Search Results for author: David Novotny

Found 21 papers, 7 papers with code

Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction

1 code implementation ICCV 2021 Jeremy Reizenstein, Roman Shapovalov, Philipp Henzler, Luca Sbordone, Patrick Labatut, David Novotny

Traditional approaches for learning 3D object categories have been predominantly trained and evaluated on synthetic datasets due to the unavailability of real 3D-annotated category-centric data.

3D Reconstruction Neural Rendering

DensePose 3D: Lifting Canonical Surface Maps of Articulated Objects to the Third Dimension

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.

3D Reconstruction

Augmenting Implicit Neural Shape Representations with Explicit Deformation Fields

no code implementations19 Aug 2021 Matan Atzmon, David Novotny, Andrea Vedaldi, Yaron Lipman

Implicit neural representation is a recent approach to learn shape collections as zero level-sets of neural networks, where each shape is represented by a latent code.

NeuroMorph: Unsupervised Shape Interpolation and Correspondence in One Go

no code implementations CVPR 2021 Marvin Eisenberger, David Novotny, Gael Kerchenbaum, Patrick Labatut, Natalia Neverova, Daniel Cremers, Andrea Vedaldi

We present NeuroMorph, a new neural network architecture that takes as input two 3D shapes and produces in one go, i. e. in a single feed forward pass, a smooth interpolation and point-to-point correspondences between them.

Unsupervised Learning of 3D Object Categories from Videos in the Wild

no code implementations CVPR 2021 Philipp Henzler, Jeremy Reizenstein, Patrick Labatut, Roman Shapovalov, Tobias Ritschel, Andrea Vedaldi, David Novotny

Our goal is to learn a deep network that, given a small number of images of an object of a given category, reconstructs it in 3D.

Continuous Surface Embeddings

1 code implementation NeurIPS 2020 Natalia Neverova, David Novotny, Vasil Khalidov, Marc Szafraniec, Patrick Labatut, Andrea Vedaldi

In this work, we focus on the task of learning and representing dense correspondences in deformable object categories.

Pose Estimation

RidgeSfM: Structure from Motion via Robust Pairwise Matching Under Depth Uncertainty

1 code implementation20 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.


Canonical 3D Deformer Maps: Unifying parametric and non-parametric methods for dense weakly-supervised category reconstruction

1 code implementation NeurIPS 2020 David Novotny, Roman Shapovalov, Andrea Vedaldi

We propose the Canonical 3D Deformer Map, a new representation of the 3D shape of common object categories that can be learned from a collection of 2D images of independent objects.

3D Reconstruction

Accelerating 3D Deep Learning with PyTorch3D

3 code implementations16 Jul 2020 Nikhila Ravi, Jeremy Reizenstein, David Novotny, Taylor Gordon, Wan-Yen Lo, Justin Johnson, Georgia Gkioxari

We address these challenges by introducing PyTorch3D, a library of modular, efficient, and differentiable operators for 3D deep learning.

Autonomous Vehicles

PerspectiveNet: A Scene-consistent Image Generator for New View Synthesis in Real Indoor Environments

no code implementations NeurIPS 2019 Ben Graham, David Novotny, Jeremy Reizenstein

Given a set of a reference RGBD views of an indoor environment, and a new viewpoint, our goal is to predict the view from that location.


Correlated Uncertainty for Learning Dense Correspondences from Noisy Labels

no code implementations NeurIPS 2019 Natalia Neverova, David Novotny, Andrea Vedaldi

We show that these models, by understanding uncertainty better, can solve the original DensePose task more accurately, thus setting the new state-of-the-art accuracy in this benchmark.

C3DPO: Canonical 3D Pose Networks for Non-Rigid Structure From Motion

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.

Learning 3D Object Categories by Looking Around Them

no code implementations ICCV 2017 David Novotny, Diane Larlus, Andrea Vedaldi

Traditional approaches for learning 3D object categories use either synthetic data or manual supervision.

Data Augmentation

AnchorNet: A Weakly Supervised Network to Learn Geometry-sensitive Features For Semantic Matching

no code implementations CVPR 2017 David Novotny, Diane Larlus, Andrea Vedaldi

Despite significant progress of deep learning in recent years, state-of-the-art semantic matching methods still rely on legacy features such as SIFT or HoG.

Learning the semantic structure of objects from Web supervision

no code implementations5 Jul 2016 David Novotny, Diane Larlus, Andrea Vedaldi

While recent research in image understanding has often focused on recognizing more types of objects, understanding more about the objects is just as important.

Cascaded Sparse Spatial Bins for Efficient and Effective Generic Object Detection

no code implementations ICCV 2015 David Novotny, Jiri Matas

The efficiency is achieved by the use of spatial bins in a novel combination with sparsity-inducing group normalized SVM.

Object Detection

Cannot find the paper you are looking for? You can Submit a new open access paper.