inversion of the generative rendering procedure, i. e., we want to find the camera pose corresponding to a rendering of the 3D scene model that is most similar with the observed input.
As a consequence of our approach, our output is a dense field of 3D rigid body motions, in contrast to the 3D translations that are the norm in scene flow.
We focus on modeling the human hand, and assume that a single rough template model is available.
We address the problem of inferring the pose of an RGB-D camera relative to a known 3D scene, given only a single acquired image.