I am a Research Scientist at Google Zurich, working on Machine Learning for visual recognition. Before that I was a post-doc at the Computer Vision Lab at EPFL in Lausanne, Switzerland, working with Pascal Fua. I obtained my PhD from the Institute of Robotics in Barcelona, Spain, co-advised by Francesc Moreno and Alberto Sanfeliu. Before my PhD I worked in mobile robotics.

News

December 2023: Received outstanding reviewer award for NeurIPS'23 (3/3 this year).
November 2023: Published PointNeRF++ to arxiv.
October 2023: Received outstanding reviewer award for ICCV'23.
July 2023: Serving as Senior PC member for AAAI'24 and AC for 3DV'24.
July 2023: GECCO accepted at ICCV'23.
June 2023: Received outstanding reviewer award for CVPR'23.
June 2023: Published SNAP to arxiv.
June 2023: Held the 2023 Image Matching Workshop.
April 2023: Launched the 2023 Image Matching Challenge at Kaggle.
March 2023: Published GECCO to arxiv.
June 2022: Published TUSK paper on arXiv.

Publications

Note: The top computer vision conferences (CVPR, ICCV, ECCV) are highly competitive, with low acceptance rates: 25%. You might be interested in the Google Scholar Metrics.

PointNeRF++: A multi-scale, point-based Neural Radiance Field

Weiwei Sun, Eduard Trulls, Yang-Che Tseng, Sneha Sambandam, Gopal Sharma, Andrea Tagliasacchi, Kwang Moo Yi

In arXiv, 2023

SNAP: Self-Supervised Neural Maps for Visual Positioning and Semantic Understanding

Paul-Edouard Sarlin, Eduard Trulls, Marc Pollefeys, Jan Hosang, Simon Lynen

In NeurIPS, 2023

GECCO: Geometrically-Conditioned Point Diffusion Models

Michał J. Tyszkiewicz, Pascal Fua, Eduard Trulls

In ICCV, 2023

TUSK: Task-Agnostic Unsupervised Keypoints

Yuhe Jin, Weiwei Sun, Jan Hosang, Eduard Trulls, Kwang Moo Yi

In NeurIPS, 2022

COTR: Correspondence Transformer for Matching Across Images

Wei Jiang, Eduard Trulls, Jan Hosang, Andrea Tagliasacchi, Kwang Moo Yi

In ICCV, 2021 (oral)

DISK: Learning local features with policy gradient

Michał J. Tyszkiewicz, Pascal Fua, Eduard Trulls

NeurIPS, 2020 (spotlight oral)

Image Matching across Wide Baselines: from Paper to Practice

Yuhe Jin, Dmytro Mishkin, Anastasiia Mishchuck, Jiri Matas, Pascal Fua, Kwang Moo Yi, Eduard Trulls

IJCV, 2020

Attentive Context Normalization for Robust Permutation-Equivariant Learning

Weiwei Sun, Wei Jiang, Eduard Trulls, Andrea Tagliasacchi, Kwang Moo Yi

In CVPR, 2020

Beyond Cartesian Representations for Local Descriptors

Patrick Ebel, Anastasiia Mishchuk, Kwang Moo Yi, Pascal Fua, Eduard Trulls

In ICCV, 2019

Linearized Multi-Sampling for Differentiable Image Transformation

Wei Jiang, Weiwei Sun, Andrea Tagliasacchi, Eduard Trulls, Kwang Moo Yi

In ICCV, 2019 (oral)

LF-Net: Learning Local Features from Images

Yuki Ono, Eduard Trulls, Pascal Fua, Kwang Moo Yi

NeurIPS, 2018

code / poster

Learning to Find Good Correspondences

Kwang Moo Yi(*), Eduard Trulls(*), Yuki Ono, Mathieu Salzmann, Vincent Lepetit, Pascal Fua (*: equal contribution)

Computer Vision and Pattern Recognition (CVPR), 2018 (oral presentation: 2.1% acceptance rate)

code / poster / slides

LIFT: Learned Invariant Feature Transform

Kwang Moo Yi(*), Eduard Trulls(*), Vincent Lepetit, Pascal Fua (*: equal contribution)

European Conference on Computer Vision (ECCV), 2016

code (tf) / code (theano, deprecated) / poster / video / supplemental

Learning to Match Aerial Images with Deep Attentive Architectures

Hani Altwaijry, Eduard Trulls, James Hays, Pascal Fua, Serge Belongie

Conference on Computer Vision and Pattern Recognition (CVPR), 2016

poster

Dense Segmentation-aware Descriptors

Eduard Trulls, Iasonas Kokkinos, Alberto Sanfeliu and Francesc Moreno-Noguer

Chapter in Dense Image Correspondences for Computer Vision, Eds. C. Liu and T. Hassner, Springer, 2015

link

Discriminative Learning of Deep Convolutional Feature Point Descriptors

Edgar Simo-Serra(*), Eduard Trulls(*), Luis Ferraz, Iasonas Kokkinos, Pascal Fua and Francesc Moreno-Noguer (*: equal contribution)

International Conference on Computer Vision (ICCV), 2015

code / poster / supplemental / spotlight

Enhancing low-level features with mid-level cues

Eduard Trulls

PhD thesis, 2015

Segmentation-aware Deformable Part Models

Eduard Trulls, Stavros Tsogkas, Iasonas Kokkinos, Alberto Sanfeliu, Francesc Moreno-Noguer

Conference on Computer Vision and Pattern Recognition (CVPR), 2014

poster / spotlight

Dense segmentation-aware descriptors

Eduard Trulls, Iasonas Kokkinos, Alberto Sanfeliu, Francesc Moreno-Noguer

Conference on Computer Vision and Pattern Recognition (CVPR), 2013

code / poster / spotlight

Spatiotemporal descriptor for wide-baseline stereo reconstruction of non-rigid and ambiguous scenes

Eduard Trulls, Alberto Sanfeliu, Francesc Moreno-Noguer

European Conference on Computer Vision (ECCV), 2012

poster / spotlight

Autonomous navigation for mobile service robots in urban pedestrian environments

Eduar Trulls, Andreu Corominas Murtra, Joan Pérez-Ibarz, Gonzalo Ferrer, Dizan Vasquez, Josep Maria Mirats-Tur, Alberto Sanfeliu

Journal of Field Robotics, 2011

Efficient use of 3D environment models for mobile robot simulation and localization

Andreu Corominas Murtra, Eduard Trulls, Josep Maria Mirats-Tur, Alberto Sanfeliu

International Conference on Simulation, Modelling, and Programming for Autonomous Robots (SIMPAR), 2010. Also in Simulation, Modelling, and Programming for Autonomous Robots, Lecture Notes in Computer Science, 2010.