no code implementations • ECCV 2020 • Boyang Deng, JP Lewis, Timothy Jeruzalski, Gerard Pons-Moll, Geoffrey Hinton, Mohammad Norouzi, Andrea Tagliasacchi
Efficient representation of articulated objects such as human bodies is an important problem in computer vision and graphics.
no code implementations • 9 May 2022 • Abhijit Kundu, Kyle Genova, Xiaoqi Yin, Alireza Fathi, Caroline Pantofaru, Leonidas Guibas, Andrea Tagliasacchi, Frank Dellaert, Thomas Funkhouser
Our model builds a panoptic radiance field representation of any scene from just color images.
1 code implementation • 7 Mar 2022 • Klaus Greff, Francois Belletti, Lucas Beyer, Carl Doersch, Yilun Du, Daniel Duckworth, David J. Fleet, Dan Gnanapragasam, Florian Golemo, Charles Herrmann, Thomas Kipf, Abhijit Kundu, Dmitry Lagun, Issam Laradji, Hsueh-Ti, Liu, Henning Meyer, Yishu Miao, Derek Nowrouzezahrai, Cengiz Oztireli, Etienne Pot, Noha Radwan, Daniel Rebain, Sara Sabour, Mehdi S. M. Sajjadi, Matan Sela, Vincent Sitzmann, Austin Stone, Deqing Sun, Suhani Vora, Ziyu Wang, Tianhao Wu, Kwang Moo Yi, Fangcheng Zhong, Andrea Tagliasacchi
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 training details.
1 code implementation • 4 Feb 2022 • Zhiqin Chen, Andrea Tagliasacchi, Thomas Funkhouser, Hao Zhang
We introduce neural dual contouring (NDC), a new data-driven approach to mesh reconstruction based on dual contouring (DC).
no code implementations • 9 Dec 2021 • Anthony Simeonov, Yilun Du, Andrea Tagliasacchi, Joshua B. Tenenbaum, Alberto Rodriguez, Pulkit Agrawal, Vincent Sitzmann
Our performance generalizes across both object instances and 6-DoF object poses, and significantly outperforms a recent baseline that relies on 2D descriptors.
no code implementations • 3 Dec 2021 • Kacper Kania, Kwang Moo Yi, Marek Kowalski, Tomasz Trzciński, Andrea Tagliasacchi
We extend neural 3D representations to allow for intuitive and interpretable user control beyond novel view rendering (i. e. camera control).
no code implementations • 29 Nov 2021 • Konstantinos Rematas, Andrew Liu, Pratul P. Srinivasan, Jonathan T. Barron, Andrea Tagliasacchi, Thomas Funkhouser, Vittorio Ferrari
The goal of this work is to perform 3D reconstruction and novel view synthesis from data captured by scanning platforms commonly deployed for world mapping in urban outdoor environments (e. g., Street View).
1 code implementation • 25 Nov 2021 • Naruya Kondo, Yuya Ikeda, Andrea Tagliasacchi, Yutaka Matsuo, Yoichi Ochiai, Shixiang Shane Gu
We hope VaxNeRF -- a careful combination of a classic technique with a deep method (that arguably replaced it) -- can empower and accelerate new NeRF extensions and applications, with its simplicity, portability, and reliable performance gains.
no code implementations • 25 Nov 2021 • Suhani Vora, Noha Radwan, Klaus Greff, Henning Meyer, Kyle Genova, Mehdi S. M. Sajjadi, Etienne Pot, Andrea Tagliasacchi, Daniel Duckworth
We present NeSF, a method for producing 3D semantic fields from posed RGB images alone.
no code implementations • 25 Nov 2021 • Mehdi S. M. Sajjadi, Henning Meyer, Etienne Pot, Urs Bergmann, Klaus Greff, Noha Radwan, Suhani Vora, Mario Lucic, Daniel Duckworth, Alexey Dosovitskiy, Jakob Uszkoreit, Thomas Funkhouser, Andrea Tagliasacchi
In this work, we propose the Scene Representation Transformer (SRT), a method which processes posed or unposed RGB images of a new area, infers a "set-latent scene representation", and synthesises novel views, all in a single feed-forward pass.
no code implementations • 19 Nov 2021 • Daniel Rebain, Mark Matthews, Kwang Moo Yi, Dmitry Lagun, Andrea Tagliasacchi
We present a method for learning a generative 3D model based on neural radiance fields, trained solely from data with only single views of each object.
no code implementations • 10 Aug 2021 • Ben Usman, Andrea Tagliasacchi, Kate Saenko, Avneesh Sud
In the era of deep learning, human pose estimation from multiple cameras with unknown calibration has received little attention to date.
1 code implementation • 27 Jun 2021 • Zhiqin Chen, Andrea Tagliasacchi, Hao Zhang
The network is trained to reconstruct a shape using a set of convexes obtained from a BSP-tree built over a set of planes, where the planes and convexes are both defined by learned network weights.
1 code implementation • CVPR 2021 • Baptiste Angles, Yuhe Jin, Simon Kornblith, Andrea Tagliasacchi, Kwang Moo Yi
We propose a deep network that can be trained to tackle image reconstruction and classification problems that involve detection of multiple object instances, without any supervision regarding their whereabouts.
no code implementations • 7 Jun 2021 • Daniel Rebain, Ke Li, Vincent Sitzmann, Soroosh Yazdani, Kwang Moo Yi, Andrea Tagliasacchi
Implicit representations of geometry, such as occupancy fields or signed distance fields (SDF), have recently re-gained popularity in encoding 3D solid shape in a functional form.
3 code implementations • ICCV 2021 • Congyue Deng, Or Litany, Yueqi Duan, Adrien Poulenard, Andrea Tagliasacchi, Leonidas Guibas
Invariance and equivariance to the rotation group have been widely discussed in the 3D deep learning community for pointclouds.
1 code implementation • ICCV 2021 • Wei Jiang, Eduard Trulls, Jan Hosang, Andrea Tagliasacchi, Kwang Moo Yi
We propose a novel framework for finding correspondences in images based on a deep neural network that, given two images and a query point in one of them, finds its correspondence in the other.
Ranked #1 on
Dense Pixel Correspondence Estimation
on ETH3D
Dense Pixel Correspondence Estimation
Optical Flow Estimation
no code implementations • 18 Dec 2020 • Francis Williams, Or Litany, Avneesh Sud, Kevin Swersky, Andrea Tagliasacchi
We introduce a technique for 3D human keypoint estimation that directly models the notion of spatial uncertainty of a keypoint.
1 code implementation • NeurIPS 2021 • Weiwei Sun, Andrea Tagliasacchi, Boyang Deng, Sara Sabour, Soroosh Yazdani, Geoffrey Hinton, Kwang Moo Yi
We propose a self-supervised capsule architecture for 3D point clouds.
no code implementations • NeurIPS 2020 • Chiyu Jiang, Jingwei Huang, Andrea Tagliasacchi, Leonidas J. Guibas
Such a space naturally allows the disentanglement of geometric style (coming from the source) and structural pose (conforming to the target).
no code implementations • 27 Nov 2020 • Sara Sabour, Andrea Tagliasacchi, Soroosh Yazdani, Geoffrey E. Hinton, David J. Fleet
Capsule networks aim to parse images into a hierarchy of objects, parts and relations.
no code implementations • CVPR 2021 • Daniel Rebain, Wei Jiang, Soroosh Yazdani, Ke Li, Kwang Moo Yi, Andrea Tagliasacchi
Moreover, we show that a Voronoi spatial decomposition is preferable for this purpose, as it is provably compatible with the Painter's Algorithm for efficient and GPU-friendly rendering.
no code implementations • 21 Oct 2020 • Soroosh Yazdani, Andrea Tagliasacchi
In this technical report, we investigate extending convolutional neural networks to the setting where functions are not sampled in a grid pattern.
no code implementations • NeurIPS 2020 • Xiaogang Wang, Yuelang Xu, Kai Xu, Andrea Tagliasacchi, Bin Zhou, Ali Mahdavi-Amiri, Hao Zhang
We introduce an end-to-end learnable technique to robustly identify feature edges in 3D point cloud data.
1 code implementation • NeurIPS 2020 • Emre Aksan, Thomas Deselaers, Andrea Tagliasacchi, Otmar Hilliges
We demonstrate qualitatively and quantitatively that our proposed approach is able to model the appearance of individual strokes, as well as the compositional structure of larger diagram drawings.
1 code implementation • 14 Jun 2020 • Chiyu "Max" Jiang, Jingwei Huang, Andrea Tagliasacchi, Leonidas Guibas
We illustrate the effectiveness of this learned deformation space for various downstream applications, including shape generation via deformation, geometric style transfer, unsupervised learning of a consistent parameterization for entire classes of shapes, and shape interpolation.
no code implementations • CVPR 2020 • Danhang Tang, Saurabh Singh, Philip A. Chou, Christian Haene, Mingsong Dou, Sean Fanello, Jonathan Taylor, Philip Davidson, Onur G. Guleryuz, yinda zhang, Shahram Izadi, Andrea Tagliasacchi, Sofien Bouaziz, Cem Keskin
We describe a novel approach for compressing truncated signed distance fields (TSDF) stored in 3D voxel grids, and their corresponding textures.
no code implementations • 6 Apr 2020 • Timothy Jeruzalski, David I. W. Levin, Alec Jacobson, Paul Lalonde, Mohammad Norouzi, Andrea Tagliasacchi
In this technical report, we investigate efficient representations of articulated objects (e. g. human bodies), which is an important problem in computer vision and graphics.
no code implementations • 8 Dec 2019 • Francis Williams, Daniele Panozzo, Kwang Moo Yi, Andrea Tagliasacchi
Voronoi diagrams are highly compact representations that are used in various Graphics applications.
no code implementations • 6 Dec 2019 • Boyang Deng, JP Lewis, Timothy Jeruzalski, Gerard Pons-Moll, Geoffrey Hinton, Mohammad Norouzi, Andrea Tagliasacchi
Efficient representation of articulated objects such as human bodies is an important problem in computer vision and graphics.
3 code implementations • CVPR 2020 • Zhiqin Chen, Andrea Tagliasacchi, Hao Zhang
The network is trained to reconstruct a shape using a set of convexes obtained from a BSP-tree built on a set of planes.
no code implementations • 25 Sep 2019 • Baptiste Angles, Simon Kornblith, Shahram Izadi, Andrea Tagliasacchi, Kwang Moo Yi
We propose a deep network that can be trained to tackle image reconstruction and classification problems that involve detection of multiple object instances, without any supervision regarding their whereabouts.
no code implementations • CVPR 2020 • Boyang Deng, Kyle Genova, Soroosh Yazdani, Sofien Bouaziz, Geoffrey Hinton, Andrea Tagliasacchi
We introduce a network architecture to represent a low dimensional family of convexes.
1 code implementation • CVPR 2020 • Weiwei Sun, Wei Jiang, Eduard Trulls, Andrea Tagliasacchi, Kwang Moo Yi
Many problems in computer vision require dealing with sparse, unordered data in the form of point clouds.
no code implementations • CVPR 2019 • Rohit Pandey, Anastasia Tkach, Shuoran Yang, Pavel Pidlypenskyi, Jonathan Taylor, Ricardo Martin-Brualla, Andrea Tagliasacchi, George Papandreou, Philip Davidson, Cem Keskin, Shahram Izadi, Sean Fanello
The key insight is to leverage previously seen "calibration" images of a given user to extrapolate what should be rendered in a novel viewpoint from the data available in the sensor.
1 code implementation • ICCV 2019 • Wei Jiang, Weiwei Sun, Andrea Tagliasacchi, Eduard Trulls, Kwang Moo Yi
We propose a novel image sampling method for differentiable image transformation in deep neural networks.
1 code implementation • 26 Nov 2018 • Baptiste Angles, Yuhe Jin, Simon Kornblith, Andrea Tagliasacchi, Kwang Moo Yi
We propose a deep network that can be trained to tackle image reconstruction and classification problems that involve detection of multiple object instances, without any supervision regarding their whereabouts.
Anomaly Detection In Surveillance Videos
Image Reconstruction
no code implementations • ICLR 2018 • Fabrizio Pedersoli, George Tzanetakis, Andrea Tagliasacchi
Binary Deep Neural Networks (BDNNs) have been shown to be an effective way of achieving this objective.
no code implementations • 16 Nov 2017 • Abhishake Kumar Bojja, Franziska Mueller, Sri Raghu Malireddi, Markus Oberweger, Vincent Lepetit, Christian Theobalt, Kwang Moo Yi, Andrea Tagliasacchi
We propose an automatic method for generating high-quality annotations for depth-based hand segmentation, and introduce a large-scale hand segmentation dataset.
1 code implementation • ICCV 2017 • Edoardo Remelli, Anastasia Tkach, Andrea Tagliasacchi, Mark Pauly
We present a robust algorithm for personalizing a sphere-mesh tracking model to a user from a collection of depth measurements.
1 code implementation • 19 May 2017 • Fabrizio Pedersoli, George Tzanetakis, Andrea Tagliasacchi
In this paper, we show how Convolutional Neural Networks (CNNs) can be implemented using binary representations.