Search Results for author: Patrick Perez

Found 17 papers, 6 papers with code

Regularizing Self-supervised 3D Scene Flows with Surface Awareness and Cyclic Consistency

1 code implementation12 Dec 2023 Patrik Vacek, David Hurych, Karel Zimmermann, Patrick Perez, Tomas Svoboda

Learning without supervision how to predict 3D scene flows from point clouds is essential to many perception systems.

Scene Flow Estimation

PointBeV: A Sparse Approach to BeV Predictions

1 code implementation1 Dec 2023 Loick Chambon, Eloi Zablocki, Mickael Chen, Florent Bartoccioni, Patrick Perez, Matthieu Cord

To address this, we propose PointBeV, a novel sparse BeV segmentation model operating on sparse BeV cells instead of dense grids.

Bird's-Eye View Semantic Segmentation

ToddlerDiffusion: Flash Interpretable Controllable Diffusion Model

no code implementations24 Nov 2023 Eslam Mohamed BAKR, Liangbing Zhao, Vincent Tao Hu, Matthieu Cord, Patrick Perez, Mohamed Elhoseiny

Diffusion-based generative models excel in perceptually impressive synthesis but face challenges in interpretability.

Denoising Image Generation

Teachers in concordance for pseudo-labeling of 3D sequential data

1 code implementation13 Jul 2022 Awet Haileslassie Gebrehiwot, Patrik Vacek, David Hurych, Karel Zimmermann, Patrick Perez, Tomáš Svoboda

We propose to leverage sequences of point clouds to boost the pseudolabeling technique in a teacher-student setup via training multiple teachers, each with access to different temporal information.

3D Object Detection 3D Semantic Segmentation +3

Effective Uncertainty Estimation with Evidential Models for Open-World Recognition

no code implementations29 Sep 2021 Charles Corbière, Marc Lafon, Nicolas Thome, Matthieu Cord, Patrick Perez

A crucial property of KLoS is to be a class-wise divergence measure built from in-distribution samples and to not require OOD training data, in contrast to current second-order uncertainty measures.

Learning how to be robust: Deep polynomial regression

no code implementations17 Apr 2018 Juan-Manuel Perez-Rua, Tomas Crivelli, Patrick Bouthemy, Patrick Perez

We bypass the need for a tailored loss function on the regression parameters by attaching to our model a differentiable hard-wired decoder corresponding to the polynomial operation at hand.

regression Video Stabilization

Structural inpainting

no code implementations27 Mar 2018 Huy V. Vo, Ngoc Q. K. Duong, Patrick Perez

Scene-agnostic visual inpainting remains very challenging despite progress in patch-based methods.

Adversarial Frontier Stitching for Remote Neural Network Watermarking

1 code implementation6 Nov 2017 Erwan Le Merrer, Patrick Perez, Gilles Trédan

The state of the art performance of deep learning models comes at a high cost for companies and institutions, due to the tedious data collection and the heavy processing requirements.

Cryptography and Security

Kernel Square-Loss Exemplar Machines for Image Retrieval

no code implementations CVPR 2017 Rafael S. Rezende, Joaquin Zepeda, Jean Ponce, Francis Bach, Patrick Perez

Zepeda and Perez have recently demonstrated the promise of the exemplar SVM (ESVM) as a feature encoder for image retrieval.

Image Retrieval Retrieval

Determining Occlusions From Space and Time Image Reconstructions

no code implementations CVPR 2016 Juan-Manuel Perez-Rua, Tomas Crivelli, Patrick Bouthemy, Patrick Perez

With this in mind, we propose a novel approach to occlusion detection where visibility or not of a point in next frame is formulated in terms of visual reconstruction.

Automatic Face Reenactment

no code implementations CVPR 2014 Pablo Garrido, Levi Valgaerts, Ole Rehmsen, Thorsten Thormaehlen, Patrick Perez, Christian Theobalt

We propose an image-based, facial reenactment system that replaces the face of an actor in an existing target video with the face of a user from a source video, while preserving the original target performance.

Clustering Face Model +4

Exemplar SVMs as Visual Feature Encoders

no code implementations CVPR 2015 Joaquin Zepeda, Patrick Perez

In this work, we investigate the use of exemplar SVMs (linear SVMs trained with one positive example only and a vast collection of negative examples) as encoders that turn generic image features into new, task-tailored features.

Image Classification Image Retrieval +1

Hybrid multi-layer Deep CNN/Aggregator feature for image classification

no code implementations13 Mar 2015 Praveen Kulkarni, Joaquin Zepeda, Frederic Jurie, Patrick Perez, Louis Chevallier

A second variant of our approach that includes the fully connected DCNN layers significantly outperforms Fisher vector schemes and performs comparably to DCNN approaches adapted to Pascal VOC 2007, yet at only a small fraction of the training and testing cost.

Classification General Classification +1

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