activity
20222026
most citedA Diffusion Approach to Radiance Field Relighting using Multi-Illumination Synthesis

17 citations · 23 across the 6 of their papers we have counts for

collaborators

6 papers

cs.GR2026

GRay: Ray Tracing 3D Gaussians Near the Speed of Splats

Yohan Poirier-Ginter, Jean-François Lalonde, George Drettakis

3D Gaussian Splatting (3DGS) is a popular representation for radiance field reconstruction, distinguished by the rendering speed of its rasterization-based renderer. While 3D Gauss…

cs.GR2026★ 2 cited

Editable Physically-based Reflections in Raytraced Gaussian Radiance Fields

Yohan Poirier-Ginter, Jeffrey Hu, Jean-François Lalonde +1

Radiance fields such as 3D Gaussian Splatting allow real-time rendering of scenes captured from photos. They also reconstruct most specular reflections with high visual quality, bu…

cs.CV2024★ 17 cited

A Diffusion Approach to Radiance Field Relighting using Multi-Illumination Synthesis

Yohan Poirier-Ginter, Alban Gauthier, Julien Philip +2

Relighting radiance fields is severely underconstrained for multi-view data, which is most often captured under a single illumination condition; It is especially hard for full scen…

cs.CV2023★ 1 cited

Robust Unsupervised StyleGAN Image Restoration

Yohan Poirier-Ginter, Jean-François Lalonde

GAN-based image restoration inverts the generative process to repair images corrupted by known degradations. Existing unsupervised methods must be carefully tuned for each task and…

cs.CV2022★ 2 cited

AdaWCT: Adaptive Whitening and Coloring Style Injection

Antoine Dufour, Yohan Poirier-Ginter, Alexandre Lessard +3

Adaptive instance normalization (AdaIN) has become the standard method for style injection: by re-normalizing features through scale-and-shift operations, it has found widespread u…

cs.CV2022★ 1 cited

Overparameterization Improves StyleGAN Inversion

Yohan Poirier-Ginter, Alexandre Lessard, Ryan Smith +1

Deep generative models like StyleGAN hold the promise of semantic image editing: modifying images by their content, rather than their pixel values. Unfortunately, working with arbi…