Alexandre Chapiro
San Carlos, California, United States
1K followers
500 connections
About
I am a Research Scientist in Reality Labs at Meta. My background is mainly on applied…
Activity
-
Feeling anxious about the future of AI? Let's talk about it… I stumbled upon this anti-electricity propaganda from the 1900s. It hit me: we're…
Feeling anxious about the future of AI? Let's talk about it… I stumbled upon this anti-electricity propaganda from the 1900s. It hit me: we're…
Liked by Alexandre Chapiro
-
Belen Masia del grupo de investigación Graphics and Imaging Lab 🗣️ "Que se utilice lo que has creado e investigado es muy…
Belen Masia del grupo de investigación Graphics and Imaging Lab 🗣️ "Que se utilice lo que has creado e investigado es muy…
Liked by Alexandre Chapiro
-
Hi, LinkedIn network — long time, no talk! I want to take the time to share my recent work and also add my contribution to the wealth of posts I’ve…
Hi, LinkedIn network — long time, no talk! I want to take the time to share my recent work and also add my contribution to the wealth of posts I’ve…
Liked by Alexandre Chapiro
Experience
Education
-
Eidgenössische Technische Hochschule Zürich
-
I completed my PhD at the Computer Graphics Lab at ETHZ, advised by Prof. Markus Gross. My thesis focused on algorithmic and perceptual techniques leveraged to improve user experience with novel displays. In particular, my work touches on applied perception, 3D and multiview displays and HDR capture and display.
For the duration of my PhD I have worked at the industrial Disney Research Zurich laboratory as a research assistant, where I was mentored by Dr. Aljoscha Smolic. During this…I completed my PhD at the Computer Graphics Lab at ETHZ, advised by Prof. Markus Gross. My thesis focused on algorithmic and perceptual techniques leveraged to improve user experience with novel displays. In particular, my work touches on applied perception, 3D and multiview displays and HDR capture and display.
For the duration of my PhD I have worked at the industrial Disney Research Zurich laboratory as a research assistant, where I was mentored by Dr. Aljoscha Smolic. During this time, I worked on a number of projects based on technological needs of business units and generated four patent applications. -
-
I completed a master's degree in applied mathematics with a focus on computer graphics at the Institute of Pure and Applied Mathematics in Rio de Janeiro. My thesis was focused on capturing HDR video using a cellphone.
-
-
I completed a bachelor's degree in Mathematics at the Federal University of Juiz de Fora (UFJF). During my undergraduate career, I co-authored two research papers presenting novel results on image processing. I finished the four year undergraduate program in three years with the highest GPA in the graduating class.
Publications
-
ColorVideoVDP: A visual difference predictor for image, video and display distortions
SIGGRAPH
This paper continues our research into perceptual video difference metrics. ColorVideoVDP is the first fully spatio-temporal color-aware metric. It models display geometry and photometry, produces an output in interpretable just-objectionable-difference units, and runs fast. Code is available on GitHub, and extensive documentation and comparisons with other methods in the literature can be seen on the project page.
Other authorsSee publication -
PEA-PODs: Perceptual Evaluation of Algorithms for Power Optimization in XR Displays
SIGGRAPH
In this work we explored several perceptual algorithms (PEAs) for power optimization of displays (PODs). Different methods may introduce alterations of different types, and save more or less power depending on the display technology. We compare like-to-like in a user study, obtaining interpretable results for perceptually subtle breakpoints on how much display power can be saved across a wide range of technologies: LCD, OLED, with or without eye tracking, and more.
Other authorsSee publication -
castleCSF — A contrast sensitivity function of color, area, spatiotemporal frequency, luminance and eccentricity
Journal of Vision
We followed up on our work unifying contrast sensitivity datasets from the literature by integrating color. This extends our data-driven CSF model to now cover color, area, spatiotemporal frequency, luminance and eccentricity. Our model performs better than any existing work, and importantly covers critical perceptual parameters necessary for display engineering and computer graphics tasks. Data, code, and additional information available on our project page.
Other authorsSee publication -
Visible Difference Predictors: A Class of Perception-Based Metrics
Society for Information Display
This short paper and presentation given at SID Display Week 2024 in San Jose gives a quick overview of different aspects of image/video difference metrics, and some of the philosophy behind our work on VDP metrics, in particular ColorVideoVDP.
Other authorsSee publication -
Perceptually Adaptive Real-Time Tone Mapping
SIGGRAPH Asia 2023
We created a perceptual framework that determines the optimal parameters for a tone mapper in real time (>1ms per frame on Quest2). We use this system and the Starburst HDR VR prototype to demonstrate that content shown with an optimized version of the Photographic TMO is preferred to heuristics or unoptimized versions even when display luminance is reduced tenfold.
Other authorsSee publication -
Skin-Screen: A Computational Fabrication Framework for Color Tattoos
SIGGRAPH 2023
In this work, we examined tattoos through the lens of computational fabrication. To build our model, we created an automatic tattoo robot, and processes to generate synthetic skins to experiment on. We created a framework to predict and modify tattoo color for different skin tones, which we hope will lead to better tattoo quality for everyone. This work also has medical and robotics applications!
Other authorsSee publication -
Geo-metric: A Perceptual Dataset of Distortions on Faces
SIGGRAPH Asia 2022
We study the perception of geometric distortions. We create a novel demographically-balanced dataset of human faces, and find the perceived magnitudes of several relevant distortions through a large-scale subjective study.
Other authorsSee publication -
Realistic Luminance in VR
SIGGRAPH Asia 2022
We used the Starburst HDR VR 20,000 nits prototype display to run a study measuring user preferences for realism when immersed in natural scenes. We found that user preference extends beyond what is available in VR today, and changes significantly between indoor and outdoor scenes.
Other authorsSee publication -
stelaCSF-A Unified Model of Contrast Sensitivity as the Function of Spatio-Temporal Frequency, Eccentricity, Luminance and Area
ACM SIGGRAPH
We unified contrast sensitivity datasets from the literature, which allowed us to create the most comprehensive and precise CSF model to date. This new model can be used to improve many applications in visual computing, such as metrics. Data, code, and additional information available on our project page.
Other authorsSee publication -
FovVideoVDP: A Visible Difference Predictor for Wide Field-of-View Video
ACM SIGGRAPH
We created a new foveated spatiotemporal metric, following the VDP line of work. This metric is fast, easy to use and has been carefully calibrated on several large datasets.
-
A Luminance-Aware Model of Judder Perception
ACM Transactions on Graphics (TOG/SIGGRAPH)
We created and validated a perceptual model of judder (non-smooth motion) based on its principal influencing components.
Other authorsSee publication -
Influence of Screen Size and Field of View on Perceived Brightness
ACM Transactions on Applied Perception
We studied the influence of screen size and distance on perceived brightness for screens as large as cinema and as small as mobile phones, an issue that affects artistic intent and appearance matching.
Other authorsSee publication -
Art-Directable Continuous Dynamic Range Video
Computers & Graphics
We defined the production and distribution challenges facing the content creation industry in the current HDR landscape and proposed Continuous Dynamic Range video as a solution.
Other authorsSee publication -
Stereo from Shading
Proceedings of Eurographics Symposium on Rendering
We use non-photorealistic shading as an alternative 3D cue, augmenting the feeling of depth in stereoscopic images.
Other authorsSee publication -
Unfolding the 8-Bit Era
European Conference on Visual Media Production
We created an immersive gaming system out of a legacy console.
This work received wide media attention and was presented at the Ludicious game festival in Zurich.Other authorsSee publication -
Video Content and Structure Description Based on Keyframes, Clusters and Storyboards
IEEE International Workshop on Multimedia Signal Processing
We developed a pipeline to segment and analyze video. Our technique could be applied for smarter editing.
Other authorsSee publication -
Optimizing stereo-to-multiview conversion for autostereoscopic displays
Eurographics
We measured perceptual aspects of autostereo content and created a depth re-mapping algorithm that tries to optimize content so that the most important regions have a fuller sense of depth while staying within the limits of the technology.
Other authorsSee publication -
Perceptual evaluation of cardboarding in 3D content visualization
Proceedings of the ACM Symposium on Applied Perception
We conducted perceptual experiments to quantify cardboarding - an artifact that occurs when not enough depth is given to a stereoscopic 3D image region.
Other authorsSee publication -
Towards Mobile HDR Video
Eurographics (extended abstract)
We created a capture and processing pipeline to generate HDR video on a mobile phone by taking sequential multiple exposures.
Other authorsSee publication -
Detection of High Frequency Regions in Multiresolution
ICIP - International Conference on Image Processing
-
High Frequency Assessment from Multiresolution Analysis
ICCS - International Conference on Computational Science
We detected high frequencies using an orientation tensor and multiresolution.
Other authorsSee publication
Languages
-
Russian
Native or bilingual proficiency
-
Spanish
Full professional proficiency
-
Portuguese
Native or bilingual proficiency
-
French
Limited working proficiency
-
English
Native or bilingual proficiency
More activity by Alexandre
-
Super Pumped to join the AR Alliance as a founding member, with an objective to unify the best brains in the market to advance the state of art of AR…
Super Pumped to join the AR Alliance as a founding member, with an objective to unify the best brains in the market to advance the state of art of AR…
Liked by Alexandre Chapiro
-
Welcome Qualcomm to the AR Alliance! Delighted to have Qualcomm bring their leadership and deep experiences to the organization and very excited to…
Welcome Qualcomm to the AR Alliance! Delighted to have Qualcomm bring their leadership and deep experiences to the organization and very excited to…
Liked by Alexandre Chapiro
-
🚀 Exciting News! 🚀 Check out my new personal website: https://lnkd.in/gDVe6zqV. I'm gearing up to graduate in December 2024 and am actively seeking…
🚀 Exciting News! 🚀 Check out my new personal website: https://lnkd.in/gDVe6zqV. I'm gearing up to graduate in December 2024 and am actively seeking…
Liked by Alexandre Chapiro
-
"Human visual perception, they concluded, is a key component for crafting next-generation AR displays and visual-experience design, focusing on the…
"Human visual perception, they concluded, is a key component for crafting next-generation AR displays and visual-experience design, focusing on the…
Liked by Alexandre Chapiro
-
The AR Alliance is preparing webinars for fall! Which webinar topics interest you most? #AR #VR #MR #Technology #AugmentedReality #TechnologyWebinar…
The AR Alliance is preparing webinars for fall! Which webinar topics interest you most? #AR #VR #MR #Technology #AugmentedReality #TechnologyWebinar…
Liked by Alexandre Chapiro
-
We’re thrilled to announce Moritz Bächer, Associate Lab Director of Disney’s Zurich-based robotics team, as a keynote speaker for DDAC 2024! Moritz…
We’re thrilled to announce Moritz Bächer, Associate Lab Director of Disney’s Zurich-based robotics team, as a keynote speaker for DDAC 2024! Moritz…
Liked by Alexandre Chapiro
-
A conferência “Grupo de Interesse Especial em Gráficos e Técnicas Interativas” (SIGGRAPH, na sigla em inglês) terminou em 1º de agosto com resultados…
A conferência “Grupo de Interesse Especial em Gráficos e Técnicas Interativas” (SIGGRAPH, na sigla em inglês) terminou em 1º de agosto com resultados…
Liked by Alexandre Chapiro
-
Oportunidade no IMPA! ✅🥳 O IMPA está com uma vaga aberta para pesquisador especializado em matemática pura, aplicada ou industrial. A posição é…
Oportunidade no IMPA! ✅🥳 O IMPA está com uma vaga aberta para pesquisador especializado em matemática pura, aplicada ou industrial. A posição é…
Liked by Alexandre Chapiro
-
I'm glad to announce that my paper "Cascading upper bounds for triangle soup Pompeiu-Hausdorff distance," coauthored with Alec Jacobson, won the SGP…
I'm glad to announce that my paper "Cascading upper bounds for triangle soup Pompeiu-Hausdorff distance," coauthored with Alec Jacobson, won the SGP…
Liked by Alexandre Chapiro
-
The XR History Museum at AWE, showcasing 80 devices from the last 25 years. It's amazing to see where we've been, we hope to shape where we're going.…
The XR History Museum at AWE, showcasing 80 devices from the last 25 years. It's amazing to see where we've been, we hope to shape where we're going.…
Liked by Alexandre Chapiro
-
We will present two papers at SIGGRAPH in Denver today. Session: Character Animation: 2D, 3D, Robot, 10:45 am - 12:15 pm MDT --- Michael Hopkins…
We will present two papers at SIGGRAPH in Denver today. Session: Character Animation: 2D, 3D, Robot, 10:45 am - 12:15 pm MDT --- Michael Hopkins…
Liked by Alexandre Chapiro
-
This is one of the most exciting applications of research in active vision that I’ve gotten to be a part of. Here we show that we can take advantage…
This is one of the most exciting applications of research in active vision that I’ve gotten to be a part of. Here we show that we can take advantage…
Liked by Alexandre Chapiro
Other similar profiles
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore More