Blog | NAVER LABS Europe
31 March 2021
Methods for visual localization blog image

Methods for visual localization

Visual localization is used by robots and self-driving cars to estimate their position and in AR apps to interact with the physical world both indoors and out in the open. This article gives an overview of current state-of-the-art methods and their advantages and drawbacks.
2021
10 March 2021
podcast Matthias Galle

NAVER LABS AI research in Europe – a podcast with lab manager Matthias Gallé

Podcast and transcript of Matthias Gallé, head of the NAVER research LAB in Europe who tells us what kind of research is going on in the labs in France and what it’s like to work there.
2021
8 December 2020
Blog Image Constrastive Learning

Improving self-supervised representation learning by synthesizing challenging negatives

How harder negatives facilitate better and faster contrastive self-supervised learning and ways of synthesizing harder negative features on-the-fly.
2020
24 August 2020
Learning Visual Representations

Learning visual representations with caption annotations

How mid-size sets of captioned images can rival with large-scale labelled image sets to learn generic representations
2020
21 August 2020

DOPE: distillation of part experts for whole-body 3D pose estimation in the wild

A novel efficient model for whole-body 3D pose estimation (including bodies, hands and faces), that is trained by mimicking the output of hand-, body- and face-pose experts.
2020
12 June 2020

GanHand: estimating the pose of a hand to enable human-like robot manipulation

A first-of-its-kind architecture that, based on a single image, predicts how a robot can pick up objects from within any scene could revolutionize applications in AR/VR and robotics.
2020
10 June 2020
One Method One Pipeline Blog Image

One method, one pipeline: NAVER LABS Europe ranks high across three visual localization challenges at CVPR 2020

1st in autonomous vehicle challenge, 2nd in local feature and 4th in handheld devices R2D2 and KAPTURE demonstrate generalizability and wide variety of applications
2020
29 January 2020
Virtual Kitti 2

Announcing Virtual KITTI 2

Latest release of the popular synthetic image dataset for training and testing. New features include increased photorealism, stereo cameras and additional ground truth.
2020
4 December 2019

R2D2: Repeatable and Reliable Detector and Descriptor

Combining keypoint reliability in an image as part of the keypoint detection problem significantly improves feature matching.
2019
25 October 2019
SLAMANTIC_blog image

SLAMANTIC – Leveraging semantics to improve VSLAM in dynamic environments

Evaluating our method on public datasets, we show that it can successfully solve challenging situations in dynamic environments which cause state-of-the-art baseline VSLAM algorithms to fail and that it maintains performance on static scenes.
2019
21 October 2019

Moulding Humans

A new double depth-map representation of the human shape allows to recover 3D details from a single image. Using 2 depth maps (visible and hidden) makes representations more efficient and easier to handle.
2019
18 October 2019
Fine-grained action retrieval

Fine-grained action retrieval from video

Fine-grained action retrieval made possible thanks to a new annotated dataset and part-of-speech embedding.
2019