EG2022

Permanent URI for this community

https://diglib.eg.org/handle/10.2312/2633163

Browse

Browsing EG2022 by Subject "Appearance and texture representations"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Improved Lighting Models for Facial Appearance Capture
    (The Eurographics Association, 2022) Xu, Yingyan; Riviere, Jérémy; Zoss, Gaspard; Chandran, Prashanth; Bradley, Derek; Gotardo, Paulo; Pelechano, Nuria; Vanderhaeghe, David
    Facial appearance capture techniques estimate geometry and reflectance properties of facial skin by performing a computationally intensive inverse rendering optimization in which one or more images are re-rendered a large number of times and compared to real images coming from multiple cameras. Due to the high computational burden, these techniques often make several simplifying assumptions to tame complexity and make the problem more tractable. For example, it is common to assume that the scene consists of only distant light sources, and ignore indirect bounces of light (on the surface and within the surface). Also, methods based on polarized lighting often simplify the light interaction with the surface and assume perfect separation of diffuse and specular reflectance. In this paper, we move in the opposite direction and demonstrate the impact on facial appearance capture quality when departing from these idealized conditions towards models that seek to more accurately represent the lighting, while at the same time minimally increasing computational burden. We compare the results obtained with a state-of-the-art appearance capture method [RGB*20], with and without our proposed improvements to the lighting model.
  • Thumbnail Image
    Item
    RGB-D Neural Radiance Fields: Local Sampling for Faster Training
    (The Eurographics Association, 2022) Dey, Arnab; Comport, Andrew I.; Sauvage, Basile; Hasic-Telalovic, Jasminka
    Learning a 3D representation of a scene has been a challenging problem for decades in computer vision. Recent advancements in implicit neural representation from images using neural radiance fields(NeRF) have shown promising results. Some of the limitations of previous NeRF based methods include longer training time, and inaccurate underlying geometry. The proposed method takes advantage of RGB-D data to reduce training time by leveraging depth sensing to improve local sampling. This paper proposes a depth-guided local sampling strategy and a smaller neural network architecture to achieve faster training time without compromising quality.