Zobrazeno 1 - 10
of 81
pro vyhledávání: '"Smolic, Aljoša"'
GAN inversion aims at inverting given images into corresponding latent codes for Generative Adversarial Networks (GANs), especially StyleGAN where exists a disentangled latent space that allows attribute-based image manipulation at latent level. As m
Externí odkaz:
http://arxiv.org/abs/2307.16151
Image quality assessment is a fundamental problem in the field of image processing, and due to the lack of reference images in most practical scenarios, no-reference image quality assessment (NR-IQA), has gained increasing attention recently. With th
Externí odkaz:
http://arxiv.org/abs/2305.09353
Autor:
Ak, Ali, Zerman, Emin, Quach, Maurice, Chetouani, Aladine, Smolic, Aljosa, Valenzise, Giuseppe, Callet, Patrick Le
Publikováno v:
IEEE Transactions on Multimedia vol. 26 (2024) pp. 6730-6742
Point clouds have become increasingly prevalent in representing 3D scenes within virtual environments, alongside 3D meshes. Their ease of capture has facilitated a wide array of applications on mobile devices, from smartphones to autonomous vehicles.
Externí odkaz:
http://arxiv.org/abs/2302.04796
Compression is an important task for many practical applications of light fields. Although previous work has proposed numerous methods for efficient light field compression, the effect of view selection on this task is not well exploited. In this wor
Externí odkaz:
http://arxiv.org/abs/2208.06464
Autor:
Lutz, Sebastian, Blythman, Richard, Ghosal, Koustav, Moynihan, Matthew, Simms, Ciaran, Smolic, Aljosa
Monocular 3D human pose estimation technologies have the potential to greatly increase the availability of human movement data. The best-performing models for single-image 2D-3D lifting use graph convolutional networks (GCNs) that typically require s
Externí odkaz:
http://arxiv.org/abs/2208.03704
Publikováno v:
Irish Machine Vision & Image Processing Conference (IMVIP 2022)
Computer vision/deep learning-based 3D human pose estimation methods aim to localize human joints from images and videos. Pose representation is normally limited to 3D joint positional/translational degrees of freedom (3DOFs), however, a further thre
Externí odkaz:
http://arxiv.org/abs/2207.12841
Autor:
Ghosal, Koustav, Smolic, Aljosa
Aspect ratio and spatial layout are two of the principal factors determining the aesthetic value of a photograph. But, incorporating these into the traditional convolution-based frameworks for the task of image aesthetics assessment is problematic. T
Externí odkaz:
http://arxiv.org/abs/2206.12869
Most of existing video action recognition models ingest raw RGB frames. However, the raw video stream requires enormous storage and contains significant temporal redundancy. Video compression (e.g., H.264, MPEG-4) reduces superfluous information by r
Externí odkaz:
http://arxiv.org/abs/2110.08814
Autor:
Alain, Martin, Smolic, Aljosa
Publikováno v:
Signal Processing: Image Communication 2022
In this paper, we study the spectral properties of re-parameterized light field. Following previous studies of the light field spectrum, which notably provided sampling guidelines, we focus on the two plane parameterization of the light field. Howeve
Externí odkaz:
http://arxiv.org/abs/2110.06064
We address the problem of exposure correction of dark, blurry and noisy images captured in low-light conditions in the wild. Classical image-denoising filters work well in the frequency space but are constrained by several factors such as the correct
Externí odkaz:
http://arxiv.org/abs/2104.10856