I am a senior research scientist and engineer at Adobe Research. My research interests lie in computer vision and machine learning; my focus is in learning and using priors from natural images. At Adobe, I worked on Dimension's match image perspective and lighting technologies.
I received my Ph.D. from the Computer Vision and Systems Laboratory of Laval University under the supervision of Jean-François Lalonde and Paulo Gotardo.
I can be reached by email at holdgeof@ad*be.com.
Snapshot polarimetric diffuse-specular separation
Guided Co-Modulated GAN for 360° Field of View Extrapolation
Material Swapping for 3D Scenes using a Learnt Material Similarity Measure
PhotoScene: Photorealistic Material and Lighting Transfer for Indoor Scenes
Temporally Consistent Relighting for Portrait Videos
NeuTex: Neural Texture Mapping for Volumetric Neural Rendering
Deep Reflectance Volumes: Relightable Reconstructions from Multi-View Photometric Images
Deep Multi Depth Panoramas for View Synthesis
Single View Metrology in the Wild
LandscapeAR: Large Scale Outdoor Augmented Reality by Matching Photographs with Terrain Models Using Learned Descriptors
RGB2AO: Ambient Occlusion Generation from RGB Images
AutoToon: Automatic Geometric Warping for Face Cartoon Generation
Single Day Outdoor Photometric Stereo
Deep Parametric Indoor Lighting Estimation
Deep Sky Modeling for Single Image Outdoor Lighting Estimation
All-Weather Deep Outdoor Lighting Estimation
A Perceptual Measure for Deep Single Image Camera Calibration
Deep Outdoor Illumination Estimation
x-hour Outdoor Photometric Stereo
What Is a Good Day for Outdoor Photometric Stereo?