تقرير
Can We Generate Realistic Hands Only Using Convolution?
العنوان: | Can We Generate Realistic Hands Only Using Convolution? |
---|---|
المؤلفون: | Hosseini, Mehran, Hosseini, Peyman |
سنة النشر: | 2024 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence, Computer Science - Machine Learning, 51, I.2.10, I.4.0, I.4.10 |
الوصف: | The enduring inability of image generative models to recreate intricate geometric features, such as those present in human hands and fingers has been an ongoing problem in image generation for nearly a decade. While strides have been made by increasing model sizes and diversifying training datasets, this issue remains prevalent across all models, from denoising diffusion models to Generative Adversarial Networks (GAN), pointing to a fundamental shortcoming in the underlying architectures. In this paper, we demonstrate how this problem can be mitigated by augmenting convolution layers geometric capabilities through providing them with a single input channel incorporating the relative $n$-dimensional Cartesian coordinate system. We show that this drastically improves quality of hand and face images generated by GANs and Variational AutoEncoders (VAE). Comment: Contains 17 pages, 14 figures, and 6 tables |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2401.01951 |
رقم الأكسشن: | edsarx.2401.01951 |
قاعدة البيانات: | arXiv |
كن أول من يترك تعليقا!