283 citations · 613 across the 31 of their papers we have counts for
7 papers · 1 filter
ControlMat: A Controlled Generative Approach to Material Capture
Giuseppe Vecchio, Rosalie Martin, Arthur Roullier +4
Material reconstruction from a photograph is a key component of 3D content creation democratization. We propose to formulate this ill-posed problem as a controlled synthesis one, l…
The Visual Language of Fabrics
Valentin Deschaintre, Julia Guerrero-Viu, Diego Gutierrez +2
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,…
PSDR-Room: Single Photo to Scene using Differentiable Rendering
Kai Yan, Fujun Luan, MiloŠ HaŠAn +3
A 3D digital scene contains many components: lights, materials and geometries, interacting to reach the desired appearance. Staging such a scene is time-consuming and requires both…
Floaters No More: Radiance Field Gradient Scaling for Improved Near-Camera Training
Julien Philip, Valentin Deschaintre
NeRF acquisition typically requires careful choice of near planes for the different cameras or suffers from background collapse, creating floating artifacts on the edges of the cap…
PhotoMat: A Material Generator Learned from Single Flash Photos
Xilong Zhou, Miloš Hašan, Valentin Deschaintre +4
Authoring high-quality digital materials is key to realism in 3D rendering. Previous generative models for materials have been trained exclusively on synthetic data; such data is l…
Materialistic: Selecting Similar Materials in Images
Prafull Sharma, Julien Philip, Michaël Gharbi +3
Separating an image into meaningful underlying components is a crucial first step for both editing and understanding images. We present a method capable of selecting the regions of…
Generating Procedural Materials from Text or Image Prompts
Yiwei Hu, Paul Guerrero, Miloš Hašan +2
Node graph systems are used ubiquitously for material design in computer graphics. They allow the use of visual programming to achieve desired effects without writing code. As high…