no code implementations • 21 Mar 2023 • Ignacio Rocco, Iurii Makarov, Filippos Kokkinos, David Novotny, Benjamin Graham, Natalia Neverova, Andrea Vedaldi
We present a method for fast 3D reconstruction and real-time rendering of dynamic humans from monocular videos with accompanying parametric body fits.
1 code implementation • 6 Dec 2022 • Mohamed El Banani, Ignacio Rocco, David Novotny, Andrea Vedaldi, Natalia Neverova, Justin Johnson, Benjamin Graham
To address this, we propose a self-supervised approach for correspondence estimation that learns from multiview consistency in short RGB-D video sequences.
no code implementations • CVPR 2022 • David Novotny, Ignacio Rocco, Samarth Sinha, Alexandre Carlier, Gael Kerchenbaum, Roman Shapovalov, Nikita Smetanin, Natalia Neverova, Benjamin Graham, Andrea Vedaldi
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.
no code implementations • ICCV 2021 • Roman Shapovalov, David Novotny, Benjamin Graham, Patrick Labatut, Andrea Vedaldi
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.
1 code implementation • ICCV 2021 • Ji Hou, Saining Xie, Benjamin Graham, Angela Dai, Matthias Nießner
Inspired by these advances in geometric understanding, we aim to imbue image-based perception with representations learned under geometric constraints.
1 code implementation • CVPR 2021 • Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie
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 #2 on 3D Semantic Segmentation on ScanNet200
1 code implementation • 20 Nov 2020 • Benjamin Graham, David Novotny
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.
no code implementations • NeurIPS 2020 • Benjamin Biggs, Sébastien Ehrhadt, Hanbyul Joo, Benjamin Graham, Andrea Vedaldi, David Novotny
We consider the problem of obtaining dense 3D reconstructions of humans from single and partially occluded views.
4 code implementations • ICLR 2021 • Angela Fan, Pierre Stock, Benjamin Graham, Edouard Grave, Remi Gribonval, Herve Jegou, Armand Joulin
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.
2 code implementations • ICCV 2019 • David Novotny, Nikhila Ravi, Benjamin Graham, Natalia Neverova, Andrea Vedaldi
We propose C3DPO, a method for extracting 3D models of deformable objects from 2D keypoint annotations in unconstrained images.
3 code implementations • ICLR 2020 • Pierre Stock, Armand Joulin, Rémi Gribonval, Benjamin Graham, Hervé Jégou
In this paper, we address the problem of reducing the memory footprint of convolutional network architectures.
1 code implementation • ICLR 2019 • Pierre Stock, Benjamin Graham, Rémi Gribonval, Hervé Jégou
Modern neural networks are over-parametrized.
1 code implementation • 26 Nov 2018 • Benjamin Graham
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.
2 code implementations • 22 Feb 2018 • Jeremy Reizenstein, Benjamin Graham
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
5 code implementations • CVPR 2018 • Benjamin Graham, Martin Engelcke, Laurens van der Maaten
Submanifold sparse convolutional networks
Ranked #4 on 3D Semantic Segmentation on SensatUrban
1 code implementation • 17 Oct 2017 • Li Yi, Lin Shao, Manolis Savva, Haibin Huang, Yang Zhou, Qirui Wang, Benjamin Graham, Martin Engelcke, Roman Klokov, Victor Lempitsky, Yuan Gan, Pengyu Wang, Kun Liu, Fenggen Yu, Panpan Shui, Bingyang Hu, Yan Zhang, Yangyan Li, Rui Bu, Mingchao Sun, Wei Wu, Minki Jeong, Jaehoon Choi, Changick Kim, Angom Geetchandra, Narasimha Murthy, Bhargava Ramu, Bharadwaj Manda, M. Ramanathan, Gautam Kumar, P Preetham, Siddharth Srivastava, Swati Bhugra, Brejesh lall, Christian Haene, Shubham Tulsiani, Jitendra Malik, Jared Lafer, Ramsey Jones, Siyuan Li, Jie Lu, Shi Jin, Jingyi Yu, Qi-Xing Huang, Evangelos Kalogerakis, Silvio Savarese, Pat Hanrahan, Thomas Funkhouser, Hao Su, Leonidas Guibas
We introduce a large-scale 3D shape understanding benchmark using data and annotation from ShapeNet 3D object database.
5 code implementations • 5 Jun 2017 • Benjamin Graham, Laurens van der Maaten
Convolutional network are the de-facto standard for analysing spatio-temporal data such as images, videos, 3D shapes, etc.
Ranked #26 on 3D Part Segmentation on ShapeNet-Part
no code implementations • 27 Feb 2017 • Benjamin Graham
Artificial neural networks can be trained with relatively low-precision floating-point and fixed-point arithmetic, using between one and 16 bits.
no code implementations • 23 Oct 2015 • Leigh Robinson, Benjamin Graham
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.
5 code implementations • 18 Dec 2014 • Benjamin Graham
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 #19 on Image Classification on MNIST
3 code implementations • 22 Sep 2014 • Benjamin Graham
Convolutional neural networks (CNNs) perform well on problems such as handwriting recognition and image classification.
Ranked #137 on Image Classification on CIFAR-100
no code implementations • 1 Aug 2013 • Benjamin Graham
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.