Search Results for author: Yannick Hold-Geoffroy

Found 34 papers, 8 papers with code

LandscapeAR: Large Scale Outdoor Augmented Reality by Matching Photographs with Terrain Models Using Learned Descriptors

1 code implementation ECCV 2020 Jan Brejcha, Michal Lukáč, Yannick Hold-Geoffroy, Oliver Wang, Martin Čadík

We introduce a solution to large scale Augmented Reality for outdoor scenes by registering camera images to textured Digital Elevation Models (DEMs).

Ranked #2 on Patch Matching on HPatches (using extra training data)

Patch Matching

PreciseCam: Precise Camera Control for Text-to-Image Generation

no code implementations22 Jan 2025 Edurne Bernal-Berdun, Ana Serrano, Belen Masia, Matheus Gadelha, Yannick Hold-Geoffroy, Xin Sun, Diego Gutierrez

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.

Prompt Engineering Text-to-Image Generation

SynthLight: Portrait Relighting with Diffusion Model by Learning to Re-render Synthetic Faces

no code implementations16 Jan 2025 Sumit Chaturvedi, Mengwei Ren, Yannick Hold-Geoffroy, Jingyuan Liu, Julie Dorsey, Zhixin Shu

Our method generalizes to diverse real photographs and produces realistic illumination effects, including specular highlights and cast shadows, while preserving the subject's identity.

Image Relighting

Text2Relight: Creative Portrait Relighting with Text Guidance

no code implementations18 Dec 2024 Junuk Cha, Mengwei Ren, Krishna Kumar Singh, He Zhang, Yannick Hold-Geoffroy, Seunghyun Yoon, HyunJoon Jung, Jae Shin Yoon, Seungryul Baek

As a condition of the lighting images, we perform image-based relighting for both foreground and background using a single portrait image or a set of OLAT (One-Light-at-A-Time) images captured from lightstage system.

Image Generation Image Relighting +1

Generative Portrait Shadow Removal

no code implementations7 Oct 2024 Jae Shin Yoon, Zhixin Shu, Mengwei Ren, Xuaner Zhang, Yannick Hold-Geoffroy, Krishna Kumar Singh, He Zhang

For robust and natural shadow removal, we propose to train the diffusion model with a compositional repurposing framework: a pre-trained text-guided image generation model is first fine-tuned to harmonize the lighting and color of the foreground with a background scene by using a background harmonization dataset; and then the model is further fine-tuned to generate a shadow-free portrait image via a shadow-paired dataset.

Image Generation Shadow Removal

COMPOSE: Comprehensive Portrait Shadow Editing

no code implementations25 Aug 2024 Andrew Hou, Zhixin Shu, Xuaner Zhang, He Zhang, Yannick Hold-Geoffroy, Jae Shin Yoon, Xiaoming Liu

Existing portrait relighting methods struggle with precise control over facial shadows, particularly when faced with challenges such as handling hard shadows from directional light sources or adjusting shadows while remaining in harmony with existing lighting conditions.

Disentanglement

PanDORA: Casual HDR Radiance Acquisition for Indoor Scenes

no code implementations8 Jul 2024 Mohammad Reza Karimi Dastjerdi, Frédéric Fortier-Chouinard, Yannick Hold-Geoffroy, Marc Hébert, Claude Demers, Nima Kalantari, Jean-François Lalonde

Most novel view synthesis methods such as NeRF are unable to capture the true high dynamic range (HDR) radiance of scenes since they are typically trained on photos captured with standard low dynamic range (LDR) cameras.

NeRF Novel View Synthesis

RGB$\leftrightarrow$X: Image decomposition and synthesis using material- and lighting-aware diffusion models

no code implementations1 May 2024 Zheng Zeng, Valentin Deschaintre, Iliyan Georgiev, Yannick Hold-Geoffroy, Yiwei Hu, Fujun Luan, Ling-Qi Yan, Miloš Hašan

Our X$\rightarrow$RGB model explores a middle ground between traditional rendering and generative models: we can specify only certain appearance properties that should be followed, and give freedom to the model to hallucinate a plausible version of the rest.

Image Generation Inverse Rendering

LightIt: Illumination Modeling and Control for Diffusion Models

no code implementations CVPR 2024 Peter Kocsis, Julien Philip, Kalyan Sunkavalli, Matthias Nießner, Yannick Hold-Geoffroy

Our method is the first that enables the generation of images with controllable, consistent lighting and performs on par with specialized relighting state-of-the-art methods.

Image Generation

Diffusion Handles Enabling 3D Edits for Diffusion Models by Lifting Activations to 3D

no code implementations CVPR 2024 Karran Pandey, Paul Guerrero, Matheus Gadelha, Yannick Hold-Geoffroy, Karan Singh, Niloy J. Mitra

Diffusion handles is a novel approach to enable 3D object edits on diffusion images requiring only existing pre-trained diffusion models depth estimation without any fine-tuning or 3D object retrieval.

3D Object Retrieval Depth Estimation +2

Diffusion Handles: Enabling 3D Edits for Diffusion Models by Lifting Activations to 3D

no code implementations2 Dec 2023 Karran Pandey, Paul Guerrero, Matheus Gadelha, Yannick Hold-Geoffroy, Karan Singh, Niloy Mitra

Our key insight is to lift diffusion activations for an object to 3D using a proxy depth, 3D-transform the depth and associated activations, and project them back to image space.

3D Object Retrieval Depth Estimation +2

PhotoMat: A Material Generator Learned from Single Flash Photos

no code implementations20 May 2023 Xilong Zhou, Miloš Hašan, Valentin Deschaintre, Paul Guerrero, Yannick Hold-Geoffroy, Kalyan Sunkavalli, Nima Khademi Kalantari

Instead, we train a generator for a neural material representation that is rendered with a learned relighting module to create arbitrarily lit RGB images; these are compared against real photos using a discriminator.

EverLight: Indoor-Outdoor Editable HDR Lighting Estimation

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.

Lighting Estimation

PixHt-Lab: Pixel Height Based Light Effect Generation for Image Compositing

no code implementations CVPR 2023 Yichen Sheng, Jianming Zhang, Julien Philip, Yannick Hold-Geoffroy, Xin Sun, He Zhang, Lu Ling, Bedrich Benes

To compensate for the lack of geometry in 2D Image compositing, recent deep learning-based approaches introduced a pixel height representation to generate soft shadows and reflections.

3D geometry

Lens Parameter Estimation for Realistic Depth of Field Modeling

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.

Single View Scene Scale Estimation Using Scale Field

no code implementations CVPR 2023 Byeong-Uk Lee, Jianming Zhang, Yannick Hold-Geoffroy, In So Kweon

In this paper, we propose a single image scale estimation method based on a novel scale field representation.

Guided Co-Modulated GAN for 360° Field of View Extrapolation

no code implementations15 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.

Image Generation

NeuTex: Neural Texture Mapping for Volumetric Neural Rendering

1 code implementation CVPR 2021 Fanbo Xiang, Zexiang Xu, Miloš Hašan, Yannick Hold-Geoffroy, Kalyan Sunkavalli, Hao Su

We achieve this by introducing a 3D-to-2D texture mapping (or surface parameterization) network into volumetric representations.

Neural Rendering

Neural Reflectance Fields for Appearance Acquisition

no code implementations9 Aug 2020 Sai Bi, Zexiang Xu, Pratul Srinivasan, Ben Mildenhall, Kalyan Sunkavalli, Miloš Hašan, Yannick Hold-Geoffroy, David Kriegman, Ravi Ramamoorthi

We combine this representation with a physically-based differentiable ray marching framework that can render images from a neural reflectance field under any viewpoint and light.

AutoToon: Automatic Geometric Warping for Face Cartoon Generation

1 code implementation6 Apr 2020 Julia Gong, Yannick Hold-Geoffroy, Jingwan Lu

Caricature, a type of exaggerated artistic portrait, amplifies the distinctive, yet nuanced traits of human faces.

Caricature

All-Weather Deep Outdoor Lighting Estimation

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.

Lighting Estimation

Single Day Outdoor Photometric Stereo

no code implementations28 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.

A Perceptual Measure for Deep Single Image Camera Calibration

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.

Camera Calibration Image Retrieval +1

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