In this work, we study the task of ``visually" translating scene text from a source language (e.g., English) to a target language (e.g., Chinese). Visual translation involves not just the recognition and translation of scene text but also the generation of the translated image that preserves visual features of the text, such as font, size, and background. There are several challenges associated with this task, such as interpolating font to unseen characters and preserving text size and the background. To address these, we introduce VTNet, a novel conditional diffusion-based method. To train the VTNet, we create a synthetic cross-lingual dataset of 600K samples of scene text images in six popular languages, including English, Hindi, Tamil, Chinese, Bengali, and German. We evaluate the performance of VTnet through extensive experiments and comparisons to related methods. Our model also surpasses the previous state-of-the-art results on the conventional scene-text editing benchmarks. Further, we present rigorous qualitative studies to understand the strengths and shortcomings of our model. Results show that our approach generalizes well to unseen words and fonts. We firmly believe our work can benefit real-world applications, such as text translation using a phone camera and translating educational materials. Code and data will be made publicly available.
Accurate detection of movable and moving objects in LiDAR is of vital importance for navigation. Most existing works focus on extracting and removing moving objects during navigation. Movable objects like pedestrians, parked vehicles, etc. although static may move in the future. This leads to erroneous navigation and accidents. In such cases, it becomes necessary to detect potentially movable objects. To this end, we present a learning-based approach that segments movable and moving objects by generating static parts of scenes that are otherwise occluded. Our model performs superior to existing baselines on static LiDAR reconstructions using 3 datasets including a challenging sparse industrial dataset. We achieve this without the assistance of any segmentation labels because such labels might not always be available for less popular yet important settings like industrial environments. The non-movable static parts of the scene generated by our model are of vital importance for downstream navigation for SLAM. The movable objects detected by our model can be fed to a downstream 3D detector for aiding navigation. Though we do not use segmentation, we evaluate our method against navigation baselines that use it to remove dynamic objects for SLAM. Through extensive experiments on several datasets, we showcase that our model surpasses these baselines on navigation.
Text erasure from an image is helpful for various tasks such as image editing and privacy preservation. In this paper, we present TPFNet, a novel one-stage (end-toend) network for text removal from images. Our network has two parts: feature synthesis and image generation. Since noise can be more effectively removed from low-resolution images, part 1 operates on low-resolution images. The output of part 1 is a low-resolution text-free image. Part 2 uses the features learned in part 1 to predict a high-resolution text-free image. In part 1, we use "pyramidal vision transformer" (PVT) as the encoder. Further, we use a novel multi-headed decoder that generates a high-pass filtered image and a segmentation map, in addition to a text-free image. The segmentation branch helps locate the text precisely, and the high-pass branch helps in learning the image structure. To precisely locate the text, TPFNet employs an adversarial loss that is conditional on the segmentation map rather than the input image. On Oxford, SCUT, and SCUT-EnsText datasets, our network outperforms recently proposed networks on nearly all the metrics. For example, on SCUT-EnsText dataset, TPFNet has a PSNR (higher is better) of 39.0 and text-detection precision (lower is better) of 21.1, compared to the best previous technique, which has a PSNR of 32.3 and precision of 53.2. The source code can be obtained from https://github.com/CandleLabAI/TPFNet
We propose a novel deep learning model named ACLNet, for cloud segmentation from ground images. ACLNet uses both deep neural network and machine learning (ML) algorithm to extract complementary features. Specifically, it uses EfficientNet-B0 as the backbone, "`a trous spatial pyramid pooling" (ASPP) to learn at multiple receptive fields, and "global attention module" (GAM) to extract finegrained details from the image. ACLNet also uses k-means clustering to extract cloud boundaries more precisely. ACLNet is effective for both daytime and nighttime images. It provides lower error rate, higher recall and higher F1-score than state-of-art cloud segmentation models. The source-code of ACLNet is available here: https://github.com/ckmvigil/ACLNet.