Despite the remarkable developments achieved by recent 3D generation works, scaling these methods to geographic extents, such as modeling thousands of square kilometers of Earth’s surface, remains an open challenge. We address this through a dual innovation in data infrastructure and model architecture. First, we introduce Aerial-Earth3D, the largest 3D aerial dataset to date, consisting of 50k curated scenes (each measuring 600m) captured across the U.S. mainland, comprising 45M multi-view Google Earth frames. Each scene provides pose-annotated multi-view images, depth maps, normals, semantic segmentation, and camera poses, with explicit quality control to ensure terrain diversity. Building on this foundation, we propose EarthCrafter, a tailored framework for large-scale 3D Earth generation via sparse-decoupled latent diffusion. Our architecture separates structural and textural generation: 1) Dual sparse 3D-VAEs compress high-resolution geometric voxels and textural 2D Gaussian Splats (2DGS) into compact latent spaces, largely alleviating the costly computation suffering from vast geographic scales while preserving critical information. 2) We propose condition-aware flow matching models trained on mixed inputs (semantics, images, or neither) to flexibly model latent geometry and texture features independently. Extensive experiments demonstrate that EarthCrafter performs substantially better in extremely large-scale generation. The framework further supports versatile applications, from semantic-guided urban layout generation to unconditional terrain synthesis, while maintaining geographic plausibility through our rich data priors from Aerial-Earth3D.

We introduce MVGenMaster, a multi-view diffusion model enhanced with 3D priors to address versatile Novel View Synthesis (NVS) tasks. MVGenMaster leverages 3D priors that are warped using metric depth and camera poses, significantly enhancing both generalization and 3D consistency in NVS. Our model features a simple yet effective pipeline that can generate up to 100 novel views conditioned on variable reference views and camera poses with a single forward process. Additionally, we have developed a comprehensive large-scale multi-view image dataset called MvD-1M, comprising up to 1.6 million scenes, equipped with well-aligned metric depth to train MVGenMaster. Moreover, we present several training and model modifications to strengthen the model with scaled-up datasets. Extensive evaluations across in- and out- of- domain benchmarks demonstrate the effectiveness of our proposed method and data formulation.

Arbitrary neural style transfer has been a popular research topic due to its rich application scenarios. Effective disentanglement of content and style is the critical factor for synthesizing an image with arbitrary style. The existing methods focus on disentangling feature representations of content and style in the spatial domain where the content and style components are innately entangled and difficult to be disentangled clearly. Therefore, these methods always suffer from low-quality results because of the sub-optimal disentanglement. To address such a challenge, this paper proposes the frequency mixer (FreMixer) module that disentangles and re-entangles the frequency spectrum of content and style components in the frequency domain. Since content and style components have different frequency-domain characteristics (frequency bands and frequency patterns), the FreMixer could well disentangle these two components. Based on the FreMixer module, we design a novel Frequency Domain Disentanglement (FDD) framework for arbitrary neural style transfer. Qualitative and quantitative experiments verify that the proposed method can render better stylized results compared to the state-of-the-art methods.

With the advancement of geo-systems and the increased availability of satellite data, a plethora of Land-Use and Land-Cover (LULC) products have been developed. The existing LULC products primarily relied on time-series imagery to classify land by pixel-based classifiers, allowing for local analysis and accurate boundary detection. However, the advent of deep learning has shifted towards the use of patch-based CNN models for generating land cover maps. In this paper, (1) we create a training dataset for China using a voting strategy based on three off-the-shelf available LULC products, avoiding the labor-intensive manual annotation. (2) We design a novel CNN-based model for LULC task, called Multi-modal Fine-grained Dual Network (dubbed as Dual-Net), which takes dual-date images to generate final maps, and reduces the need for gap-free temporal sequences or separate cloud detection. To leverage the correlation between location, date, and category, we embed multi-modal information (dates and geo-locations) to the model. Further, by incorporating low-level constraints and using pseudo-label refinement, we continually improve the performance and achieve more refined segmentation. (3) Due to the lack of a suitable validation dataset for China, we create a new validation dataset called China Sentinel2 Validation Dataset (CSVD) by manually annotating 733 finely labeled images of 1024 × 1024 pixels of China-specific Sentinel2 data. (4) Extensive experiments demonstrate that our model outperforms existing LULC products and produces more fine-grained segmentation results comparable to other patch-based products. Finally, we release annual LULC maps for China in 2020-2022 and also make our model accessible online for real-time results export.