Related papers: TextBoost: Boosting Scene Text Fidelity in Ultra-l…
Digital camera and mobile document image acquisition are new trends arising in the world of Optical Character Recognition and text detection. In some cases, such process integrates many distortions and produces poorly scanned text or…
This paper deals with deep transductive learning, and proposes TransBoost as a procedure for fine-tuning any deep neural model to improve its performance on any (unlabeled) test set provided at training time. TransBoost is inspired by a…
Extremely low-light text images are common in natural scenes, making scene text detection and recognition challenging. One solution is to enhance these images using low-light image enhancement methods before text extraction. However,…
Text Recognition is one of the challenging tasks of computer vision with considerable practical interest. Optical character recognition (OCR) enables different applications for automation. This project focuses on word detection and…
Ultra-high-resolution (UHR) remote sensing imagery couples kilometer-scale context with query-critical evidence that may occupy only a few pixels. Such vast spatial scale leads to a quadratic explosion of visual tokens and hinders the…
Image codecs are typically optimized to trade-off bitrate \vs distortion metrics. At low bitrates, this leads to compression artefacts which are easily perceptible, even when training with perceptual or adversarial losses. To improve image…
Recent advancements in prompt tuning have successfully adapted large-scale models like Contrastive Language-Image Pre-trained (CLIP) for downstream tasks such as scene text detection. Typically, text prompt complements the text encoder's…
Traditional image compression methods aim to reconstruct images for human perception, prioritizing visual fidelity over task relevance. In contrast, Coding for Machines focuses on preserving information essential for automated…
Over the past few years, the field of scene text detection has progressed rapidly that modern text detectors are able to hunt text in various challenging scenarios. However, they might still fall short when handling text instances of…
In this Technical Report we propose a set of improvements with respect to the KernelBoost classifier presented in [Becker et al., MICCAI 2013]. We start with a scheme inspired by Auto-Context, but that is suitable in situations where the…
This study addresses the challenge of, without training or fine-tuning, controlling the global color aspect of images generated with a diffusion model. We rewrite the guidance equations to ensure that the outputs are closer to a known color…
Text-to-image diffusion models are typically trained to optimize the log-likelihood objective, which presents challenges in meeting specific requirements for downstream tasks, such as image aesthetics and image-text alignment. Recent…
Text and faces are among the most perceptually salient and practically important patterns in visual generation, yet they remain challenging for autoregressive generators built on discrete tokenization. A central bottleneck is the tokenizer:…
A rapidly increasing portion of Internet traffic is dominated by requests from mobile devices with limited- and metered-bandwidth constraints. To satisfy these requests, it has become standard practice for websites to transmit small and…
Artificial Intelligence-Generated Content (AIGC) has made significant strides, with high-resolution text-to-image (T2I) generation becoming increasingly critical for improving users' Quality of Experience (QoE). Although…
Diffusion-based generative image compression has demonstrated remarkable potential for achieving realistic reconstruction at ultra-low bitrates. The key to unlocking this potential lies in making the entire compression process…
In this paper, we introduce the problem of zero-shot text-guided exploration of the solutions to open-domain image super-resolution. Our goal is to allow users to explore diverse, semantically accurate reconstructions that preserve data…
Scene text recognition in low-resource languages frequently faces challenges due to the limited availability of training datasets derived from real-world scenes. This study proposes a novel approach that generates text images in…
We present a method for exploiting weakly annotated images to improve text extraction pipelines. The approach uses an arbitrary end-to-end text recognition system to obtain text region proposals and their, possibly erroneous,…
Image tokenization, the process of transforming raw image pixels into a compact low-dimensional latent representation, has proven crucial for scalable and efficient image generation. However, mainstream image tokenization methods generally…