Gram Matrix - Paper Copilot

Generative Modelling of BRDF Textures from Flash Images

Philipp Henzler, Valentin Deschaintre, Niloy J. Mitra, Tobias Ritschel

University College London; Adobe Research; Imperial College London

Portals

Abstract

We learn a latent space for easy capture, consistent interpolation, and efficient reproduction of visual material appearance. When users provide a photo of a stationary natural material captured under flashlight illumination, first it is converted into a latent material code. Then, in the second step, conditioned on the material code, our method produces an infinite and diverse spatial field of BRDF model parameters (diffuse albedo, normals, roughness, specular albedo) that subsequently allows rendering in complex scenes and illuminations, matching the appearance of the input photograph. Technically, we jointly embed all flash images into a latent space using a convolutional encoder, and -- conditioned on these latent codes -- convert random spatial fields into fields of BRDF parameters using a convolutional neural network (CNN). We condition these BRDF parameters to match the visual characteristics (statistics and spectra of visual features) of the input under matching light. A user study compares our approach favorably to previous work, even those with access to BRDF supervision.

Related Works

Textures in Graphics; Material Modeling

Two-Stream Convolutional Networks for Dynamic Texture Synthesis

Matthew Tesfaldet, Marcus A. Brubaker, Konstantinos G. Derpanis

York University; Pyerson University

Portals

Abstract

We introduce a two-stream model for dynamic texture synthesis. Our model is based on pre-trained convolutional networks (ConvNets) that target two independent tasks: (i) object recognition, and (ii) optical flow prediction. Given an input dynamic texture, statistics of filter responses from the object recognition ConvNet encapsulate the per-frame appearance of the input texture, while statistics of filter responses from the optical flow ConvNet model its dynamics. To generate a novel texture, a randomly initialized input sequence is optimized to match the feature statistics from each stream of an example texture. Inspired by recent work on image style transfer and enabled by the two-stream model, we also apply the synthesis approach to combine the texture appearance from one texture with the dynamics of another to generate entirely novel dynamic textures. We show that our approach generates novel, high quality samples that match both the framewise appearance and temporal evolution of input texture. Finally, we quantitatively evaluate our texture synthesis approach with a thorough user study.

High-Resolution Multi-Scale Neural Texture Synthesis

Xavier Snelgrove

Portals

Abstract

We introduce a novel multi-scale approach for synthesizing high-resolution natural textures using convolutional neural networks trained on image classification tasks. Previous breakthroughs were based on the observation that correlations between features at intermediate layers of the network are a powerful texture representation, however the fixed receptive field of network neurons limits the maximum size of texture features that can be synthesized. We show that rather than matching statistical properties at many layers of the CNN, better results can be achieved by matching a small number of network layers but across many scales of a Gaussian pyramid. This leads to qualitatively superior synthesized high-resolution textures.

Texture Synthesis Using Convolutional Neural Networks

Leon A. Gatys, Alexander S. Ecker, Matthias Bethge

Centre for Integrative Neuroscience, University of Tubingen; Bernstein Center for Computational Neuroscience; Graduate School of Neural Information Processing, University of Tubingen; Max Planck Institute for Biological Cybernetics; Baylor College of Medicine

Portals

Abstract

Here we introduce a new model of natural textures based on the feature spaces of convolutional neural networks optimised for object recognition. Samples from the model are of high perceptual quality demonstrating the generative power of neural networks trained in a purely discriminative fashion. Within the model, textures are represented by the correlations between feature maps in several layers of the network. We show that across layers the texture representations increasingly capture the statistical properties of natural images while making object information more and more explicit. The model provides a new tool to generate stimuli for neuroscience and might offer insights into the deep representations learned by convolutional neural networks.

INS: Unified Implicit Neural Stylization

Zhiwen Fan, Yifan Jiang, Peihao Wang, Xinyu Gong, Dejia Xu, Zhangyang Wang

The University of Texas at Austin

Portals

Abstract

Representing visual signals by implicit representation (e.g., a coordinate based deep network) has prevailed among many vision tasks. This work explores a new intriguing direction: training a stylized implicit representation, using a generalized approach that can apply to various 2D and 3D scenarios. We conduct a pilot study on a variety of implicit functions, including 2D coordinate-based representation, neural radiance field, and signed distance function. Our solution is a Unified Implicit Neural Stylization framework, dubbed INS. In contrary to vanilla implicit representation, INS decouples the ordinary implicit function into a style implicit module and a content implicit module, in order to separately encode the representations from the style image and input scenes. An amalgamation module is then applied to aggregate these information and synthesize the stylized output. To regularize the geometry in 3D scenes, we propose a novel self-distillation geometry consistency loss which preserves the geometry fidelity of the stylized scenes. Comprehensive experiments are conducted on multiple task settings, including novel view synthesis of complex scenes, stylization for implicit surfaces, and fitting images using MLPs. We further demonstrate that the learned representation is continuous not only spatially but also style-wise, leading to effortlessly interpolating between different styles and generating images with new mixed styles. Please refer to the video on our project page for more view synthesis results: https://zhiwenfan.github.io/INS.

Related Works

Implicit Function; Implicit 3D Scene Representation; Stylization

Comparisons

Style3D, Adain

Improving the Neural Algorithm of Artistic Style

Roman Novak, Yaroslav Nikulin

Ecole normale superieure de Cachan

Portals

Abstract

In this work we investigate different avenues of improving the Neural Algorithm of Artistic Style (by Leon A. Gatys, Alexander S. Ecker and Matthias Bethge, arXiv:1508.06576). While showing great results when transferring homogeneous and repetitive patterns, the original style representation often fails to capture more complex properties, like having separate styles of foreground and background. This leads to visual artifacts and undesirable textures appearing in unexpected regions when performing style transfer. We tackle this issue with a variety of approaches, mostly by modifying the style representation in order for it to capture more information and impose a tighter constraint on the style transfer result. In our experiments, we subjectively evaluate our best method as producing from barely noticeable to significant improvements in the quality of style transfer.

Category: Gram Matrix

Portals

Abstract

Related Works

Portals

Abstract

Portals

Abstract

Portals

Abstract

Portals

Abstract

Related Works

Comparisons

Portals

Abstract