The lack of large-scale, demographically diverse face images with precise Action Unit (AU) occurrence and intensity annotations has long been recognized as a fundamental bottleneck in developing generalizable facial AU recognition systems. In this paper, we propose MAUGen, a diffusion-based multi-modal framework that jointly generates a large collection of photorealistic facial expressions and anatomically consistent AU labels, including both occurrence and intensity, conditioned on a single descriptive text prompt. Our MAUGen involves two key modules: (1) a Multi-modal Representation Learning (MRL) module that captures the relationships among the paired facial textual description, facial identity, facial expression image, and AU activations within a unified latent space; and (2) a Diffusion-based Image-label Generator (DIG) that decodes the obtained joint representation into aligned facial image-label pairs across diverse identities. Under this framework, we introduce the Multi-Identity Facial Action (MIFA), a large-scale multi-modal (i.e., text descriptions, face images with labels) synthetic dataset that features comprehensive AU annotations and identity variations. Extensive experiments demonstrate that MAUGen outperforms existing methods in synthesizing photorealistic, demographically diverse facial images, along with semantically aligned AU labels.

3D Gaussian Splatting (3DGS) techniques have achieved satisfactory 3D scene representation. Despite their impressive performance, they confront challenges due to the limitation of structure-from-motion (SfM) methods on acquiring accurate scene initialization, or the inefficiency of densification strategy. In this paper, we introduce a novel framework EasySplat to achieve high-quality 3DGS modeling. Instead of using SfM for scene initialization, we employ a novel method to release the power of large-scale pointmap approaches. Specifically, we propose an efficient grouping strategy based on view similarity, and use robust pointmap priors to obtain high-quality point clouds and camera poses for 3D scene initialization. After obtaining a reliable scene structure, we propose a novel densification approach that adaptively splits Gaussian primitives based on the average shape of neighboring Gaussian ellipsoids, utilizing KNN scheme. In this way, the proposed method tackles the limitation on initialization and optimization, leading to an efficient and accurate 3DGS modeling. Extensive experiments demonstrate that EasySplat outperforms the current state-of-the-art (SOTA) in handling novel view synthesis.

Recently, implicit function-based approaches have advanced 3D human reconstruction from a single-view image. However, previous methods suffer from issues such as noisy artifacts, loss of geometric details, and broken limbs under the scenarios of challenging poses. To address these problems, a novel end-to-end deep neural network named ReGIR is proposed, which is a multi-level architecture combining the parametric model with implicit function. The architecture consists of a coarse level and a fine level, and for each level, normal maps and the signed distance function (SDF) are introduced to encode query points. Furthermore, the network is trained in a coarse-to-fine manner to enable robust human body reconstruction with geometric details. Our extensive qualitative and quantitative experiments demonstrate that ReGIR achieves competitive reconstruction results.

Pan-sharpening aims to fuse panchromatic (PAN) images with low-resolution multi-spectral (LR-MS) images to generate high-resolution multi-spectral (HR-MS) images. Despite the impressive performance of existing learning-based methods, they are constrained by coarse fusion strategies in frequency or spatial domain. In this paper, we discover that PAN images can provide all the spatial textures required for HR-MS images, while spectral information must be provided jointly by PAN and LR-MS images. Inspired by this, we propose a noval frequency-spatial domain information fusion network for pan-sharpening, called FSDNet. Specifically, we design a Dual-Domain Information Processing Module (DDPM) to construct FSDNet. It consists of a Frequency Domain Feature Processing Block (FDB), a Spatial Domain Information Processing Block (SDB), and an Information Fusion Block (IFB). The FDB in the frequency domain uses the Adaptive Amplitude Fusion Block (AAFB) and convolution layers to finely modulate amplitude and phase components, exploring global information. The SDB uses cascaded residual blocks to capture and enhance local information in the spatial domain. The IFB based on invertible neural networks (INNs) introduces Multi-Scale Self-Attention Block (MSAB), achieves effective information fusion and reduce information loss. Extensive experiments on the QuickBird and GaoFen-2 datasets demonstrate the effectiveness and superiority of our method.

Pan-sharpening aims to reconstruct high-resolution multi-spectral (HR-MS) images from panchromatic (PAN) images and low-resolution multi-spectral (LR-MS) images. Despite demonstrated performance, existing learning-based methods struggle to address the ill-posed problem from spectral and spatial perspectives. Generally, mitigating the ill-posed issue involves obtaining the probability distribution of HR-MS images. In this paper, we propose DuCoFPan, a novel dual-condition flow-based network for pan-sharpening, which learns the distributions of HR-MS images guided by spectral and spatial conditions, respectively. Specifically, we design a Dual-Condition Flow Module (DCFM) that adopts spectral and spatial conditions through reversible affine transformations. For condition injection, we present a Spectral-based Condition Injection Block (SPEB) capturing fine-grained spectral features in the Fourier domain and a Spatial-based Condition Injection Block (SPAB) extracting spatial features. Additionally, we devise a Feature Interaction Block (FIB) to promote information flow. Extensive experiments on QuickBird and GaoFen-2 datasets demonstrate the effectiveness and superiority of our method.