Search for: All records

Latent diffusion models have been demonstrated to generate high-quality images, while offering efficiency in model training compared to diffusion models operating in the pixel space. However, incorporating latent diffusion models to solve inverse problems remains a challenging problem due to the nonlinearity of the encoder and decoder. To address these issues, we propose ReSample, an algorithm that can solve general inverse problems with pre-trained latent diffusion models. Our algorithm incorporates data consistency by solving an optimization problem during the reverse sampling process, a concept that we term as hard data consistency. Upon solving this optimization problem, we propose a novel resampling scheme to map the measurement-consistent sample back onto the noisy data manifold and theoretically demonstrate its benefits. Lastly, we apply our algorithm to solve a wide range of linear and nonlinear inverse problems in both natural and medical images, demonstrating that our approach outperforms existing state-of-the-art approaches, including those based on pixel-space diffusion models. 

Technological convergence network (TCN) is an effective method to identify the advancement of technology convergence. However, the previous TCN investigations are limited to a single level of IPC (abbreviation of International Patent Classification) rather than different IPC hierarchies, which can only provide decision support for policy-makers with one dimension instead of various ones. In this study, we propose a new approach to construct TCNs across different IPC hierarchies based on technology co-classification analysis, and further identify key technology fields by employing the indicator of betweenness centrality (BC) in the TCNs from any IPC hierarchy. This study makes two important contributions. First, theoretically, our study is to contribute to understanding the advancement of technological convergence from various IPC hierarchies, rather than a single IPC level. Second, methodologically, the new approach we propose can benefit decision-makers serving at various levels of technology management agencies. We conclude possible implications and future directions.