In this work, we address two limitations of existing conditional diffusion models: their slow inference speed due to the iterative denoising process and their reliance on paired data for model fine-tuning. To tackle these issues, we introduce a general method for adapting a single-step diffusion model to new tasks and domains through adversarial learning objectives. Specifically, we consolidate various modules of the vanilla latent diffusion model into a single end-to-end generator network with small trainable weights, enhancing its ability to preserve the input image structure while reducing overfitting. We demonstrate that, for unpaired settings, our model CycleGAN-Turbo outperforms existing GAN-based and diffusion-based methods for various scene translation tasks, such as day-to-night conversion and adding/removing weather effects like fog, snow, and rain. We extend our method to paired settings, where our model pix2pix-Turbo is on par with recent works like Control-Net for Sketch2Photo and Edge2Image, but with a single-step inference. This work suggests that single-step diffusion models can serve as strong backbones for a range of GAN learning objectives. Our code and models are available at https://github.com/GaParmar/img2img-turbo.
Scene depth estimation from paintings can streamline the process of 3D sculpture creation so that visually impaired people appreciate the paintings with tactile sense. However, measuring depth of oriental landscape painting images is extremely challenging due to its unique method of depicting depth and poor preservation. To address the problem of scene depth estimation from oriental landscape painting images, we propose a novel framework that consists of two-step Image-to-Image translation method with CLIP-based image matching at the front end to predict the real scene image that best matches with the given oriental landscape painting image. Then, we employ a pre-trained SOTA depth estimation model for the generated real scene image. In the first step, CycleGAN converts an oriental landscape painting image into a pseudo-real scene image. We utilize CLIP to semantically match landscape photo images with an oriental landscape painting image for training CycleGAN in an unsupervised manner. Then, the pseudo-real scene image and oriental landscape painting image are fed into DiffuseIT to predict a final real scene image in the second step. Finally, we measure depth of the generated real scene image using a pre-trained depth estimation model such as MiDaS. Experimental results show that our approach performs well enough to predict real scene images corresponding to oriental landscape painting images. To the best of our knowledge, this is the first study to measure the depth of oriental landscape painting images. Our research potentially assists visually impaired people in experiencing paintings in diverse ways. We will release our code and resulting dataset.
Hematoxylin and Eosin (H&E) staining is the most commonly used for disease diagnosis and tumor recurrence tracking. Hematoxylin excels at highlighting nuclei, whereas eosin stains the cytoplasm. However, H&E stain lacks details for differentiating different types of cells relevant to identifying the grade of the disease or response to specific treatment variations. Pathologists require special immunohistochemical (IHC) stains that highlight different cell types. These stains help in accurately identifying different regions of disease growth and their interactions with the cell's microenvironment. The advent of deep learning models has made Image-to-Image (I2I) translation a key research area, reducing the need for expensive physical staining processes. Pix2Pix and CycleGAN are still the most commonly used methods for virtual staining applications. However, both suffer from hallucinations or staining irregularities when H&E stain has less discriminate information about the underlying cells IHC needs to highlight (e.g.,CD3 lymphocytes). Diffusion models are currently the state-of-the-art models for image generation and conditional generation tasks. However, they require extensive and diverse datasets (millions of samples) to converge, which is less feasible for virtual staining applications.Inspired by the success of multitask deep learning models for limited dataset size, we propose StainDiffuser, a novel multitask dual diffusion architecture for virtual staining that converges under a limited training budget. StainDiffuser trains two diffusion processes simultaneously: (a) generation of cell-specific IHC stain from H&E and (b) H&E-based cell segmentation using coarse segmentation only during training. Our results show that StainDiffuser produces high-quality results for easier (CK8/18,epithelial marker) and difficult stains(CD3, Lymphocytes).
Visual Place Recognition (VPR) is crucial in computer vision, aiming to retrieve database images similar to a query image from an extensive collection of known images. However, like many vision-related tasks, learning-based VPR often experiences a decline in performance during nighttime due to the scarcity of nighttime images. Specifically, VPR needs to address the cross-domain problem of night-to-day rather than just the issue of a single nighttime domain. In response to these issues, we present NocPlace, which leverages a generated large-scale, multi-view, nighttime VPR dataset to embed resilience against dazzling lights and extreme darkness in the learned global descriptor. Firstly, we establish a day-night urban scene dataset called NightCities, capturing diverse nighttime scenarios and lighting variations across 60 cities globally. Following this, an unpaired image-to-image translation network is trained on this dataset. Using this trained translation network, we process an existing VPR dataset, thereby obtaining its nighttime version. The NocPlace is then fine-tuned using night-style images, the original labels, and descriptors inherited from the Daytime VPR model. Comprehensive experiments on various nighttime VPR test sets reveal that NocPlace considerably surpasses previous state-of-the-art methods.
Image-to-image translation is a common task in computer vision and has been rapidly increasing the impact on the field of medical imaging. Deep learning-based methods that employ conditional generative adversarial networks (cGANs), such as Pix2PixGAN, have been extensively explored to perform image-to-image translation tasks. However, when noisy medical image data are considered, such methods cannot be directly applied to produce clean images. Recently, an augmented GAN architecture named AmbientGAN has been proposed that can be trained on noisy measurement data to synthesize high-quality clean medical images. Inspired by AmbientGAN, in this work, we propose a new cGAN architecture, Ambient-Pix2PixGAN, for performing medical image-to-image translation tasks by use of noisy measurement data. Numerical studies that consider MRI-to-PET translation are conducted. Both traditional image quality metrics and task-based image quality metrics are employed to assess the proposed Ambient-Pix2PixGAN. It is demonstrated that our proposed Ambient-Pix2PixGAN can be successfully trained on noisy measurement data to produce high-quality translated images in target imaging modality.
Generative Adversarial Networks (GANs) have shown remarkable success in modeling complex data distributions for image-to-image translation. Still, their high computational demands prohibit their deployment in practical scenarios like edge devices. Existing GAN compression methods mainly rely on knowledge distillation or convolutional classifiers' pruning techniques. Thus, they neglect the critical characteristic of GANs: their local density structure over their learned manifold. Accordingly, we approach GAN compression from a new perspective by explicitly encouraging the pruned model to preserve the density structure of the original parameter-heavy model on its learned manifold. We facilitate this objective for the pruned model by partitioning the learned manifold of the original generator into local neighborhoods around its generated samples. Then, we propose a novel pruning objective to regularize the pruned model to preserve the local density structure over each neighborhood, resembling the kernel density estimation method. Also, we develop a collaborative pruning scheme in which the discriminator and generator are pruned by two pruning agents. We design the agents to capture interactions between the generator and discriminator by exchanging their peer's feedback when determining corresponding models' architectures. Thanks to such a design, our pruning method can efficiently find performant sub-networks and can maintain the balance between the generator and discriminator more effectively compared to baselines during pruning, thereby showing more stable pruning dynamics. Our experiments on image translation GAN models, Pix2Pix and CycleGAN, with various benchmark datasets and architectures demonstrate our method's effectiveness.
In daily life, we tend to present the front of our faces by staring squarely at a facial recognition machine, instead of facing it sideways, in order to increase the chance of being correctly recognised. Few-shot-learning (FSL) classification is challenging in itself because a model has to identify images that belong to classes previously unseen during training. Therefore, a warped and non-typical query or support image during testing can make it even more challenging for a model to predict correctly. In our work, to increase the chance of correct prediction during testing, we aim to rectify the test input of a trained FSL model by generating new samples of the tested classes through image-to-image translation. An FSL model is usually trained on classes with sufficient samples, and then tested on classes with few-shot samples. Our proposed method first captures the style or shape of the test image, and then identifies a suitable trained class sample. It then transfers the style or shape of the test image to the train-class images for generation of more test-class samples, before performing classification based on a set of generated samples instead of just one sample. Our method has potential in empowering a trained FSL model to score higher during the testing phase without any extra training nor dataset. According to our experiments, by augmenting the support set with just 1 additional generated sample, we can achieve around 2% improvement for trained FSL models on datasets consisting of either animal faces or traffic signs. By augmenting both the support set and the queries, we can achieve even more performance improvement. Our Github Repository is publicly available.
Image-to-Image translation (I2I) is a subtype of Machine Learning (ML) that has tremendous potential in applications where two domains of images and the need for translation between the two exist, such as the removal of fog. For example, this could be useful for autonomous vehicles, which currently struggle with adverse weather conditions like fog. However, datasets for I2I tasks are not abundant and typically hard to acquire. Here, we introduce STEREOFOG, a dataset comprised of $10,067$ paired fogged and clear images, captured using a custom-built device, with the purpose of exploring I2I's potential in this domain. It is the only real-world dataset of this kind to the best of our knowledge. Furthermore, we apply and optimize the pix2pix I2I ML framework to this dataset. With the final model achieving an average Complex Wavelet-Structural Similarity (CW-SSIM) score of $0.76$, we prove the technique's suitability for the problem.
Image-to-image translation (I2IT) refers to the process of transforming images from a source domain to a target domain while maintaining a fundamental connection in terms of image content. In the past few years, remarkable advancements in I2IT were achieved by Generative Adversarial Networks (GANs), which nevertheless struggle with translations requiring high precision. Recently, Diffusion Models have established themselves as the engine of choice for image generation. In this paper we introduce S2ST, a novel framework designed to accomplish global I2IT in complex photorealistic images, such as day-to-night or clear-to-rain translations of automotive scenes. S2ST operates within the seed space of a Latent Diffusion Model, thereby leveraging the powerful image priors learned by the latter. We show that S2ST surpasses state-of-the-art GAN-based I2IT methods, as well as diffusion-based approaches, for complex automotive scenes, improving fidelity while respecting the target domain's appearance across a variety of domains. Notably, S2ST obviates the necessity for training domain-specific translation networks.
Deep learning (DL) has led to significant improvements in medical image synthesis, enabling advanced image-to-image translation to generate synthetic images. However, DL methods face challenges such as domain shift and high demands for training data, limiting their generalizability and applicability. Historically, image synthesis was also carried out using deformable image registration (DIR), a method that warps moving images of a desired modality to match the anatomy of a fixed image. However, concerns about its speed and accuracy led to its decline in popularity. With the recent advances of DL-based DIR, we now revisit and reinvigorate this line of research. In this paper, we propose a fast and accurate synthesis method based on DIR. We use the task of synthesizing a rare magnetic resonance (MR) sequence, white matter nulled (WMn) T1-weighted (T1-w) images, to demonstrate the potential of our approach. During training, our method learns a DIR model based on the widely available MPRAGE sequence, which is a cerebrospinal fluid nulled (CSFn) T1-w inversion recovery gradient echo pulse sequence. During testing, the trained DIR model is first applied to estimate the deformation between moving and fixed CSFn images. Subsequently, this estimated deformation is applied to align the paired WMn counterpart of the moving CSFn image, yielding a synthetic WMn image for the fixed CSFn image. Our experiments demonstrate promising results for unsupervised image synthesis using DIR. These findings highlight the potential of our technique in contexts where supervised synthesis methods are constrained by limited training data.