348 citations · 1.5k across the 43 of their papers we have counts for
11 papers · 1 filter
Neural Fourier Filter Bank
Zhijie Wu, Yuhe Jin, Kwang Moo Yi
We present a novel method to provide efficient and highly detailed reconstructions. Inspired by wavelets, we learn a neural field that decompose the signal both spatially and frequ…
Bootstrapping Human Optical Flow and Pose
Aritro Roy Arko, James J. Little, Kwang Moo Yi
We propose a bootstrapping framework to enhance human optical flow and pose. We show that, for videos involving humans in scenes, we can improve both the optical flow and the pose…
Attention Beats Concatenation for Conditioning Neural Fields
Daniel Rebain, Mark J. Matthews, Kwang Moo Yi +3
Neural fields model signals by mapping coordinate inputs to sampled values. They are becoming an increasingly important backbone architecture across many fields from vision and gra…
Estimating Visual Information From Audio Through Manifold Learning
Fabrizio Pedersoli, Dryden Wiebe, Amin Banitalebi +3
We propose a new framework for extracting visual information about a scene only using audio signals. Audio-based methods can overcome some of the limitations of vision-based method…
NeuralBF: Neural Bilateral Filtering for Top-down Instance Segmentation on Point Clouds
Weiwei Sun, Daniel Rebain, Renjie Liao +4
We introduce a method for instance proposal generation for 3D point clouds. Existing techniques typically directly regress proposals in a single feed-forward step, leading to inacc…
TUSK: Task-Agnostic Unsupervised Keypoints
Yuhe Jin, Weiwei Sun, Jan Hosang +2
Existing unsupervised methods for keypoint learning rely heavily on the assumption that a specific keypoint type (e.g. elbow, digit, abstract geometric shape) appears only once in…
FlowNet-PET: Unsupervised Learning to Perform Respiratory Motion Correction in PET Imaging
Teaghan O'Briain, Carlos Uribe, Kwang Moo Yi +3
To correct for respiratory motion in PET imaging, an interpretable and unsupervised deep learning technique, FlowNet-PET, was constructed. The network was trained to predict the op…
A Simple Method to Boost Human Pose Estimation Accuracy by Correcting the Joint Regressor for the Human3.6m Dataset
Eric Hedlin, Helge Rhodin, Kwang Moo Yi
Many human pose estimation methods estimate Skinned Multi-Person Linear (SMPL) models and regress the human joints from these SMPL estimates. In this work, we show that the most wi…
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…
NeuMan: Neural Human Radiance Field from a Single Video
Wei Jiang, Kwang Moo Yi, Golnoosh Samei +2
Photorealistic rendering and reposing of humans is important for enabling augmented reality experiences. We propose a novel framework to reconstruct the human and the scene that ca…
Repurposing Existing Deep Networks for Caption and Aesthetic-Guided Image Cropping
Nora Horanyi, Kedi Xia, Kwang Moo Yi +3
We propose a novel optimization framework that crops a given image based on user description and aesthetics. Unlike existing image cropping methods, where one typically trains a de…