Related papers: HyperDiT: Hyper-Connected Transformers for High-Fi…

Semantic segmentation, which aims to classify every pixel in an image, is a key task in machine perception, with many applications across robotics and autonomous driving. Due to the high dimensionality of this task, most existing approaches…

Modern Latent Diffusion Models (LDMs) typically operate in low-level Variational Autoencoder (VAE) latent spaces that are primarily optimized for pixel-level reconstruction. To unify vision generation and understanding, a burgeoning trend…

In the realm of high-resolution (HR), fine-grained image segmentation, the primary challenge is balancing broad contextual awareness with the precision required for detailed object delineation, capturing intricate details and the finest…

Recent advances in diffusion transformers (DiTs) have set new standards in image generation, yet remain impractical for on-device deployment due to their high computational and memory costs. In this work, we present an efficient DiT…

Diffusion models have shown remarkable performance in image generation in recent years. However, due to a quadratic increase in memory during generating ultra-high-resolution images (e.g. 4096*4096), the resolution of generated images is…

Hyperspectral Image (HSI) classification is an important issue in remote sensing field with extensive applications in earth science. In recent years, a large number of deep learning-based HSI classification methods have been proposed.…

Diffusion Transformers (DiTs) excel at generation, but their global self-attention makes controllable, reference-image-based editing a distinct challenge. Unlike U-Nets, naively injecting local appearance into a DiT can disrupt its holistic…

Preparing training data for deep vision models is a labor-intensive task. To address this, generative models have emerged as an effective solution for generating synthetic data. While current generative models produce image-level category…

We study generative super-resolution (SR) in real-world scenarios where content and degradations vary across domains, genres, and segments. For example, images and videos may alternate between text overlays, fast motion, smooth cartoons,…

The fast development of self-supervised learning lowers the bar learning feature representation from massive unlabeled data and has triggered a series of research on change detection of remote sensing images. Challenges in adapting…

Pixel diffusion aims to generate images directly in pixel space in an end-to-end fashion. This approach avoids the limitations of VAE in the two-stage latent diffusion, offering higher model capacity. Existing pixel diffusion models suffer…

The key to integrating visual language tasks is to establish a good alignment strategy. Recently, visual semantic representation has achieved fine-grained visual understanding by dividing grids or image patches. However, the coarse-grained…

A visual metaphor constitutes a high-order form of human creativity, employing cross-domain semantic fusion to transform abstract concepts into impactful visual rhetoric. Despite the remarkable progress of generative AI, existing models…

Although image-based virtual try-on has made considerable progress, emerging approaches still encounter challenges in producing high-fidelity and robust fitting images across diverse scenarios. These methods often struggle with issues such…

Diffusion Transformers (DiT) have established a new state-of-the-art in high-fidelity image synthesis; however, their massive computational complexity and memory requirements hinder local deployment on resource-constrained edge devices. In…

Recovering clean and accurate geometry from images is essential for robotics and augmented reality. However, existing geometry foundation models still suffer severely from flying pixels and the loss of fine details. In this paper, we…

Weakly supervised semantic segmentation (WSSS) approaches typically rely on class activation maps (CAMs) for initial seed generation, which often fail to capture global context due to limited supervision from image-level labels. To address…

Hypergraphs play a pivotal role in the modelling of data featuring higher-order relations involving more than two entities. Hypergraph neural networks emerge as a powerful tool for processing hypergraph-structured data, delivering…

This manuscript presents PoreDiT, a novel generative model designed for high-efficiency digital rock reconstruction at gigavoxel scales. Addressing the significant challenges in digital rock physics (DRP), particularly the trade-off between…

Large-scale pre-trained diffusion models have been extensively adopted for real-world image Super-Resolution because of their powerful generative priors through textual guidance. However, when super-resolving high-resolution images with…