Satellite-to-street view synthesis aims at generating a realistic street-view image from its corresponding satellite-view image. Although stable diffusion models have exhibit remarkable performance in a variety of image generation applications, their reliance on similar-view inputs to control the generated structure or texture restricts their application to the challenging cross-view synthesis task. In this work, we propose CrossViewDiff, a cross-view diffusion model for satellite-to-street view synthesis. To address the challenges posed by the large discrepancy across views, we design the satellite scene structure estimation and cross-view texture mapping modules to construct the structural and textural controls for street-view image synthesis. We further design a cross-view control guided denoising process that incorporates the above controls via an enhanced cross-view attention module. To achieve a more comprehensive evaluation of the synthesis results, we additionally design a GPT-based scoring method as a supplement to standard evaluation metrics. We also explore the effect of different data sources (e.g., text, maps, building heights, and multi-temporal satellite imagery) on this task. Results on three public cross-view datasets show that CrossViewDiff outperforms current state-of-the-art on both standard and GPT-based evaluation metrics, generating high-quality street-view panoramas with more realistic structures and textures across rural, suburban, and urban scenes. The code and models of this work will be released at https://opendatalab.github.io/CrossViewDiff/.
Dual-energy computed tomography (DECT) has been widely used to obtain quantitative elemental composition of imaged subjects for personalized and precise medical diagnosis. Compared with DECT leveraging advanced X-ray source and/or detector technologies, the use of the sequential-scanning data acquisition scheme to implement DECT may make a broader impact on clinical practice because this scheme requires no specialized hardware designs and can be directly implemented into conventional CT systems. However, since the concentration of iodinated contrast agent in the imaged subject varies over time, sequentially scanned data sets acquired at two tube potentials are temporally inconsistent. As existing material basis image reconstruction approaches assume that the data sets acquired at two tube potentials are temporally consistent, the violation of this assumption results in inaccurate quantification of material concentration. In this work, we developed sequential-scanning DECT imaging using high temporal resolution image reconstruction and error-compensated material basis image generation, ACCELERATION in short, to address the technical challenge induced by temporal inconsistency of sequentially scanned data sets and improve quantification accuracy of material concentration in sequential-scanning DECT. ACCELERATION has been validated and evaluated using numerical simulation data sets generated from clinical human subject exams and experimental human subject studies. Results demonstrated the improvement of quantification accuracy and image quality using ACCELERATION.
Simple data augmentation techniques, such as rotations and flips, are widely used to enhance the generalization power of computer vision models. However, these techniques often fail to modify high-level semantic attributes of a class. To address this limitation, researchers have explored generative augmentation methods like the recently proposed DA-Fusion. Despite some progress, the variations are still largely limited to textural changes, thus falling short on aspects like varied viewpoints, environment, weather conditions, or even class-level semantic attributes (eg, variations in a dog's breed). To overcome this challenge, we propose DIAGen, building upon DA-Fusion. First, we apply Gaussian noise to the embeddings of an object learned with Textual Inversion to diversify generations using a pre-trained diffusion model's knowledge. Second, we exploit the general knowledge of a text-to-text generative model to guide the image generation of the diffusion model with varied class-specific prompts. Finally, we introduce a weighting mechanism to mitigate the impact of poorly generated samples. Experimental results across various datasets show that DIAGen not only enhances semantic diversity but also improves the performance of subsequent classifiers. The advantages of DIAGen over standard augmentations and the DA-Fusion baseline are particularly pronounced with out-of-distribution samples.
Variational Autoencoders (VAEs), as a form of deep generative model, have been widely used in recent years, and shown great great peformance in a number of different domains, including image generation and anomaly detection, etc.. This paper aims to explore neural network model compression method based on VAE. The experiment uses different neural network models for MNIST recognition as compression targets, including Feedforward Neural Network (FNN), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM). These models are the most basic models in deep learning, and other more complex and advanced models are based on them or inherit their features and evolve. In the experiment, the first step is to train the models mentioned above, each trained model will have different accuracy and number of total parameters. And then the variants of parameters for each model are processed as training data in VAEs separately, and the trained VAEs are tested by the true model parameters. The experimental results show that using the latent space as a representation of the model compression can improve the compression rate compared to some traditional methods such as pruning and quantization, meanwhile the accuracy is not greatly affected using the model parameters reconstructed based on the latent space. In the future, a variety of different large-scale deep learning models will be used more widely, so exploring different ways to save time and space on saving or transferring models will become necessary, and the use of VAE in this paper can provide a basis for these further explorations.
Variational Autoencoders (VAEs) are a popular framework for unsupervised learning and data generation. A plethora of methods have been proposed focusing on improving VAEs, with the incorporation of adversarial objectives and the integration of prior learning mechanisms being prominent directions. When it comes to the former, an indicative instance is the recently introduced family of Introspective VAEs aiming at ensuring that a low likelihood is assigned to unrealistic samples. In this study, we focus on the Soft-IntroVAE (S-IntroVAE) and investigate the implication of incorporating a multimodal and learnable prior into this framework. Namely, we formulate the prior as a third player and show that when trained in cooperation with the decoder constitutes an effective way for prior learning, which shares the Nash Equilibrium with the vanilla S-IntroVAE. Furthermore, based on a modified formulation of the optimal ELBO in S-IntroVAE, we develop theoretically motivated regularizations, that is (i) adaptive variance clipping to stabilize training when learning the prior and (ii) responsibility regularization to discourage the formation of inactive prior mode. Finally, we perform a series of targeted experiments on a 2D density estimation benchmark and in an image generation setting comprised of the (F)-MNIST and CIFAR-10 datasets demonstrating the benefit of prior learning in S-IntroVAE in generation and representation learning.
Text-driven 3D scene generation has seen significant advancements recently. However, most existing methods generate single-view images using generative models and then stitch them together in 3D space. This independent generation for each view often results in spatial inconsistency and implausibility in the 3D scenes. To address this challenge, we proposed a novel text-driven 3D-consistent scene generation model: SceneDreamer360. Our proposed method leverages a text-driven panoramic image generation model as a prior for 3D scene generation and employs 3D Gaussian Splatting (3DGS) to ensure consistency across multi-view panoramic images. Specifically, SceneDreamer360 enhances the fine-tuned Panfusion generator with a three-stage panoramic enhancement, enabling the generation of high-resolution, detail-rich panoramic images. During the 3D scene construction, a novel point cloud fusion initialization method is used, producing higher quality and spatially consistent point clouds. Our extensive experiments demonstrate that compared to other methods, SceneDreamer360 with its panoramic image generation and 3DGS can produce higher quality, spatially consistent, and visually appealing 3D scenes from any text prompt. Our codes are available at \url{https://github.com/liwrui/SceneDreamer360}.
The performance of anomaly inspection in industrial manufacturing is constrained by the scarcity of anomaly data. To overcome this challenge, researchers have started employing anomaly generation approaches to augment the anomaly dataset. However, existing anomaly generation methods suffer from limited diversity in the generated anomalies and struggle to achieve a seamless blending of this anomaly with the original image. In this paper, we overcome these challenges from a new perspective, simultaneously generating a pair of the overall image and the corresponding anomaly part. We propose DualAnoDiff, a novel diffusion-based few-shot anomaly image generation model, which can generate diverse and realistic anomaly images by using a dual-interrelated diffusion model, where one of them is employed to generate the whole image while the other one generates the anomaly part. Moreover, we extract background and shape information to mitigate the distortion and blurriness phenomenon in few-shot image generation. Extensive experiments demonstrate the superiority of our proposed model over state-of-the-art methods in terms of both realism and diversity. Overall, our approach significantly improves the performance of downstream anomaly detection tasks, including anomaly detection, anomaly localization, and anomaly classification tasks.
Concept-based explanations have become a popular choice for explaining deep neural networks post-hoc because, unlike most other explainable AI techniques, they can be used to test high-level visual "concepts" that are not directly related to feature attributes. For instance, the concept of "stripes" is important to classify an image as a zebra. Concept-based explanation methods, however, require practitioners to guess and collect multiple candidate concept image sets, which can often be imprecise and labor-intensive. Addressing this limitation, in this paper, we frame concept image set creation as an image generation problem. However, since naively using a generative model does not result in meaningful concepts, we devise a reinforcement learning-based preference optimization (RLPO) algorithm that fine-tunes the vision-language generative model from approximate textual descriptions of concepts. Through a series of experiments, we demonstrate the capability of our method to articulate complex and abstract concepts which aligns with the test class that are otherwise challenging to craft manually. In addition to showing the efficacy and reliability of our method, we show how our method can be used as a diagnostic tool for analyzing neural networks.
Traditional dietary assessment methods heavily rely on self-reporting, which is time-consuming and prone to bias. Recent advancements in Artificial Intelligence (AI) have revealed new possibilities for dietary assessment, particularly through analysis of food images. Recognizing foods and estimating food volumes from images are known as the key procedures for automatic dietary assessment. However, both procedures required large amounts of training images labeled with food names and volumes, which are currently unavailable. Alternatively, recent studies have indicated that training images can be artificially generated using Generative Adversarial Networks (GANs). Nonetheless, convenient generation of large amounts of food images with known volumes remain a challenge with the existing techniques. In this work, we present a simple GAN-based neural network architecture for conditional food image generation. The shapes of the food and container in the generated images closely resemble those in the reference input image. Our experiments demonstrate the realism of the generated images and shape-preserving capabilities of the proposed framework.
Our study delves into the fusion of abstract art interpretation and text-to-image synthesis, addressing the challenge of achieving precise spatial control over image composition solely through textual prompts. Leveraging the capabilities of ControlNet, we empower users with finer control over the synthesis process, enabling enhanced manipulation of synthesized imagery. Inspired by the minimalist forms found in abstract artworks, we introduce a novel condition crafted from geometric primitives such as triangles.
Compositionality is a critical capability in Text-to-Image (T2I) models, as it reflects their ability to understand and combine multiple concepts from text descriptions. Existing evaluations of compositional capability rely heavily on human-designed text prompts or fixed templates, limiting their diversity and complexity, and yielding low discriminative power. We propose ConceptMix, a scalable, controllable, and customizable benchmark which automatically evaluates compositional generation ability of T2I models. This is done in two stages. First, ConceptMix generates the text prompts: concretely, using categories of visual concepts (e.g., objects, colors, shapes, spatial relationships), it randomly samples an object and k-tuples of visual concepts, then uses GPT4-o to generate text prompts for image generation based on these sampled concepts. Second, ConceptMix evaluates the images generated in response to these prompts: concretely, it checks how many of the k concepts actually appeared in the image by generating one question per visual concept and using a strong VLM to answer them. Through administering ConceptMix to a diverse set of T2I models (proprietary as well as open ones) using increasing values of k, we show that our ConceptMix has higher discrimination power than earlier benchmarks. Specifically, ConceptMix reveals that the performance of several models, especially open models, drops dramatically with increased k. Importantly, it also provides insight into the lack of prompt diversity in widely-used training datasets. Additionally, we conduct extensive human studies to validate the design of ConceptMix and compare our automatic grading with human judgement. We hope it will guide future T2I model development.
Food image composition requires the use of existing dish images and background images to synthesize a natural new image, while diffusion models have made significant advancements in image generation, enabling the construction of end-to-end architectures that yield promising results. However, existing diffusion models face challenges in processing and fusing information from multiple images and lack access to high-quality publicly available datasets, which prevents the application of diffusion models in food image composition. In this paper, we introduce a large-scale, high-quality food image composite dataset, FC22k, which comprises 22,000 foreground, background, and ground truth ternary image pairs. Additionally, we propose a novel food image composition method, Foodfusion, which leverages the capabilities of the pre-trained diffusion models and incorporates a Fusion Module for processing and integrating foreground and background information. This fused information aligns the foreground features with the background structure by merging the global structural information at the cross-attention layer of the denoising UNet. To further enhance the content and structure of the background, we also integrate a Content-Structure Control Module. Extensive experiments demonstrate the effectiveness and scalability of our proposed method.
Text-to-Image(T2I) models have achieved remarkable success in image generation and editing, yet these models still have many potential issues, particularly in generating inappropriate or Not-Safe-For-Work(NSFW) content. Strengthening attacks and uncovering such vulnerabilities can advance the development of reliable and practical T2I models. Most of the previous works treat T2I models as white-box systems, using gradient optimization to generate adversarial prompts. However, accessing the model's gradient is often impossible in real-world scenarios. Moreover, existing defense methods, those using gradient masking, are designed to prevent attackers from obtaining accurate gradient information. While several black-box jailbreak attacks have been explored, they achieve the limited performance of jailbreaking T2I models due to difficulties associated with optimization in discrete spaces. To address this, we propose HTS-Attack, a heuristic token search attack method. HTS-Attack begins with an initialization that removes sensitive tokens, followed by a heuristic search where high-performing candidates are recombined and mutated. This process generates a new pool of candidates, and the optimal adversarial prompt is updated based on their effectiveness. By incorporating both optimal and suboptimal candidates, HTS-Attack avoids local optima and improves robustness in bypassing defenses. Extensive experiments validate the effectiveness of our method in attacking the latest prompt checkers, post-hoc image checkers, securely trained T2I models, and online commercial models.
The robotics community has consistently aimed to achieve generalizable robot manipulation with flexible natural language instructions. One primary challenge is that obtaining robot trajectories fully annotated with both actions and texts is time-consuming and labor-intensive. However, partially-annotated data, such as human activity videos without action labels and robot trajectories without text labels, are much easier to collect. Can we leverage these data to enhance the generalization capabilities of robots? In this paper, we propose GR-MG, a novel method which supports conditioning on a text instruction and a goal image. During training, GR-MG samples goal images from trajectories and conditions on both the text and the goal image or solely on the image when text is not available. During inference, where only the text is provided, GR-MG generates the goal image via a diffusion-based image-editing model and conditions on both the text and the generated image. This approach enables GR-MG to leverage large amounts of partially-annotated data while still using languages to flexibly specify tasks. To generate accurate goal images, we propose a novel progress-guided goal image generation model which injects task progress information into the generation process. In simulation experiments, GR-MG improves the average number of tasks completed in a row of 5 from 3.35 to 4.04. In real-robot experiments, GR-MG is able to perform 58 different tasks and improves the success rate from 68.7\% to 78.1\% and 44.4\% to 60.6\% in simple and generalization settings, respectively. It also outperforms comparing baseline methods in few-shot learning of novel skills. Video demos, code, and checkpoints are available on the project page: https://gr-mg.github.io/.
Text-driven diffusion models have achieved remarkable success in image editing, but a crucial component in these models-text embeddings-has not been fully explored. The entanglement and opacity of text embeddings present significant challenges to achieving precise image editing. In this paper, we provide a comprehensive and in-depth analysis of text embeddings in Stable Diffusion XL, offering three key insights. First, while the 'aug_embedding' captures the full semantic content of the text, its contribution to the final image generation is relatively minor. Second, 'BOS' and 'Padding_embedding' do not contain any semantic information. Lastly, the 'EOS' holds the semantic information of all words and contains the most style features. Each word embedding plays a unique role without interfering with one another. Based on these insights, we propose a novel approach for controllable image editing using a free-text embedding control method called PSP (Prompt-Softbox-Prompt). PSP enables precise image editing by inserting or adding text embeddings within the cross-attention layers and using Softbox to define and control the specific area for semantic injection. This technique allows for obejct additions and replacements while preserving other areas of the image. Additionally, PSP can achieve style transfer by simply replacing text embeddings. Extensive experimental results show that PSP achieves significant results in tasks such as object replacement, object addition, and style transfer.
Animating human face images aims to synthesize a desired source identity in a natural-looking way mimicking a driving video's facial movements. In this context, Generative Adversarial Networks have demonstrated remarkable potential in real-time face reenactment using a single source image, yet are constrained by limited geometry consistency compared to graphic-based approaches. In this paper, we introduce Geometry-guided GAN for Face Animation (G3FA) to tackle this limitation. Our novel approach empowers the face animation model to incorporate 3D information using only 2D images, improving the image generation capabilities of the talking head synthesis model. We integrate inverse rendering techniques to extract 3D facial geometry properties, improving the feedback loop to the generator through a weighted average ensemble of discriminators. In our face reenactment model, we leverage 2D motion warping to capture motion dynamics along with orthogonal ray sampling and volume rendering techniques to produce the ultimate visual output. To evaluate the performance of our G3FA, we conducted comprehensive experiments using various evaluation protocols on VoxCeleb2 and TalkingHead benchmarks to demonstrate the effectiveness of our proposed framework compared to the state-of-the-art real-time face animation methods.
Following the advancements in text-guided image generation technology exemplified by Stable Diffusion, video generation is gaining increased attention in the academic community. However, relying solely on text guidance for video generation has serious limitations, as videos contain much richer content than images, especially in terms of motion. This information can hardly be adequately described with plain text. Fortunately, in computer vision, various visual representations can serve as additional control signals to guide generation. With the help of these signals, video generation can be controlled in finer detail, allowing for greater flexibility for different applications. Integrating various controls, however, is nontrivial. In this paper, we propose a universal framework called EasyControl. By propagating and injecting condition features through condition adapters, our method enables users to control video generation with a single condition map. With our framework, various conditions including raw pixels, depth, HED, etc., can be integrated into different Unet-based pre-trained video diffusion models at a low practical cost. We conduct comprehensive experiments on public datasets, and both quantitative and qualitative results indicate that our method outperforms state-of-the-art methods. EasyControl significantly improves various evaluation metrics across multiple validation datasets compared to previous works. Specifically, for the sketch-to-video generation task, EasyControl achieves an improvement of 152.0 on FVD and 19.9 on IS, respectively, in UCF101 compared with VideoComposer. For fidelity, our model demonstrates powerful image retention ability, resulting in high FVD and IS in UCF101 and MSR-VTT compared to other image-to-video models.
The emergence of text-to-image synthesis (TIS) models has significantly influenced digital image creation by producing high-quality visuals from written descriptions. Yet these models heavily rely on the quality and specificity of textual prompts, posing a challenge for novice users who may not be familiar with TIS-model-preferred prompt writing. Existing solutions relieve this via automatic model-preferred prompt generation from user queries. However, this single-turn manner suffers from limited user-centricity in terms of result interpretability and user interactivity. To address these issues, we propose DialPrompt, a multi-turn dialogue-based TIS prompt generation model that emphasises user-centricity. DialPrompt is designed to follow a multi-turn guidance workflow, where in each round of dialogue the model queries user with their preferences on possible optimization dimensions before generating the final TIS prompt. To achieve this, we mined 15 essential dimensions for high-quality prompts from advanced users and curated a multi-turn dataset. Through training on this dataset, DialPrompt can improve interpretability by allowing users to understand the correlation between specific phrases and image attributes. Additionally, it enables greater user control and engagement in the prompt generation process, leading to more personalized and visually satisfying outputs. Experiments indicate that DialPrompt achieves a competitive result in the quality of synthesized images, outperforming existing prompt engineering approaches by 5.7%. Furthermore, in our user evaluation, DialPrompt outperforms existing approaches by 46.5% in user-centricity score and is rated 7.9/10 by 19 human reviewers.
Recent advancements in text-to-image models, such as Stable Diffusion, show significant demographic biases. Existing de-biasing techniques rely heavily on additional training, which imposes high computational costs and risks of compromising core image generation functionality. This hinders them from being widely adopted to real-world applications. In this paper, we explore Stable Diffusion's overlooked potential to reduce bias without requiring additional training. Through our analysis, we uncover that initial noises associated with minority attributes form "minority regions" rather than scattered. We view these "minority regions" as opportunities in SD to reduce bias. To unlock the potential, we propose a novel de-biasing method called 'weak guidance,' carefully designed to guide a random noise to the minority regions without compromising semantic integrity. Through analysis and experiments on various versions of SD, we demonstrate that our proposed approach effectively reduces bias without additional training, achieving both efficiency and preservation of core image generation functionality.
Coupling latent diffusion based image generation with contextual bandits enables the creation of eye-catching personalized product images at scale that was previously either impossible or too expensive. In this paper we showcase how we utilized these technologies to increase user engagement with recommendations in online retargeting campaigns for e-commerce.