Related papers: Three-dimensional Conditional Diffusion Models for…
Latent Diffusion models (LDMs) have achieved remarkable results in synthesizing high-resolution images. However, the iterative sampling process is computationally intensive and leads to slow generation. Inspired by Consistency Models (song…
Recent work showed that large diffusion models can be reused as highly precise monocular depth estimators by casting depth estimation as an image-conditional image generation task. While the proposed model achieved state-of-the-art results,…
Targeting a cone with the half-angle as 10-deg at M = 27 and H = 72 km, simulations were conducted comparatively to analyze the predictions by different equilibrium and non-equilibrium gas models. Following validation and grid studies,…
Current and upcoming 21-cm experiments will soon be able to map 21-cm spatial fluctuations in three dimensions for a wide range of redshifts. However, bright foreground contamination and the nature of radio interferometry create significant…
Limited-angle computed tomography (LACT) reconstruction is an inverse problem with severe ill-posedness arising from missing projection angles, and it is difficult to restore high-precision images without sufficient prior knowledge. In…
The three-point correlation function (3PCF) of the 21cm brightness temperature from the Epoch of Reionization (EoR) probes complementary information to the commonly studied two-point correlation function (2PCF) about the morphology of…
Diffusion models have achieved remarkable success in generating high quality image and video data. More recently, they have also been used for image compression with high perceptual quality. In this paper, we present a novel approach to…
Generating 3D images of complex objects conditionally from a few 2D views is a difficult synthesis problem, compounded by issues such as domain gap and geometric misalignment. For instance, a unified framework such as Generative Adversarial…
The information regarding how the intergalactic medium is reionized by astrophysical sources is contained in the tomographic three-dimensional 21 cm images from the epoch of reionization. In Zhao et al. (2022a) ("Paper I"), we demonstrated…
Controlling illumination in images is essential for photography and visual content creation. While closed-source models have demonstrated impressive illumination control, open-source alternatives either require heavy control inputs like…
Advanced accelerator-based light sources such as free electron lasers (FEL) accelerate highly relativistic electron beams to generate incredibly short (10s of femtoseconds) coherent flashes of light for dynamic imaging, whose brightness…
Robust in-bed human pose estimation under blanket occlusion remains challenging due to the scarcity of reliable labeled training data for heavily covered poses. Existing approaches rely on multi-modal sensing or image-to-image translation…
We introduce a powerful semi-numeric modeling tool, 21cmFAST, designed to efficiently simulate the cosmological 21-cm signal. Our code generates 3D realizations of evolved density, ionization, peculiar velocity, and spin temperature fields,…
The conditional diffusion model (CDM) enhances the standard diffusion model by providing more control, improving the quality and relevance of the outputs, and making the model adaptable to a wider range of complex tasks. However, inaccurate…
AI-generated content has attracted lots of attention recently, but photo-realistic video synthesis is still challenging. Although many attempts using GANs and autoregressive models have been made in this area, the visual quality and length…
Accurate 3D human pose estimation remains a critical yet unresolved challenge, requiring both temporal coherence across frames and fine-grained modeling of joint relationships. However, most existing methods rely solely on geometric cues…
Acting in human environments is a crucial capability for general-purpose robots, necessitating a robust understanding of natural language and its application to physical tasks. This paper seeks to harness the capabilities of diffusion…
We show that cascaded diffusion models are capable of generating high fidelity images on the class-conditional ImageNet generation benchmark, without any assistance from auxiliary image classifiers to boost sample quality. A cascaded…
We have constructed three-dimensional models for the equilibrium abundance of molecular hydrogen within diffuse interstellar clouds of arbitrary geometry that are illuminated by ultraviolet radiation. The position-dependent photo-…
Low-field (LF) MRI scanners (<1T) are still prevalent in settings with limited resources or unreliable power supply. However, they often yield images with lower spatial resolution and contrast than high-field (HF) scanners. This quality…