2022-05-11 更新
Generate and Edit Your Own Character in a Canonical View
Authors:Jeong-gi Kwak, Yuanming Li, Dongsik Yoon, David Han, Hanseok Ko
Recently, synthesizing personalized characters from a single user-given portrait has received remarkable attention as a drastic popularization of social media and the metaverse. The input image is not always in frontal view, thus it is important to acquire or predict canonical view for 3D modeling or other applications. Although the progress of generative models enables the stylization of a portrait, obtaining the stylized image in canonical view is still a challenging task. There have been several studies on face frontalization but their performance significantly decreases when input is not in the real image domain, e.g., cartoon or painting. Stylizing after frontalization also results in degenerated output. In this paper, we propose a novel and unified framework which generates stylized portraits in canonical view. With a proposed latent mapper, we analyze and discover frontalization mapping in a latent space of StyleGAN to stylize and frontalize at once. In addition, our model can be trained with unlabelled 2D image sets, without any 3D supervision. The effectiveness of our method is demonstrated by experimental results.
PDF AI for Content Creation Workshop at CVPR 2022
论文截图
Analysis of Different Losses for Deep Learning Image Colorization
Authors:Coloma Ballester, Aurélie Bugeau, Hernan Carrillo, Michaël Clément, Rémi Giraud, Lara Raad, Patricia Vitoria
Image colorization aims to add color information to a grayscale image in a realistic way. Recent methods mostly rely on deep learning strategies. While learning to automatically colorize an image, one can define well-suited objective functions related to the desired color output. Some of them are based on a specific type of error between the predicted image and ground truth one, while other losses rely on the comparison of perceptual properties. But, is the choice of the objective function that crucial, i.e., does it play an important role in the results? In this chapter, we aim to answer this question by analyzing the impact of the loss function on the estimated colorization results. To that goal, we review the different losses and evaluation metrics that are used in the literature. We then train a baseline network with several of the reviewed objective functions: classic L1 and L2 losses, as well as more complex combinations such as Wasserstein GAN and VGG-based LPIPS loss. Quantitative results show that the models trained with VGG-based LPIPS provide overall slightly better results for most evaluation metrics. Qualitative results exhibit more vivid colors when with Wasserstein GAN plus the L2 loss or again with the VGG-based LPIPS. Finally, the convenience of quantitative user studies is also discussed to overcome the difficulty of properly assessing on colorized images, notably for the case of old archive photographs where no ground truth is available.
PDF arXiv admin note: text overlap with arXiv:2204.02850
论文截图
LatentKeypointGAN: Controlling Images via Latent Keypoints — Extended Abstract
Authors:Xingzhe He, Bastian Wandt, Helge Rhodin
Generative adversarial networks (GANs) can now generate photo-realistic images. However, how to best control the image content remains an open challenge. We introduce LatentKeypointGAN, a two-stage GAN internally conditioned on a set of keypoints and associated appearance embeddings providing control of the position and style of the generated objects and their respective parts. A major difficulty that we address is disentangling the image into spatial and appearance factors with little domain knowledge and supervision signals. We demonstrate in a user study and quantitative experiments that LatentKeypointGAN provides an interpretable latent space that can be used to re-arrange the generated images by re-positioning and exchanging keypoint embeddings, such as generating portraits by combining the eyes, and mouth from different images. Notably, our method does not require labels as it is self-supervised and thereby applies to diverse application domains, such as editing portraits, indoor rooms, and full-body human poses.
PDF
论文截图
Do Not Escape From the Manifold: Discovering the Local Coordinates on the Latent Space of GANs
Authors:Jaewoong Choi, Junho Lee, Changyeon Yoon, Jung Ho Park, Geonho Hwang, Myungjoo Kang
The discovery of the disentanglement properties of the latent space in GANs motivated a lot of research to find the semantically meaningful directions on it. In this paper, we suggest that the disentanglement property is closely related to the geometry of the latent space. In this regard, we propose an unsupervised method for finding the semantic-factorizing directions on the intermediate latent space of GANs based on the local geometry. Intuitively, our proposed method, called Local Basis, finds the principal variation of the latent space in the neighborhood of the base latent variable. Experimental results show that the local principal variation corresponds to the semantic factorization and traversing along it provides strong robustness to image traversal. Moreover, we suggest an explanation for the limited success in finding the global traversal directions in the latent space, especially W-space of StyleGAN2. We show that W-space is warped globally by comparing the local geometry, discovered from Local Basis, through the metric on Grassmannian Manifold. The global warpage implies that the latent space is not well-aligned globally and therefore the global traversal directions are bound to show limited success on it.
PDF 24 pages, 19 figures
论文截图
High-Resolution UAV Image Generation for Sorghum Panicle Detection
Authors:Enyu Cai, Zhankun Luo, Sriram Baireddy, Jiaqi Guo, Changye Yang, Edward J. Delp
The number of panicles (or heads) of Sorghum plants is an important phenotypic trait for plant development and grain yield estimation. The use of Unmanned Aerial Vehicles (UAVs) enables the capability of collecting and analyzing Sorghum images on a large scale. Deep learning can provide methods for estimating phenotypic traits from UAV images but requires a large amount of labeled data. The lack of training data due to the labor-intensive ground truthing of UAV images causes a major bottleneck in developing methods for Sorghum panicle detection and counting. In this paper, we present an approach that uses synthetic training images from generative adversarial networks (GANs) for data augmentation to enhance the performance of Sorghum panicle detection and counting. Our method can generate synthetic high-resolution UAV RGB images with panicle labels by using image-to-image translation GANs with a limited ground truth dataset of real UAV RGB images. The results show the improvements in panicle detection and counting using our data augmentation approach.
PDF
论文截图