相关论文: TextSSR: Diffusion-based Data Synthesis for Scene …

Segmentation-based methods are widely used for scene text detection due to their superiority in describing arbitrary-shaped text instances. However, two major problems still exist: 1) current label generation techniques are mostly empirical…

In recent years, significant progress has been made in scene text recognition by data-driven methods. However, due to the scarcity of annotated real-world data, the training of these methods predominantly relies on synthetic data. The…

Synthetic face recognition (SFR) aims to generate synthetic face datasets that mimic the distribution of real face data, which allows for training face recognition models in a privacy-preserving manner. Despite the remarkable potential of…

Scene text removal (STR) contains two processes: text localization and background reconstruction. Through integrating both processes into a single network, previous methods provide an implicit erasure guidance by modifying all pixels in the…

Recent scene text detection methods are almost based on deep learning and data-driven. Synthetic data is commonly adopted for pre-training due to expensive annotation cost. However, there are obvious domain discrepancies between synthetic…

Although recent works based on deep learning have made progress in improving recognition accuracy on scene text recognition, how to handle low-quality text images in end-to-end deep networks remains a research challenge. In this paper, we…

It is highly desirable to obtain a model that can generate high-quality 3D meshes from text prompts in just seconds. While recent attempts have adapted pre-trained text-to-image diffusion models, such as Stable Diffusion (SD), into…

Image super-resolution (SR) aims to reconstruct high resolution images with both high perceptual quality and low distortion, but is fundamentally limited by the perception-distortion trade-off. GAN-based SR methods reduce distortion but…

Driven by deep neural networks and large scale datasets, scene text detection methods have progressed substantially over the past years, continuously refreshing the performance records on various standard benchmarks. However, limited by the…

Inspired by speech recognition, recent state-of-the-art algorithms mostly consider scene text recognition as a sequence prediction problem. Though achieving excellent performance, these methods usually neglect an important fact that text in…

This paper presents the first exploration of text-to-image diffusion models for zero-shot sketch-based 3D shape retrieval (ZS-SBSR). Existing sketch-based 3D shape retrieval methods struggle in zero-shot settings due to the absence of…

The adaptation capability to a wide range of domains is crucial for scene text spotting models when deployed to real-world conditions. However, existing state-of-the-art (SOTA) approaches usually incorporate scene text detection and…

Diffusion-based models have been widely used in various visual generation tasks, showing promising results in image super-resolution (SR), while typically being limited by dozens or even hundreds of sampling steps. Although existing methods…

Generating a coherent sequence of images that tells a visual story, using text-to-image diffusion models, often faces the critical challenge of maintaining subject consistency across all story scenes. Existing approaches, which typically…

We demonstrate that pre-trained text-to-image diffusion models, despite being trained on raster images, possess a remarkable capacity to guide vector sketch synthesis. In this paper, we introduce DiffSketcher, a novel algorithm for…

In this paper we introduce a new method for text detection in natural images. The method comprises two contributions: First, a fast and scalable engine to generate synthetic images of text in clutter. This engine overlays synthetic text to…

Text-to-image diffusion models produce impressive results but are frustrating tools for artists who desire fine-grained control. For example, a common use case is to create images of a specific instance in novel contexts, i.e.,…

Training models to high-end performance requires availability of large labeled datasets, which are expensive to get. The goal of our work is to automatically synthesize labeled datasets that are relevant for a downstream task. We propose…

A classical problem in computer vision is to infer a 3D scene representation from few images that can be used to render novel views at interactive rates. Previous work focuses on reconstructing pre-defined 3D representations, e.g. textured…

Recent progress in 3D scene understanding enables scalable learning of representations across large datasets of diverse scenes. As a consequence, generalization to unseen scenes and objects, rendering novel views from just a single or a…