Partial convolution for padding, inpainting, and image synthesis
Partial convolution weights convolutions with binary masks and renormalizes on valid pixels.
It was originally proposed for image inpainting task because a corrupted image processed …
It was originally proposed for image inpainting task because a corrupted image processed …
Vecgan: Image-to-image translation with interpretable latent directions
We propose VecGAN, an image-to-image translation framework for facial attribute editing
with interpretable latent directions. Facial attribute editing task faces the challenges of …
with interpretable latent directions. Facial attribute editing task faces the challenges of …
Dual contrastive loss and attention for gans
Abstract Generative Adversarial Networks (GANs) produce impressive results on
unconditional image generation when powered with large-scale image datasets. Yet …
unconditional image generation when powered with large-scale image datasets. Yet …
Umat: Uncertainty-aware single image high resolution material capture
C Rodriguez-Pardo… - Proceedings of the …, 2023 - openaccess.thecvf.com
We propose a learning-based method to recover normals, specularity, and roughness from a
single diffuse image of a material, using microgeometry appearance as our primary cue …
single diffuse image of a material, using microgeometry appearance as our primary cue …
Multi-frequency representation enhancement with privilege information for video super-resolution
CNN's limited receptive field restricts its ability to capture long-range spatial-temporal
dependencies, leading to unsatisfactory performance in video super-resolution. To tackle …
dependencies, leading to unsatisfactory performance in video super-resolution. To tackle …
Painterly image harmonization in dual domains
Image harmonization aims to produce visually harmonious composite images by adjusting
the foreground appearance to be compatible with the background. When the composite …
the foreground appearance to be compatible with the background. When the composite …
On exploring multiplicity of primitives and attributes for texture recognition in the wild
Texture recognition is a challenging visual task since its multiple primitives or attributes can
be perceived from the texture image under different spatial contexts. Existing approaches …
be perceived from the texture image under different spatial contexts. Existing approaches …
View generalization for single image textured 3d models
Humans can easily infer the underlying 3D geometry and texture of an object only from a
single 2D image. Current computer vision methods can do this, too, but suffer from view …
single 2D image. Current computer vision methods can do this, too, but suffer from view …
Fine detailed texture learning for 3D meshes with generative models
This paper presents a method to achieve fine detailed texture learning for 3D models that
are reconstructed from both multi-view and single-view images. The framework is posed as …
are reconstructed from both multi-view and single-view images. The framework is posed as …
Seamlessgan: Self-supervised synthesis of tileable texture maps
C Rodriguez-Pardo, E Garces - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Real-time graphics applications require high-quality textured materials to convey realism in
virtual environments. Generating these textures is challenging as they need to be visually …
virtual environments. Generating these textures is challenging as they need to be visually …