相关论文: Exploring the Role of Synthetic Data Augmentation …

As insufficient data volume and quality remain the key impediments to the adoption of modern subsymbolic AI, techniques of synthetic data generation are in high demand. Simulation offers an apt, systematic approach to generating diverse…

Video data is more cost-effective than motion capture data for learning 3D character motion controllers, yet synthesizing realistic and diverse behaviors directly from videos remains challenging. Previous approaches typically rely on…

Human generation has achieved significant progress. Nonetheless, existing methods still struggle to synthesize specific regions such as faces and hands. We argue that the main reason is rooted in the training data. A holistic human dataset…

In the field of deep learning applied to face recognition, securing large-scale, high-quality datasets is vital for attaining precise and reliable results. However, amassing significant volumes of high-quality real data faces hurdles such…

Human emotion synthesis is a crucial aspect of affective computing. It involves using computational methods to mimic and convey human emotions through various modalities, with the goal of enabling more natural and effective human-computer…

Human anatomy, morphology, and associated diseases can be studied using medical imaging data. However, access to medical imaging data is restricted by governance and privacy concerns, data ownership, and the cost of acquisition, thus…

Machine learning has significant potential for optimizing various industrial processes. However, data acquisition remains a major challenge as it is both time-consuming and costly. Synthetic data offers a promising solution to augment…

Unconditional human image generation is an important task in vision and graphics, which enables various applications in the creative industry. Existing studies in this field mainly focus on "network engineering" such as designing new…

The proliferation of generative video technologies has intensified the need for reliable methods to detect and characterize synthetic media. To address this challenge, we organized the \href{https://safe-video-2025.dsri.org}{SAFE: Synthetic…

The use of synthetic data for training computer vision algorithms has become increasingly popular due to its cost-effectiveness, scalability, and ability to provide accurate multi-modality labels. Although recent studies have demonstrated…

Synthetic data has recently reached a level of visual fidelity that makes it nearly indistinguishable from real data, offering great promise for privacy-preserving data sharing in medical imaging. However, fully synthetic datasets still…

Despite remarkable progress having been made on the problem of 3D human pose and shape estimation (HPS), current state-of-the-art methods rely heavily on either confined indoor mocap datasets or datasets generated by a rendering engine…

To make medical datasets accessible without sharing sensitive patient information, we introduce a novel end-to-end approach for generative de-identification of dynamic medical imaging data. Until now, generative methods have faced…

This survey presents a comprehensive analysis of data augmentation techniques in human-centric vision tasks, a first of its kind in the field. It delves into a wide range of research areas including person ReID, human parsing, human pose…

Human motion generation aims to generate natural human pose sequences and shows immense potential for real-world applications. Substantial progress has been made recently in motion data collection technologies and generation methods, laying…

Annotated datasets are critical for training neural networks for object detection, yet their manual creation is time- and labour-intensive, subjective to human error, and often limited in diversity. This challenge is particularly pronounced…

Makeup transfer aims to apply the makeup style of a reference portrait to a source portrait while preserving identity and background. Early methods formulate this task as unsupervised image-to-image translation, relying on surrogate…

Modern video diffusion models excel at appearance synthesis but still struggle with physical consistency: objects drift, collisions lack realistic rebound, and material responses seldom match their underlying properties. We present PhyCo, a…

Synthetic data generation overcomes limitations of real-world machine learning. Traditional methods are valuable for augmenting costly datasets but only optimize one criterion: realism. In this paper, we tackle the problem of generating…

Cell tracking remains a pivotal yet challenging task in biomedical research. The full potential of deep learning for this purpose is often untapped due to the limited availability of comprehensive and varied training data sets. In this…