Search Results for author:
Found 24 papers, 18 papers with code
Sparse arrays of signatures for online character recognition
We show that the path signature, used as a set of features for consumption by a convolutional neural network (CNN), improves the accuracy of online character recognition---that is the task of reading characters represented as a collection of paths.
Spatially-sparse convolutional neural networks
Convolutional neural networks (CNNs) perform well on problems such as handwriting recognition and image classification.
Ranked #144 on
Image Classification
on CIFAR-100
(using extra training data)
Fractional Max-Pooling
However, if you simply alternate convolutional layers with max-pooling layers, performance is limited due to the rapid reduction in spatial size, and the disjoint nature of the pooling regions.
Ranked #17 on
Image Classification
on MNIST
Confusing Deep Convolution Networks by Relabelling
Deep convolutional neural networks have become the gold standard for image recognition tasks, demonstrating many current state-of-the-art results and even achieving near-human level performance on some tasks.
Low-Precision Batch-Normalized Activations
Artificial neural networks can be trained with relatively low-precision floating-point and fixed-point arithmetic, using between one and 16 bits.
Submanifold Sparse Convolutional Networks
Convolutional network are the de-facto standard for analysing spatio-temporal data such as images, videos, 3D shapes, etc.
Ranked #34 on
3D Part Segmentation
on ShapeNet-Part
Large-Scale 3D Shape Reconstruction and Segmentation from ShapeNet Core55
We introduce a large-scale 3D shape understanding benchmark using data and annotation from ShapeNet 3D object database.
3D Semantic Segmentation with Submanifold Sparse Convolutional Networks
Submanifold sparse convolutional networks
Ranked #5 on
3D Semantic Segmentation
on SensatUrban
The iisignature library: efficient calculation of iterated-integral signatures and log signatures
Iterated-integral signatures and log signatures are vectors calculated from a path that characterise its shape.
Data Structures and Algorithms Mathematical Software Rings and Algebras
Unsupervised learning with sparse space-and-time autoencoders
We use spatially-sparse two, three and four dimensional convolutional autoencoder networks to model sparse structures in 2D space, 3D space, and 3+1=4 dimensional space-time.
And the Bit Goes Down: Revisiting the Quantization of Neural Networks
In this paper, we address the problem of reducing the memory footprint of convolutional network architectures.
C3DPO: Canonical 3D Pose Networks for Non-Rigid Structure From Motion
We propose C3DPO, a method for extracting 3D models of deformable objects from 2D keypoint annotations in unconstrained images.
Training with Quantization Noise for Extreme Model Compression
A standard solution is to train networks with Quantization Aware Training, where the weights are quantized during training and the gradients approximated with the Straight-Through Estimator.
3D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Data
We consider the problem of obtaining dense 3D reconstructions of humans from single and partially occluded views.
RidgeSfM: Structure from Motion via Robust Pairwise Matching Under Depth Uncertainty
Using a set of high-quality sparse keypoint matches, we optimize over the per-frame linear combinations of depth planes and camera poses to form a geometrically consistent cloud of keypoints.
Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts
The rapid progress in 3D scene understanding has come with growing demand for data; however, collecting and annotating 3D scenes (e. g. point clouds) are notoriously hard.
Ranked #8 on
3D Semantic Segmentation
on ScanNet200
Pri3D: Can 3D Priors Help 2D Representation Learning?
Inspired by these advances in geometric understanding, we aim to imbue image-based perception with representations learned under geometric constraints.
DensePose 3D: Lifting Canonical Surface Maps of Articulated Objects to the Third Dimension
The method learns, in an end-to-end fashion, a soft partition of a given category-specific 3D template mesh into rigid parts together with a monocular reconstruction network that predicts the part motions such that they reproject correctly onto 2D DensePose-like surface annotations of the object.
KeyTr: Keypoint Transporter for 3D Reconstruction of Deformable Objects in Videos
Compared to weaker deformation models, this significantly reduces the reconstruction ambiguity and, for dynamic objects, allows Keypoint Transporter to obtain reconstructions of the quality superior or at least comparable to prior approaches while being much faster and reliant on a pre-trained monocular depth estimator network.
Self-Supervised Correspondence Estimation via Multiview Registration
To address this, we propose a self-supervised approach for correspondence estimation that learns from multiview consistency in short RGB-D video sequences.
Real-time volumetric rendering of dynamic humans
We present a method for fast 3D reconstruction and real-time rendering of dynamic humans from monocular videos with accompanying parametric body fits.
DynamicStereo: Consistent Dynamic Depth from Stereo Videos
The network learns to pool information from neighboring frames to improve the temporal consistency of its predictions.
CoTracker: It is Better to Track Together
We introduce CoTracker, a transformer-based model that tracks dense points in a frame jointly across a video sequence.
