Related papers: MILD: Multi-Layer Diffusion Strategy for Complex a…

The goal of scene text image super-resolution is to reconstruct high-resolution text-line images from unrecognizable low-resolution inputs. The existing methods relying on the optimization of pixel-level loss tend to yield text edges that…

Beyond high-fidelity image synthesis, diffusion models have recently exhibited promising results in dense visual perception tasks. However, most existing work treats diffusion models as a standalone component for perception tasks, employing…

In image classification, a significant problem arises from bias in the datasets. When it contains only specific types of images, the classifier begins to rely on shortcuts - simplistic and erroneous rules for decision-making. This leads to…

Recent generative-prior-based methods have shown promising blind face restoration performance. They usually project the degraded images to the latent space and then decode high-quality faces either by single-stage latent optimization or…

Diffusion models have shown superior performance in image generation and manipulation, but the inherent stochasticity presents challenges in preserving and manipulating image content and identity. While previous approaches like DreamBooth…

Diffusion Transformers (DiTs) have emerged as a leading architecture for text-to-image synthesis, producing high-quality and photorealistic images. However, the quadratic scaling properties of the attention in DiTs hinder image generation…

We present a novel method for 3D scene editing using diffusion models, designed to ensure view consistency and realism across perspectives. Our approach leverages attention features extracted from a single reference image to define the…

Semantic segmentation demands dense pixel-level annotations, which can be prohibitively expensive - especially under extremely constrained labeling budgets. In this paper, we address the problem of low-budget active learning for semantic…

While 2D diffusion models have achieved remarkable success in identity-preserving personalization, extending this capability to 3D assets remains a significant challenge due to the complexities of multi-view consistency and spatial control.…

Understanding how neural populations in higher visual areas encode object-centered visual information remains a central challenge in computational neuroscience. Prior works have investigated representational alignment between artificial…

Despite the rapid advancement of unsupervised learning in visual representation, it requires training on large-scale datasets that demand costly data collection, and pose additional challenges due to concerns regarding data privacy.…

While Masked Diffusion Language Models (MDLMs) relying on token masking and unmasking have shown promise in language modeling, their computational efficiency and generation flexibility remain constrained by the masking paradigm. In this…

Collaborative 3D object detection holds significant importance in the field of autonomous driving, as it greatly enhances the perception capabilities of each individual agent by facilitating information exchange among multiple agents.…

Person re-identification is a key challenge for surveillance across multiple sensors. Prompted by the advent of powerful deep learning models for visual recognition, and inexpensive RGB-D cameras and sensor-rich mobile robotic platforms,…

Cloud contamination severely degrades the usability of remote sensing imagery and poses a fundamental challenge for downstream Earth observation tasks. Recently, diffusion-based models have emerged as a dominant paradigm for remote sensing…

Facial Landmark Detection (FLD) in thermal imagery is critical for applications in challenging lighting conditions, but it is hampered by the lack of rich visual cues. Conventional cross-modal solutions, like feature fusion or image…

Text-driven image generation using diffusion models has recently gained significant attention. To enable more flexible image manipulation and editing, recent research has expanded from single image generation to transparent layer generation…

Recent advancements in diffusion models have notably improved the perceptual quality of generated images in text-to-image synthesis tasks. However, diffusion models often struggle to produce images that accurately reflect the intended…

Text-guided image editing model has achieved great success in general domain. However, directly applying these models to the fashion domain may encounter two issues: (1) Inaccurate localization of editing region; (2) Weak editing magnitude.…

Multiple Instance Learning (MIL) has garnered widespread attention in the field of Whole Slide Image (WSI) classification as it replaces pixel-level manual annotation with diagnostic reports as labels, significantly reducing labor costs.…