1 code implementation • 7 Dec 2023 • Justine Giroux, Mohammad Reza Karimi Dastjerdi, Yannick Hold-Geoffroy, Javier Vazquez-Corral, Jean-François Lalonde
Progress in lighting estimation is tracked by computing existing image quality assessment (IQA) metrics on images from standard datasets.
no code implementations • 8 May 2023 • Mohamed Abid, Arman Afrasiyabi, Ihsen Hedhli, Jean-François Lalonde, Christian Gagné
Conditioned on a target image, such methods extract the target style and combine it with the source image content, keeping coherence between the domains.
no code implementations • ICCV 2023 • Mohammad Reza Karimi Dastjerdi, Jonathan Eisenmann, Yannick Hold-Geoffroy, Jean-François Lalonde
In this work, we propose to bridge the gap between these recent trends in the literature, and propose a method which combines a parametric light model with 360{\deg} panoramas, ready to use as HDRI in rendering engines.
no code implementations • ICCV 2023 • Christophe Bolduc, Justine Giroux, Marc Hébert, Claude Demers, Jean-François Lalonde
The resulting dataset is a rich representation of indoor scenes which displays a wide range of illuminance and color, and varied types of light sources.
no code implementations • ICCV 2023 • Akshaya Athwale, Ichrak Shili, Émile Bergeron, Arman Afrasiyabi, Justin Lagüe, Ola Ahmad, Jean-François Lalonde
Wide-angle lenses are commonly used in perception tasks requiring a large field of view.
1 code implementation • CVPR 2023 • Yohan Poirier-Ginter, Jean-François Lalonde
GAN-based image restoration inverts the generative process to repair images corrupted by known degradations.
no code implementations • ICCV 2023 • Dominique Piché-Meunier, Yannick Hold-Geoffroy, Jianming Zhang, Jean-François Lalonde
Instead, we go further and propose to use a lens-based representation that models the depth of field using two parameters: the blur factor and focus disparity.
1 code implementation • CVPR 2023 • Geoffroi Côté, Fahim Mannan, Simon Thibault, Jean-François Lalonde, Felix Heide
Recently, joint optimization approaches that design lenses alongside other components of the image acquisition and processing pipeline -- notably, downstream neural networks -- have achieved improved imaging quality or better performance on vision tasks.
1 code implementation • 8 Nov 2022 • Henrique Weber, Mathieu Garon, Jean-François Lalonde
We present a method for estimating lighting from a single perspective image of an indoor scene.
no code implementations • 25 Aug 2022 • Yannick Hold-Geoffroy, Dominique Piché-Meunier, Kalyan Sunkavalli, Jean-Charles Bazin, François Rameau, Jean-François Lalonde
Image editing and compositing have become ubiquitous in entertainment, from digital art to AR and VR experiences.
no code implementations • 16 Aug 2022 • Pulkit Gera, Mohammad Reza Karimi Dastjerdi, Charles Renaud, P. J. Narayanan, Jean-François Lalonde
We present PanoHDR-NeRF, a neural representation of the full HDR radiance field of an indoor scene, and a pipeline to capture it casually, without elaborate setups or complex capture protocols.
no code implementations • 24 Jul 2022 • Bhavya Goyal, Jean-François Lalonde, Yin Li, Mohit Gupta
This creates a trade-off between these two kinds of image degradations: motion blur (due to long exposure) vs. noise (due to short exposure), also referred as a dual image corruption pair in this paper.
no code implementations • 12 May 2022 • Yohan Poirier-Ginter, Alexandre Lessard, Ryan Smith, Jean-François Lalonde
We show that this allows us to obtain near-perfect image reconstruction without the need for encoders nor for altering the latent space after training.
no code implementations • 15 Apr 2022 • Mohammad Reza Karimi Dastjerdi, Yannick Hold-Geoffroy, Jonathan Eisenmann, Siavash Khodadadeh, Jean-François Lalonde
We propose a method to extrapolate a 360{\deg} field of view from a single image that allows for user-controlled synthesis of the out-painted content.
no code implementations • CVPR 2022 • Arman Afrasiyabi, Hugo Larochelle, Jean-François Lalonde, Christian Gagné
In image classification, it is common practice to train deep networks to extract a single feature vector per input image.
1 code implementation • 26 Nov 2021 • Fabio Pizzati, Jean-François Lalonde, Raoul de Charette
To enforce feature consistency, our framework learns a style manifold between source and proxy anchor domains (assumed to be composed of large numbers of images).
1 code implementation • 23 Jul 2021 • Mohamed Abderrahmen Abid, Ihsen Hedhli, Jean-François Lalonde, Christian Gagne
This differs from previous methods that focus on translating a given image style into a target content, our translation approach being able to simultaneously imitate the style and merge the structural information of the LR target.
Ranked #5 on Image-to-Image Translation on CelebA-HQ
1 code implementation • ICCV 2021 • Arman Afrasiyabi, Jean-François Lalonde, Christian Gagné
In contrast, we propose to model base classes with mixture models by simultaneously training the feature extractor and learning the mixture model parameters in an online manner.
no code implementations • 8 Oct 2020 • Louis-Philippe Asselin, Denis Laurendeau, Jean-François Lalonde
Recent work has demonstrated that deep learning approaches can successfully be used to recover accurate estimates of the spatially-varying BRDF (SVBRDF) of a surface from as little as a single image.
no code implementations • 6 Sep 2020 • Maxime Tremblay, Shirsendu Sukanta Halder, Raoul de Charette, Jean-François Lalonde
In this context, we present a rain rendering pipeline that enables the systematic evaluation of common computer vision algorithms to controlled amounts of rain.
1 code implementation • 9 Jun 2020 • Etienne Dubeau, Mathieu Garon, Benoit Debaque, Raoul de Charette, Jean-François Lalonde
In this paper, we propose, for the first time, to use an event-based camera to increase the speed of 3D object tracking in 6 degrees of freedom.
1 code implementation • 7 Feb 2020 • Sébastien de Blois, Mathieu Garon, Christian Gagné, Jean-François Lalonde
Computer vision datasets containing multiple modalities such as color, depth, and thermal properties are now commonly accessible and useful for solving a wide array of challenging tasks.
2 code implementations • ECCV 2020 • Arman Afrasiyabi, Jean-François Lalonde, Christian Gagné
Few-shot image classification aims at training a model from only a few examples for each of the "novel" classes.
1 code implementation • 26 Nov 2019 • Jean-Philippe Mercier, Mathieu Garon, Philippe Giguère, Jean-François Lalonde
In this context, we propose a generic 2D object instance detection approach that uses example viewpoints of the target object at test time to retrieve its 2D location in RGB images, without requiring any additional training (i. e. fine-tuning) step.
no code implementations • 19 Oct 2019 • Marc-André Gardner, Yannick Hold-Geoffroy, Kalyan Sunkavalli, Christian Gagné, Jean-François Lalonde
We present a method to estimate lighting from a single image of an indoor scene.
no code implementations • ICCV 2019 • Shirsendu Sukanta Halder, Jean-François Lalonde, Raoul de Charette
Our rendering relies on a physical particle simulator, an estimation of the scene lighting and an accurate rain photometric modeling to augment images with arbitrary amount of realistic rain or fog.
no code implementations • CVPR 2019 • Jinsong Zhang, Kalyan Sunkavalli, Yannick Hold-Geoffroy, Sunil Hadap, Jonathan Eisenmann, Jean-François Lalonde
We use this network to label a large-scale dataset of LDR panoramas with lighting parameters and use them to train our single image outdoor lighting estimation network.
no code implementations • CVPR 2019 • Mathieu Garon, Kalyan Sunkavalli, Sunil Hadap, Nathan Carr, Jean-François Lalonde
We propose a real-time method to estimate spatiallyvarying indoor lighting from a single RGB image.
no code implementations • CVPR 2020 • Thomas Nestmeyer, Jean-François Lalonde, Iain Matthews, Andreas M. Lehrmann
Relighting is an essential step in realistically transferring objects from a captured image into another environment.
no code implementations • CVPR 2019 • Yannick Hold-Geoffroy, Akshaya Athawale, Jean-François Lalonde
We propose a data-driven learned sky model, which we use for outdoor lighting estimation from a single image.
1 code implementation • SIGGRAPH 2019 2019 • Ethan Tseng, Felix Yu, Yuting Yang, Fahim Mannan, Karl St. Arnaud, Derek Nowrouzezahrai, Jean-François Lalonde, Felix Heide
We present a fully automatic system to optimize the parameters of black-box hardware and software image processing pipelines according to any arbitrary (i. e., application-specific) metric.
no code implementations • 15 Oct 2018 • Jinsong Zhang, Rodrigo Verschae, Shohei Nobuhara, Jean-François Lalonde
Our experiments reveal that the MLP network, already used similarly in previous work, achieves an RMSE skill score of 7% over the commonly-used persistence baseline on the 1-minute future photovoltaic power prediction task.
1 code implementation • 3DV 2018 - International Conference on 3D Vision 2018 • Henrique Weber, Donald Prévost, Jean-François Lalonde
To achieve this, we developed a deep learning method that is able to encode the latent space of indoor lighting using few parameters and that is trained on a database of environment maps.
no code implementations • 28 Mar 2018 • Yannick Hold-Geoffroy, Paulo F. U. Gotardo, Jean-François Lalonde
Our analysis reveals that partially cloudy days improve the conditioning of the outdoor PS problem while sunny days do not allow the unambiguous recovery of surface normals from photometric cues alone.
1 code implementation • ECCV 2018 • Mathieu Garon, Denis Laurendeau, Jean-François Lalonde
We present a challenging and realistic novel dataset for evaluating 6-DOF object tracking algorithms.
no code implementations • CVPR 2018 • Yannick Hold-Geoffroy, Kalyan Sunkavalli, Jonathan Eisenmann, Matt Fisher, Emiliano Gambaretto, Sunil Hadap, Jean-François Lalonde
This network is trained using automatically generated samples from a large-scale panorama dataset, and considerably outperforms other methods, including recent deep learning-based approaches, in terms of standard L2 error.
no code implementations • 1 Apr 2017 • Marc-André Gardner, Kalyan Sunkavalli, Ersin Yumer, Xiaohui Shen, Emiliano Gambaretto, Christian Gagné, Jean-François Lalonde
We propose an automatic method to infer high dynamic range illumination from a single, limited field-of-view, low dynamic range photograph of an indoor scene.
no code implementations • ICCV 2017 • Jinsong Zhang, Jean-François Lalonde
Outdoor lighting has extremely high dynamic range.
no code implementations • 28 Mar 2017 • Mathieu Garon, Jean-François Lalonde
We present a temporal 6-DOF tracking method which leverages deep learning to achieve state-of-the-art performance on challenging datasets of real world capture.
1 code implementation • CVPR 2017 • Yannick Hold-Geoffroy, Kalyan Sunkavalli, Sunil Hadap, Emiliano Gambaretto, Jean-François Lalonde
We present a CNN-based technique to estimate high-dynamic range outdoor illumination from a single low dynamic range image.
Ranked #1 on Outdoor Light Source Estimation on SUN360