Related papers: From Geometric Mimicry to Comprehensive Generation…
Text-to-image diffusion models exhibit remarkable generative capabilities, but lack precise control over object counts and spatial arrangements. This work introduces a two-stage system to address these compositional limitations. The first…
Cross-modality data translation has attracted great interest in image computing. Deep generative models (\textit{e.g.}, GANs) show performance improvement in tackling those problems. Nevertheless, as a fundamental challenge in image…
Recent progress in diffusion models significantly advances various image generation tasks. However, the current mainstream approach remains focused on building task-specific models, which have limited efficiency when supporting a wide range…
Identity-consistent generation has become an important focus in text-to-image research, with recent models achieving notable success in producing images aligned with a reference identity. Yet, the scarcity of large-scale paired datasets…
Despite the unprecedented success of text-to-image diffusion models, controlling the number of depicted objects using text is surprisingly hard. This is important for various applications from technical documents, to children's books to…
Image deocclusion (or amodal completion) aims to recover the invisible regions (\ie, shape and appearance) of occluded instances in images. Despite recent advances, the scarcity of high-quality data that balances diversity, plausibility,…
The recent surge in interest in city layout generation underscores its significance in urban planning and smart city development. The task involves procedurally or automatically generating spatial arrangements for urban elements such as…
Generative modeling is typically framed as learning mapping rules, but from an observer's perspective without access to these rules, the task becomes disentangling the geometric support from the probability distribution. We propose that…
Diffusion-based models have achieved state-of-the-art performance on text-to-image synthesis tasks. However, one critical limitation of these models is the low fidelity of generated images with respect to the text description, such as…
With the rapid adoption of diffusion models, synthetic data generation has emerged as a promising approach for addressing the growing demand for large-scale image datasets. However, images generated purely by diffusion models often exhibit…
Geospatial imaging leverages data from diverse sensing modalities-such as EO, SAR, and LiDAR, ranging from ground-level drones to satellite views. These heterogeneous inputs offer significant opportunities for scene understanding but…
Recently, large-scale diffusion models, e.g., Stable diffusion and DallE2, have shown remarkable results on image synthesis. On the other hand, large-scale cross-modal pre-trained models (e.g., CLIP, ALIGN, and FILIP) are competent for…
Interior design is a complex and creative discipline involving aesthetics, functionality, ergonomics, and materials science. Effective solutions must meet diverse requirements, typically producing multiple deliverables such as renderings…
In recent years, event cameras have gained significant attention due to their bio-inspired properties, such as high temporal resolution and high dynamic range. However, obtaining large-scale labeled ground-truth data for event-based vision…
How should representations from complementary sensors be integrated for autonomous driving? Geometry-based sensor fusion has shown great promise for perception tasks such as object detection and motion forecasting. However, for the actual…
Large-scale text-to-image models have demonstrated amazing ability to synthesize diverse and high-fidelity images. However, these models are often violated by several limitations. Firstly, they require the user to provide precise and…
Recent advancements in deep learning for medical image segmentation are often limited by the scarcity of high-quality training data.While diffusion models provide a potential solution by generating synthetic images, their effectiveness in…
Recent years have seen remarkable progress in both multimodal understanding models and image generation models. Despite their respective successes, these two domains have evolved independently, leading to distinct architectural paradigms:…
The generation of sounding videos has seen significant advancements with the advent of diffusion models. However, existing methods often lack the fine-grained control needed to generate viewpoint-specific content from larger, immersive…
Diffusion models have attracted significant attention due to the remarkable ability to create content and generate data for tasks like image classification. However, the usage of diffusion models to generate the high-quality object…