Geometry- and appearance-controlled full-body human image generation is an interesting but challenging task. Existing solutions are either unconditional or dependent on coarse conditions (e.g., pose, text), thus lacki...
详细信息
Geometry- and appearance-controlled full-body human image generation is an interesting but challenging task. Existing solutions are either unconditional or dependent on coarse conditions (e.g., pose, text), thus lacking explicit geometry and appearance control of body and garment. Sketching offers such editing ability and has been adopted in various sketch-based face generation and editing solutions. However, directly adapting sketch-based face generation to full-body generation often fails to produce high-fidelity and diverse results due to the high complexity and diversity in the pose, body shape, and garment shape and texture. Recent geometrically controllable diffusion-based methods mainly rely on prompts to generate appearance. It is hard to balance the realism and the faithfulness of their results to the sketch when the input is coarse. This work presents Sketch2Human, the first system for controllable full-body human image generation guided by a semantic sketch (for geometry control) and a reference image (for appearance control). Our solution is based on the latent space of StyleGAN-Human with inverted geometry and appearance latent codes as input. Specifically, we present a sketch encoder trained with a large synthetic dataset sampled from StyleGAN-Human's latent space and directly supervised by sketches rather than real images. Considering the entangled information of partial geometry and texture in StyleGAN-Human and the absence of disentangled datasets, we design a novel training scheme that creates geometry-preserved and appearance-transferred training data to tune a generator to achieve disentangled geometry and appearance control. Although our method is trained with synthetic data, it can also handle hand-drawn sketches. Qualitative and quantitative evaluations demonstrate the superior performance of our method to state-of-the-art methods. IEEE
The project aims to create an automated system for detecting fungal contamination in dried red chilies using advanced deep learning algorithms such as Convolutional Neural Network (CNN), Visual Geometry Group (VGG16),...
详细信息
Blindness, largely resulting from conditions such as Diabetic Retinopathy, Glaucoma, and Cataract, stands as a significant health concern. This paper introduces a novel approach proposing an automatic, self-diagnosing...
详细信息
In addition to traditional approaches, several computerized techniques have been developed to enhance the results. The automation in the medical domain considerably reduced the burden and improved disease diagnosis, t...
详细信息
In recent times, ensuring the safety of women while walking on roads has emerged as an increasingly urgent and complex challenge, with a significant increase in the number of crimes against women being reported. Signi...
详细信息
Today most of our daily activities are led by the Internet like banking transactions, shopping, communication, transportation, and so on. Without the internet and its applications, we could not envision our lives. How...
详细信息
Bacterial diseases cause a major threat to the health globally which necessitates to its accurate detection as well as diagnosis. There are various traditional methods like clinical assessments, laboratory techniques,...
详细信息
This paper presents the application of advanced speech recognition technologies to transcribe and analyze customer interactions, enhancing both business efficiency and customer experience. Motivated by the need for hu...
详细信息
The integrity of product warranties stands as a critical concern, marked by challenges like data tampering and fabrication within traditional verification systems. This paper explores the transformative potential of b...
详细信息
The area of speech, language, and machine learning research has extensively investigated text-to-speech (TTS), sometimes referred to as speech synthesis. Its importance has grown due to its applicability in many diffe...
详细信息
暂无评论