Related papers: PODiff: Latent Diffusion in Proper Orthogonal Deco…
Land surface temperature (LST) super-resolution is important for environmental monitoring. However, it remains challenging as coarse thermal observations severely underdetermine fine-scale structure. In this paper, we propose Earth…
In this work, a numerical simulation of 1D Burgers' equation is developed using finite difference method and a reduced order model (ROM) of the simulation is developed using proper orthogonal decomposition (POD). The objective of this work…
Defects in laser powder bed fusion (L-PBF) parts often result from the meso-scale dynamics of the molten alloy near the laser, known as the melt pool. For instance, the melt pool can directly contribute to the formation of undesirable…
This study focuses on the stratification patterns and dynamic evolution of reservoir water temperatures, aiming to estimate and reconstruct the temperature field using limited and noisy local measurement data. Due to complex measurement…
Old-photo face restoration poses significant challenges due to compounded degradations such as breakage, fading, and severe blur. Existing pre-trained diffusion-guided methods either rely on explicit degradation priors or global statistical…
Generative models have achieved remarkable success in image, video, and text domains. Inspired by this, researchers have explored utilizing generative models to generate neural network parameters. However, these efforts have been limited by…
Generalizable 3D object reconstruction from single-view RGB-D images remains a challenging task, particularly with real-world data. Current state-of-the-art methods develop Transformer-based implicit field learning, necessitating an…
Diffusion-based voxel prior modelling is challenging for the reconstruction of large-scale 3D porous microstructures. Due to the demanding requirements for simultaneously modelling both the continuous pore morphology and the discrete…
Latent diffusion models excel at generating high-quality images but lose the benefits of end-to-end modeling. They discard information during image encoding, require a separately trained decoder, and model an auxiliary distribution to the…
Recently, perceptual image compression has achieved significant advancements, delivering high visual quality at low bitrates for natural images. However, for screen content, existing methods often produce noticeable artifacts when…
Seismic data frequently exhibits missing traces, substantially affecting subsequent seismic processing and interpretation. Deep learning-based approaches have demonstrated significant advancements in reconstructing irregularly missing…
Automotive radar has shown promising developments in environment perception due to its cost-effectiveness and robustness in adverse weather conditions. However, the limited availability of annotated radar data poses a significant challenge…
Image geolocalization is a fundamental yet challenging task, aiming at inferring the geolocation on Earth where an image is taken. State-of-the-art methods employ either grid-based classification or gallery-based image-location retrieval,…
The ability to generate 3D multiphase microstructures on-demand with targeted attributes can greatly accelerate the design of advanced materials. Here, we present a conditional latent diffusion model (LDM) framework that rapidly synthesizes…
Transferring visual style between images while preserving semantic correspondence between similar objects remains a central challenge in computer vision. While existing methods have made great strides, most of them operate at global level…
Image completion is a challenging task, particularly when ensuring that generated content seamlessly integrates with existing parts of an image. While recent diffusion models have shown promise, they often struggle with maintaining…
Recently, diffusion models have achieved great success in image synthesis. However, when it comes to the layout-to-image generation where an image often has a complex scene of multiple objects, how to make strong control over both the…
Generative models have demonstrated strong performance in conditional settings and can be viewed as a form of data compression, where the condition serves as a compact representation. However, their limited controllability and…
We present a cascaded diffusion model based on a part-level implicit 3D representation. Our model achieves state-of-the-art generation quality and also enables part-level shape editing and manipulation without any additional training in…
Conventional class-guided diffusion models generally succeed in generating images with correct semantic content, but often struggle with texture details. This limitation stems from the usage of class priors, which only provide coarse and…