Diego Gutiérrez
YOU?
Author Swipe
View article: Looking Around Flatland: End-to-End 2D Real-Time NLOS Imaging
Looking Around Flatland: End-to-End 2D Real-Time NLOS Imaging Open
Non-line-of-sight (NLOS) imaging methods reconstruct scenes hidden around one corner using indirect third-bounce illumination with high temporal resolution on a visible surface. Unfortunately, acquiring or simulating this information is ex…
View article: Artist‐Inator: Text‐based, Gloss‐aware Non‐photorealistic Stylization
Artist‐Inator: Text‐based, Gloss‐aware Non‐photorealistic Stylization Open
Large diffusion models have made a remarkable leap synthesizing high‐quality artistic images from text descriptions. However, these powerful pre‐trained models still lack control to guide key material appearance properties, such as gloss. …
View article: Parents’ Perspective on Multi-Grade Teaching in Tubabao Island’s Elementary Education
Parents’ Perspective on Multi-Grade Teaching in Tubabao Island’s Elementary Education Open
This research aims to explore the perspectives of parents on Multi-grade Teaching. To gather data, the researchers used a qualitative research design, specifically narrative inquiry research design. The research study takes place at the fi…
View article: Crossing Borders Without Crossing Boundaries: How Sociolinguistic Awareness Can Optimize User Engagement with Localized Spanish AI Models Across Hispanophone Countries
Crossing Borders Without Crossing Boundaries: How Sociolinguistic Awareness Can Optimize User Engagement with Localized Spanish AI Models Across Hispanophone Countries Open
Large language models are, by definition, based on language. In an effort to underscore the critical need for regional localized models, this paper examines primary differences between variants of written Spanish across Latin America and S…
View article: PreciseCam: Precise Camera Control for Text-to-Image Generation
PreciseCam: Precise Camera Control for Text-to-Image Generation Open
Images as an artistic medium often rely on specific camera angles and lens distortions to convey ideas or emotions; however, such precise control is missing in current text-to-image models. We propose an efficient and general solution that…
View article: Looking Around Flatland: End-to-End 2D Real-Time NLOS Imaging
Looking Around Flatland: End-to-End 2D Real-Time NLOS Imaging Open
Time-gated non-line-of-sight (NLOS) imaging methods reconstruct scenes hidden around a corner by inverting the optical path of indirect photons measured at visible surfaces. These methods are, however, hindered by intricate, time-consuming…
View article: Polarimetric BSSRDF Acquisition of Dynamic Faces
Polarimetric BSSRDF Acquisition of Dynamic Faces Open
Acquisition and modeling of polarized light reflection and scattering help reveal the shape, structure, and physical characteristics of an object, which is increasingly important in computer graphics. However, current polarimetric acquisit…
View article: TexSliders: Diffusion-Based Texture Editing in CLIP Space
TexSliders: Diffusion-Based Texture Editing in CLIP Space Open
Generative models have enabled intuitive image creation and manipulation using natural language. In particular, diffusion models have recently shown remarkable results for natural image editing. In this work, we propose to apply diffusion …
View article: Predicting Perceived Gloss: Do Weak Labels Suffice?
Predicting Perceived Gloss: Do Weak Labels Suffice? Open
Estimating perceptual attributes of materials directly from images is a challenging task due to their complex, not fully‐understood interactions with external factors, such as geometry and lighting. Supervised deep learning models have rec…
View article: Real‐Time Underwater Spectral Rendering
Real‐Time Underwater Spectral Rendering Open
The light field in an underwater environment is characterized by complex multiple scattering interactions and wavelength‐dependent attenuation, requiring significant computational resources for the simulation of underwater scenes. We prese…
View article: Predicting Perceived Gloss: Do Weak Labels Suffice?
Predicting Perceived Gloss: Do Weak Labels Suffice? Open
Estimating perceptual attributes of materials directly from images is a challenging task due to their complex, not fully-understood interactions with external factors, such as geometry and lighting. Supervised deep learning models have rec…
View article: Modeling the Impact of Head-Body Rotations on Audio-Visual Spatial Perception for Virtual Reality Applications
Modeling the Impact of Head-Body Rotations on Audio-Visual Spatial Perception for Virtual Reality Applications Open
Humans perceive the world by integrating multimodal sensory feedback, including visual and auditory stimuli, which holds true in virtual reality (VR) environments. Proper synchronization of these stimuli is crucial for perceiving a coheren…
View article: Validation of a New Digital and Automated Color Perception Test
Validation of a New Digital and Automated Color Perception Test Open
Although color vision deficiencies are very prevalent, there are no ideal methods for assessing color vision in all environments. We compared a new digital and automated method that quantifies color perception for the three protan, deutan,…
View article: Cohesive framework for non-line-of-sight imaging based on Dirac notation
Cohesive framework for non-line-of-sight imaging based on Dirac notation Open
The non-line-of-sight (NLOS) imaging field encompasses both experimental and computational frameworks that focus on imaging elements that are out of the direct line-of-sight, for example, imaging elements that are around a corner. Current …
View article: Self-Calibrating, Fully Differentiable NLOS Inverse Rendering
Self-Calibrating, Fully Differentiable NLOS Inverse Rendering Open
Existing time-resolved non-line-of-sight (NLOS) imaging methods reconstruct\nhidden scenes by inverting the optical paths of indirect illumination measured\nat visible relay surfaces. These methods are prone to reconstruction artifacts\ndu…
View article: Task-Dependent Visual Behavior in Immersive Environments: A Comparative Study of Free Exploration, Memory and Visual Search
Task-Dependent Visual Behavior in Immersive Environments: A Comparative Study of Free Exploration, Memory and Visual Search Open
Visual behavior depends on both bottom-up mechanisms, where gaze is driven by the visual conspicuity of the stimuli, and top-down mechanisms, guiding attention towards relevant areas based on the task or goal of the viewer. While this is w…
View article: D-SAV360: A Dataset of Gaze Scanpaths on 360° Ambisonic Videos
D-SAV360: A Dataset of Gaze Scanpaths on 360° Ambisonic Videos Open
Understanding human visual behavior within virtual reality environments is crucial to fully leverage their potential. While previous research has provided rich visual data from human observers, existing gaze datasets often suffer from the …
View article: Colour perception develops throughout childhood with increased risk of deficiencies in children born prematurely
Colour perception develops throughout childhood with increased risk of deficiencies in children born prematurely Open
Aim To quantify the impact of prematurity on chromatic discrimination throughout childhood, from 2 to 15 years of age. Methods We recruited two cohorts of children, as part of the TrackAI Project, an international project with seven differ…
View article: Towards latent representations of gloss in complex stimuli using unsupervised learning
Towards latent representations of gloss in complex stimuli using unsupervised learning Open
Our visual perception of the world is strongly influenced by material appearance. Humans can easily recognize and discriminate materials, despite the influence on their final appearance of confounding factors such as illumination or surfac…
View article: Virtual Mirrors: Non-Line-of-Sight Imaging Beyond the Third Bounce
Virtual Mirrors: Non-Line-of-Sight Imaging Beyond the Third Bounce Open
Non-line-of-sight (NLOS) imaging methods are capable of reconstructing complex scenes that are not visible to an observer using indirect illumination. However, they assume only third-bounce illumination, so they are currently limited to si…
View article: The Visual Language of Fabrics
The Visual Language of Fabrics Open
We introduce text2fabric, a novel dataset that links free-text descriptions to various fabric materials. The dataset comprises 15,000 natural language descriptions associated to 3,000 corresponding images of fabric materials. Traditionally…
View article: Virtual Mirrors: Non-Line-of-Sight Imaging Beyond the Third Bounce
Virtual Mirrors: Non-Line-of-Sight Imaging Beyond the Third Bounce Open
Non-line-of-sight (NLOS) imaging methods are capable of reconstructing complex scenes that are not visible to an observer using indirect illumination. However, they assume only third-bounce illumination, so they are currently limited to si…
View article: The Visual Language of Fabrics
The Visual Language of Fabrics Open
We introduce text2fabric, a novel dataset that links free-text descriptions to various fabric materials. The dataset comprises 15,000 natural language descriptions associated to 3,000 corresponding images of fabric materials. Traditionally…
View article: Zone Plate Virtual Lenses for Memory-Constrained NLOS Imaging
Zone Plate Virtual Lenses for Memory-Constrained NLOS Imaging Open
Phasor Fields is a wave-based formulation that allows computing time-efficient NLOS reconstructions using Rayleigh-Sommerfeld diffraction kernels. Unfortunately, these kernels are heavy in memory, hampering the integration in memory-constr…