Subject: Reflectance modeling × Start date: 2025 ×

Search Results

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item
    Perceived Quality of BRDF Models
    (The Eurographics Association and John Wiley & Sons Ltd., 2025) Kavoosighafi, Behnaz; Mantiuk, Rafal K.; Hajisharif, Saghi; Miandji, Ehsan; Unger, Jonas; Wang, Beibei; Wilkie, Alexander
    Material appearance is commonly modeled with the Bidirectional Reflectance Distribution Functions (BRDFs), which need to trade accuracy for complexity and storage cost. To investigate the current practices of BRDF modeling, we collect the first high dynamic range stereoscopic video dataset that captures the perceived quality degradation with respect to a number of parametric and non-parametric BRDF models. Our dataset shows that the current loss functions used to fit BRDF models, such as mean-squared error of logarithmic reflectance values, correlate poorly with the perceived quality of materials in rendered videos. We further show that quality metrics that compare rendered material samples give a significantly higher correlation with subjective quality judgments, and a simple Euclidean distance in the ITP color space (DEITP) shows the highest correlation. Additionally, we investigate the use of different BRDF-space metrics as loss functions for fitting BRDF models and find that logarithmic mapping is the most effective approach for BRDF-space loss functions.
  • Thumbnail Image
    Item
    VideoMat: Extracting PBR Materials from Video Diffusion Models
    (The Eurographics Association and John Wiley & Sons Ltd., 2025) Munkberg, Jacob; Wang, Zian; Liang, Ruofan; Shen, Tianchang; Hasselgren, Jon; Wang, Beibei; Wilkie, Alexander
    We leverage finetuned video diffusion models, intrinsic decomposition of videos, and physically-based differentiable rendering to generate high quality materials for 3D models given a text prompt or a single image. We condition a video diffusion model to respect the input geometry and lighting condition. This model produces multiple views of a given 3D model with coherent material properties. Secondly, we use a recent model to extract intrinsics (base color, roughness, metallic) from the generated video. Finally, we use the intrinsics alongside the generated video in a differentiable path tracer to robustly extract PBR materials directly compatible with common content creation tools.
  • Thumbnail Image
    Item
    Real-time Image-based Lighting of Glints
    (The Eurographics Association and John Wiley & Sons Ltd., 2025) Kneiphof, Tom; Klein, Reinhard; Wang, Beibei; Wilkie, Alexander
    Image-based lighting is a widely used technique to reproduce shading under real-world lighting conditions, especially in realtime rendering applications. A particularly challenging scenario involves materials exhibiting a sparkling or glittering appearance, caused by discrete microfacets scattered across their surface. In this paper, we propose an efficient approximation for image-based lighting of glints, enabling fully dynamic material properties and environment maps. Our novel approach is grounded in real-time glint rendering under area light illumination and employs standard environment map filtering techniques. Crucially, our environment map filtering process is sufficiently fast to be executed on a per-frame basis. Our method assumes that the environment map is partitioned into few homogeneous regions of constant radiance. By filtering the corresponding indicator functions with the normal distribution function, we obtain the probabilities for individual microfacets to reflect light from each region. During shading, these probabilities are utilized to hierarchically sample a multinomial distribution, facilitated by our novel dual-gated Gaussian approximation of binomial distributions. We validate that our real-time approximation is close to ground-truth renderings for a range of material properties and lighting conditions, and demonstrate robust and stable performance, with little overhead over rendering glints from a single directional light. Compared to rendering smooth materials without glints, our approach requires twice as much memory to store the prefiltered environment map.
  • Thumbnail Image
    Item
    MatSwap: Light-aware Material Transfers in Images
    (The Eurographics Association and John Wiley & Sons Ltd., 2025) Lopes, Ivan; Deschaintre, Valentin; Hold-Geoffroy, Yannick; Charette, Raoul de; Wang, Beibei; Wilkie, Alexander
    We present MatSwap, a method to transfer materials to designated surfaces in an image realistically. Such a task is non-trivial due to the large entanglement of material appearance, geometry, and lighting in a photograph. In the literature, material editing methods typically rely on either cumbersome text engineering or extensive manual annotations requiring artist knowledge and 3D scene properties that are impractical to obtain. In contrast, we propose to directly learn the relationship between the input material-as observed on a flat surface-and its appearance within the scene, without the need for explicit UV mapping. To achieve this, we rely on a custom light- and geometry-aware diffusion model. We fine-tune a large-scale pre-trained text-toimage model for material transfer using our synthetic dataset, preserving its strong priors to ensure effective generalization to real images. As a result, our method seamlessly integrates a desired material into the target location in the photograph while retaining the identity of the scene. MatSwap is evaluated on synthetic and real images showing that it compares favorably to recent works. Our code and data are made publicly available on https://github.com/astra-vision/MatSwap