Search Results for author: Julian Straub

Found 21 papers, 6 papers with code

OrienterNet: Visual Localization in 2D Public Maps with Neural Matching

no code implementations CVPR 2023 Paul-Edouard Sarlin, Daniel DeTone, Tsun-Yi Yang, Armen Avetisyan, Julian Straub, Tomasz Malisiewicz, Samuel Rota Bulo, Richard Newcombe, Peter Kontschieder, Vasileios Balntas

We bridge this gap by introducing OrienterNet, the first deep neural network that can localize an image with sub-meter accuracy using the same 2D semantic maps that humans use.

Visual Localization

Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild

1 code implementation CVPR 2023 Garrick Brazil, Abhinav Kumar, Julian Straub, Nikhila Ravi, Justin Johnson, Georgia Gkioxari

In 3D, existing benchmarks are small in size and approaches specialize in few object categories and specific domains, e. g. urban driving scenes.

3D Object Detection 3D Object Recognition

Nerfels: Renderable Neural Codes for Improved Camera Pose Estimation

no code implementations4 Jun 2022 Gil Avraham, Julian Straub, Tianwei Shen, Tsun-Yi Yang, Hugo Germain, Chris Sweeney, Vasileios Balntas, David Novotny, Daniel DeTone, Richard Newcombe

This paper presents a framework that combines traditional keypoint-based camera pose optimization with an invertible neural rendering mechanism.

Neural Rendering Pose Estimation

ODAM: Object Detection, Association, and Mapping using Posed RGB Video

1 code implementation ICCV 2021 Kejie Li, Daniel DeTone, Steven Chen, Minh Vo, Ian Reid, Hamid Rezatofighi, Chris Sweeney, Julian Straub, Richard Newcombe

Localizing objects and estimating their extent in 3D is an important step towards high-level 3D scene understanding, which has many applications in Augmented Reality and Robotics.

3D Object Detection object-detection +1

FroDO: From Detections to 3D Objects

no code implementations11 May 2020 Kejie Li, Martin Rünz, Meng Tang, Lingni Ma, Chen Kong, Tanner Schmidt, Ian Reid, Lourdes Agapito, Julian Straub, Steven Lovegrove, Richard Newcombe

We introduce FroDO, a method for accurate 3D reconstruction of object instances from RGB video that infers object location, pose and shape in a coarse-to-fine manner.

3D Reconstruction Object Reconstruction +1

Analyzing Visual Representations in Embodied Navigation Tasks

no code implementations12 Mar 2020 Erik Wijmans, Julian Straub, Dhruv Batra, Irfan Essa, Judy Hoffman, Ari Morcos

Recent advances in deep reinforcement learning require a large amount of training data and generally result in representations that are often over specialized to the target task.

Reinforcement Learning (RL)

Insights on Visual Representations for Embodied Navigation Tasks

no code implementations ICLR 2020 Erik Wijmans, Julian Straub, Irfan Essa, Dhruv Batra, Judy Hoffman, Ari Morcos

Surprisingly, we find that slight differences in task have no measurable effect on the visual representation for both SqueezeNet and ResNet architectures.

StereoDRNet: Dilated Residual Stereo Net

no code implementations3 Apr 2019 Rohan Chabra, Julian Straub, Chris Sweeney, Richard Newcombe, Henry Fuchs

We propose a system that uses a convolution neural network (CNN) to estimate depth from a stereo pair followed by volumetric fusion of the predicted depth maps to produce a 3D reconstruction of a scene.

3D Reconstruction

DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation

4 code implementations CVPR 2019 Jeong Joon Park, Peter Florence, Julian Straub, Richard Newcombe, Steven Lovegrove

In this work, we introduce DeepSDF, a learned continuous Signed Distance Function (SDF) representation of a class of shapes that enables high quality shape representation, interpolation and completion from partial and noisy 3D input data.

3D Reconstruction 3D Shape Representation

Bayesian Nonparametric Modeling of Driver Behavior using HDP Split-Merge Sampling Algorithm

no code implementations27 Jan 2018 Vadim Smolyakov, Julian Straub, Sue Zheng, John W. Fisher III

In a novel manner, we demonstrate how the sparsity of the personal road network of a driver in conjunction with a hierarchical topic model allows data driven predictions about destinations as well as likely road conditions.

Direction-Aware Semi-Dense SLAM

no code implementations18 Sep 2017 Julian Straub, Randi Cabezas, John Leonard, John W. Fisher III

To aide simultaneous localization and mapping (SLAM), future perception systems will incorporate forms of scene understanding.

Scene Understanding Segmentation +1

Small-Variance Nonparametric Clustering on the Hypersphere

no code implementations CVPR 2015 Julian Straub, Trevor Campbell, Jonathan P. How, John W. Fisher III

Based on the small-variance limit of Bayesian nonparametric von-Mises-Fisher (vMF) mixture distributions, we propose two new flexible and efficient k-means-like clustering algorithms for directional data such as surface normals.

Clustering Nonparametric Clustering +1

Efficient Global Point Cloud Alignment using Bayesian Nonparametric Mixtures

no code implementations CVPR 2017 Julian Straub, Trevor Campbell, Jonathan P. How, John W. Fisher III

Point cloud alignment is a common problem in computer vision and robotics, with applications ranging from 3D object recognition to reconstruction.

3D Object Recognition

Semantically-Aware Aerial Reconstruction From Multi-Modal Data

no code implementations ICCV 2015 Randi Cabezas, Julian Straub, John W. Fisher III

We consider a methodology for integrating multiple sensors along with semantic information to enhance scene representations.

A Mixture of Manhattan Frames: Beyond the Manhattan World

no code implementations CVPR 2014 Julian Straub, Guy Rosman, Oren Freifeld, John J. Leonard, John W. Fisher III

Traditional approaches to scene representation exploit this phenomenon via the somewhat restrictive assumption that every plane is perpendicular to one of the axes of a single coordinate system.

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