While the community of 3D point cloud generation has witnessed a big growth in recent years, there still lacks an effective way to enable intuitive user control in the generation process, hence limiting the general utility of such methods. Since an intuitive way of decomposing a shape is through its parts, we propose to tackle the task of controllable part-based point cloud generation. We introduce DiffFacto, a novel probabilistic generative model that learns the distribution of shapes with part-level control. We propose a factorization that models independent part style and part configuration distributions, and present a novel cross diffusion network that enables us to generate coherent and plausible shapes under our proposed factorization. Experiments show that our method is able to generate novel shapes with multiple axes of control. It achieves state-of-the-art part-level generation quality and generates plausible and coherent shape, while enabling various downstream editing applications such as shape interpolation, mixing and transformation editing. Code will be made publicly available.
论文检索
输入标题、作者或关键词，从 9,256 篇学术成果中精准定位
Unsupervised anomaly detection aims to train models with only anomaly-free images to detect and localize unseen anomalies. Previous reconstruction-based methods have been limited by inaccurate reconstruction results. This work presents a denoising model to detect and localize the anomalies with a generative diffusion model. In particular, we introduce random noise to overwhelm the anomalous pixels and obtain pixel-wise precise anomaly scores from the intermediate denoising process. We find that the KL divergence of the diffusion model serves as a better anomaly score compared with the traditional RGB space score. Furthermore, we reconstruct the features from a pre-trained deep feature extractor as our feature level score to improve localization performance. Moreover, we propose a gradient denoising process to smoothly transform an anomalous image into a normal one. Our denoising model outperforms the state-of-the-art reconstruction-based anomaly detection methods for precise anomaly localization and high-quality normal image reconstruction on the MVTec-AD benchmark.
Despite the proven significance of hyperspectral images (HSIs) in performing various computer vision tasks, its potential is adversely affected by the low-resolution (LR) property in the spatial domain, resulting from multiple physical factors. Inspired by recent advancements in deep generative models, we propose an HSI Super-resolution (SR) approach with Conditional Diffusion Models (HSR-Diff) that merges a high-resolution (HR) multispectral image (MSI) with the corresponding LR-HSI. HSR-Diff generates an HR-HSI via repeated refinement, in which the HR-HSI is initialized with pure Gaussian noise and iteratively refined. At each iteration, the noise is removed with a Conditional Denoising Transformer (CDFormer) that is trained on denoising at different noise levels, conditioned on the hierarchical feature maps of HR-MSI and LR-HSI. In addition, a progressive learning strategy is employed to exploit the global information of full-resolution images. Systematic experiments have been conducted on four public datasets, demonstrating that HSR-Diff outperforms state-of-the-art methods.
Fashion illustration is used by designers to communicate their vision and to bring the design idea from conceptualization to realization, showing how clothes interact with the human body. In this context, computer vision can thus be used to improve the fashion design process. Differently from previous works that mainly focused on the virtual try-on of garments, we propose the task of multimodal-conditioned fashion image editing, guiding the generation of human-centric fashion images by following multimodal prompts, such as text, human body poses, and garment sketches. We tackle this problem by proposing a new architecture based on latent diffusion models, an approach that has not been used before in the fashion domain. Given the lack of existing datasets suitable for the task, we also extend two existing fashion datasets, namely Dress Code and VITON-HD, with multimodal annotations collected in a semi-automatic manner. Experimental results on these new datasets demonstrate the effectiveness of our proposal, both in terms of realism and coherence with the given multimodal inputs. Source code and collected multimodal annotations are publicly available at: https://github.com/aimagelab/multimodal-garment-designer.
Recent progress in generative models has resulted in models that produce both realistic as well as relevant images for most textual inputs. These models are being used to generate millions of images everyday, and hold the potential to drastically impact areas such as generative art, digital marketing and data augmentation. Given their outsized impact, it is important to ensure that the generated content reflects the artifacts and surroundings across the globe, rather than over-representing certain parts of the world. In this paper, we measure the geographical representativeness of common nouns (e.g., a house) generated through DALL.E 2 and Stable Diffusion models using a crowdsourced study comprising 540 participants across 27 countries. For deliberately underspecified inputs without country names, the generated images most reflect the surroundings of the United States followed by India, and the top generations rarely reflect surroundings from all other countries (average score less than 3 out of 5). Specifying the country names in the input increases the representativeness by 1.44 points on average on a 5-point Likert scale for DALL.E 2 and 0.75 for Stable Diffusion, however, the overall scores for many countries still remain low, highlighting the need for future models to be more geographically inclusive. Lastly, we examine the feasibility of quantifying the geographical representativeness of generated images without conducting user studies.
Recently, diffusion models have achieved remarkable success in text-to-image generation, enabling the creation of high-quality images from text prompts and various conditions. However, existing methods for customizing these models are limited by handling multiple personalized subjects and the risk of overfitting. Moreover, the large parameter space is inefficient for model storage. In this paper, we propose a novel approach to address the limitations in existing text-to-image diffusion models for personalization and customization. Our method involves fine-tuning the singular values of the weight matrices, leading to a compact and efficient parameter space that reduces the risk of overfitting and language-drifting. Our approach also includes a Cut-Mix-Unmix data-augmentation technique to enhance the quality of multi-subject image generation and a simple text-based image editing framework. Our proposed SVDiff method has a significantly smaller model size (1.7MB for StableDiffusion) compared to existing methods, making it more practical for real-world applications.
Despite all recent progress, it is still challenging to edit and manipulate natural images with modern generative models. When using Generative Adversarial Network (GAN), one major hurdle is in the inversion process mapping a real image to its corresponding noise vector in the latent space, since its necessary to be able to reconstruct an image to edit its contents. Likewise for Denoising Diffusion Implicit Models (DDIM), the linearization assumption in each inversion step makes the whole deterministic inversion process unreliable. Existing approaches that have tackled the problem of inversion stability often incur in significant trade-offs in computational efficiency. In this work we propose an Accelerated Iterative Diffusion Inversion method, dubbed AIDI, that significantly improves reconstruction accuracy with minimal additional overhead in space and time complexity. By using a novel blended guidance technique, we show that effective results can be obtained on a large range of image editing tasks without large classifier-free guidance in inversion. Furthermore, when compared with other diffusion inversion based works, our proposed process is shown to be more robust for fast image editing in the 10 and 20 diffusion steps' regimes.
Large-scale pre-training tasks like image classification, captioning, or self-supervised techniques do not incentivize learning the semantic boundaries of objects. However, recent generative foundation models built using text-based latent diffusion techniques may learn semantic boundaries. This is because they have to synthesize intricate details about all objects in an image based on a text description. Therefore, we present a technique for segmenting real and AI-generated images using latent diffusion models (LDMs) trained on internet-scale datasets. First, we show that the latent space of LDMs (z-space) is a better input representation compared to other feature representations like RGB images or CLIP encodings for text-based image segmentation. By training the segmentation models on the latent z-space, which creates a compressed representation across several domains like different forms of art, cartoons, illustrations, and photographs, we are also able to bridge the domain gap between real and AI-generated images. We show that the internal features of LDMs contain rich semantic information and present a technique in the form of LD-ZNet to further boost the performance of text-based segmentation. Overall, we show up to 6% improvement over standard baselines for text-to-image segmentation on natural images. For AI-generated imagery, we show close to 20% improvement compared to state-of-the-art techniques. The project is available at https://koutilya-pnvr.github.io/LD-ZNet/.
While text-to-image synthesis currently enjoys great popularity among researchers and the general public, the security of these models has been neglected so far. Many text-guided image generation models rely on pre-trained text encoders from external sources, and their users trust that the retrieved models will behave as promised. Unfortunately, this might not be the case. We introduce backdoor attacks against text-guided generative models and demonstrate that their text encoders pose a major tampering risk. Our attacks only slightly alter an encoder so that no suspicious model behavior is apparent for image generations with clean prompts. By then inserting a single character trigger into the prompt, e.g., a non-Latin character or emoji, the adversary can trigger the model to either generate images with pre-defined attributes or images following a hidden, potentially malicious description. We empirically demonstrate the high effectiveness of our attacks on Stable Diffusion and highlight that the injection process of a single backdoor takes less than two minutes. Besides phrasing our approach solely as an attack, it can also force an encoder to forget phrases related to certain concepts, such as nudity or violence, and help to make image generation safer.
Text-guided human motion generation has drawn significant interest because of its impactful applications spanning animation and robotics. Recently, application of diffusion models for motion generation has enabled improvements in the quality of generated motions. However, existing approaches are limited by their reliance on relatively small-scale motion capture data, leading to poor performance on more diverse, in-the-wild prompts. In this paper, we introduce Make-An-Animation, a text-conditioned human motion generation model which learns more diverse poses and prompts from large-scale image-text datasets, enabling significant improvement in performance over prior works. Make-An-Animation is trained in two stages. First, we train on a curated large-scale dataset of (text, static pseudo-pose) pairs extracted from image-text datasets. Second, we fine-tune on motion capture data, adding additional layers to model the temporal dimension. Unlike prior diffusion models for motion generation, Make-An-Animation uses a U-Net architecture similar to recent text-to-video generation models. Human evaluation of motion realism and alignment with input text shows that our model reaches state-of-the-art performance on text-to-motion generation.
Previous raw image-based low-light image enhancement methods predominantly relied on feed-forward neural networks to learn deterministic mappings from low-light to normally-exposed images. However, they failed to capture critical distribution information, leading to visually undesirable results. This work addresses the issue by seamlessly integrating a diffusion model with a physics-based exposure model. Different from a vanilla diffusion model that has to perform Gaussian denoising, with the injected physics-based exposure model, our restoration process can directly start from a noisy image instead of pure noise. As such, our method obtains significantly improved performance and reduced inference time compared with vanilla diffusion models. To make full use of the advantages of different intermediate steps, we further propose an adaptive residual layer that effectively screens out the side-effect in the iterative refinement when the intermediate results have been already well-exposed. The proposed framework can work with both real-paired datasets, SOTA noise models, and different backbone networks. We evaluate the proposed method on various public benchmarks, achieving promising results with consistent improvements using different exposure models and backbones. Besides, the proposed method achieves better generalization capacity for unseen amplifying ratios and better performance than a larger feedforward neural model when few parameters are adopted. The code is released at https://github.com/wyf0912/ExposureDiffusion.
In this work, we focus on synthesizing high-quality textures on 3D meshes. We present Point-UV diffusion, a coarse-to-fine pipeline that marries the denoising diffusion model with UV mapping to generate 3D consistent and high-quality texture images in UV space. We start with introducing a point diffusion model to synthesize low-frequency texture components with our tailored style guidance to tackle the biased color distribution. The derived coarse texture offers global consistency and serves as a condition for the subsequent UV diffusion stage, aiding in regularizing the model to generate a 3D consistent UV texture image. Then, a UV diffusion model with hybrid conditions is developed to enhance the texture fidelity in the 2D UV space. Our method can process meshes of any genus, generating diversified, geometry-compatible, and high-fidelity textures.
In this paper, we rethink the low-light image enhancement task and propose a physically explainable and generative diffusion model for low-light image enhancement, termed as Diff-Retinex. We aim to integrate the advantages of the physical model and the generative network. Furthermore, we hope to supplement and even deduce the information missing in the low-light image through the generative network. Therefore, Diff-Retinex formulates the low-light image enhancement problem into Retinex decomposition and conditional image generation. In the Retinex decomposition, we integrate the superiority of attention in Transformer and meticulously design a Retinex Transformer decomposition network (TDN) to decompose the image into illumination and reflectance maps. Then, we design multi-path generative diffusion networks to reconstruct the normal-light Retinex probability distribution and solve the various degradations in these components respectively, including dark illumination, noise, color deviation, loss of scene contents, etc. Owing to generative diffusion model, Diff-Retinex puts the restoration of low-light subtle detail into practice. Extensive experiments conducted on real-world low-light datasets qualitatively and quantitatively demonstrate the effectiveness, superiority, and generalization of the proposed method.
Semantic segmentation has made significant progress in recent years thanks to deep neural networks, but the common objective of generating a single segmentation output that accurately matches the image's content may not be suitable for safety-critical domains such as medical diagnostics and autonomous driving. Instead, multiple possible correct segmentation maps may be required to reflect the true distribution of annotation maps. In this context, stochastic semantic segmentation methods must learn to predict conditional distributions of labels given the image, but this is challenging due to the typically multimodal distributions, high-dimensional output spaces, and limited annotation data. To address these challenges, we propose a conditional categorical diffusion model (CCDM) for semantic segmentation based on Denoising Diffusion Probabilistic Models. Our model is conditioned to the input image, enabling it to generate multiple segmentation label maps that account for the aleatoric uncertainty arising from divergent ground truth annotations. Our experimental results show that CCDM achieves state-of-the-art performance on LIDC, a stochastic semantic segmentation dataset, and outperforms established baselines on the classical segmentation dataset Cityscapes.
The surprisingly fluent predictive performance of LLM (Large Language Models) as well as the high-quality photo-realistic rendering of Diffusion Models has heralded a new beginning in the area of Generative AI. Such kinds of deep learning based models with billions of parameters and pre-trained on massive-scale data-sets are also called Large Foundation Models (LFM). These models not only have caught the public imagination but also have led to an unprecedented surge in interest towards the applications of these models. Instead of the previous approach of developing AI models for specific tasks, more and more researchers are developing large task-agnostic models pre-trained on massive data, which can then be adapted to a variety of downstream tasks via fine-tuning, fewshot learning, or zero-shot learning. Some examples are ChatGPT, LLaMA, GPT-4, Flamingo, MidJourney, Stable-Diffusion and DALLE. Some of them can handle text (e.g., ChatGPT, LLaMA) while some others (e.g., GPT-4 and Flamingo) can utilize multimodal data and can hence be considered Multimodal Large Foundation Models (MLFM). Several recent studies have shown that when adapted to specific tasks (e.g., visual question answering), the foundation models can often surpass the performance of state-of-the-art, fully supervised AI models. However, applying foundation models to specialized domain tasks (e.g., medical diagnosis, financial recommendation etc.) raises many ethical issues (e.g., privacy, model bias or hallucinations). The panel members will discuss the emerging trends in the development and use of large multimodal foundation models. Some of the issues to be discussed are: Research issues in going from LLM to MLFM Behaviour of MLFM Application Potential of MLFM Trust issues in MLFM Limitations of MLFM Societal, Legal and Regulatory issues of MLFM Promising future research in MLFM This panel will bring together several leading experts from universities, research institutions, and industry who will discuss and debate together with the audience. We invite everybody to participate and contribute towards this important and promising research direction.
Diffusion models have shown impressive capabilities in the generative AI space. These models have the capability to create images in a variety of styles from photorealistic and futuristic to many more artistic styles by simply using text prompts. This tutorial aims to introduce the underlying mechanisms that make these models successful along with hands-on exercises. The tutorial will start with explaining the diffusion concept with forward and reverse processes. Then, it will cover the fine-tuning process and the control procedures such as guidance and conditioning. The provided hands-on exercises will help apply these concepts on some real-world problems.
With the development of deep learning, multimedia data generation (e.g., image generation, audio synthesis, music composition, and video generation) has attracted a lot of attention. Deep learning methods for data generation usually build a mapping from source condition X to target data Y. The target Y (e.g., image, speech, music, video) is usually high-dimensional and complex, and contains rich information not exist in source data, which hinders the effective and efficient learning on the source-target mapping. Representation learning has achieved rapid progress in the past decade, which is beneficial for data understanding tasks. However, traditional representation learning cannot address the challenges faced by multimedia data generation tasks. This tutorial revisits the learning paradigms for data generation and introduces a paradigm called regeneration learning that can improve the effectiveness and efficiency of multimedia data generation. We show that a variety of tasks in multimedia data generation (e.g., image generation, speech synthesis, music composition, video generation) can benefit from this regeneration learning paradigm, and a lot of recent popular data generation models (e.g., DALL-E 1/2, Stable Diffusion, AudioLM, NaturalSpeech 2, MusicLM) can be covered by this learning paradigm.
Offline Multiple Appropriate Facial Reaction Generation (OMAFRG) aims to predict the reaction of different listeners given a speaker, which is useful in the senario of human-computer interaction and social media analysis. In recent years, the Offline Facial Reactions Generation (OFRG) task has been explored in different ways. However, most studies only focus on the deterministic reaction of the listeners. The research of the non-deterministic (i.e. OMAFRG) always lacks of sufficient attention and the results are far from satisfactory. Compared with the deterministic OFRG tasks, the OMAFRG task is closer to the true circumstance but corresponds to higher difficulty for its requirement of modeling stochasticity and context. In this paper, we propose a new model named FRDiff to tackle this issue. Our model is developed based on the diffusion model architecture with some modification to enhance its ability of aggregating the context features. And the inherent property of stochasticity in diffusion model enables our model to generate multiple reactions. We conduct experiments on the datasets provided by the ACM Multimedia REACT2023 and obtain the second place on the board, which demonstrates the effectiveness of our method.
We demonstrate an automatic 3D creation system, which can create realistic 3D assets solely from a text or image prompt without requiring any specialized 3D modeling skills. Users can either describe the object they envision in natural language or upload a reference image that records what they have seen with the phone. Our system will generate a high-quality 3D mesh that faithfully matches the users' input. We propose a coarse-to-fine framework to achieve this goal. Specifically, we first obtain a low-resolution mesh instantly by utilizing a pre-trained text/image conditional 3D generative model. Using such coarse mesh as the initialization, we further optimize a high-resolution textured 3D mesh with fine-grained appearance guidance from large-scale 2D diffusion models. Our system can create visually-pleasing results in minutes, which is significantly faster than existing methods. Meanwhile, the system ensures that the resulting 3D assets are precisely aligned with the input text or image prompt. With these advanced capabilities, our demonstration provides a streamlined and intuitive platform for users to incorporate 3D creation into their daily lives.
MobileVidFactory: Automatic Diffusion-Based Social Media Video Generation for Mobile Devices from Text
PDF ↗Videos for mobile devices become the most popular access to share and acquire information recently. For the convenience of users' creation, in this paper, we present a system, namely MobileVidFactory, to automatically generate vertical mobile videos where users only need to give simple texts mainly. Our system consists of two parts: basic and customized generation. In the basic generation, we utilize the pretrained image diffusion model, and adapt it to a high-quality open-domain vertical video generator. As for the audio, by retrieving from our big database, our system matches a suitable background sound for the video. Additionally to produce customized content, our system allows users to add specified screen texts for enriching visual expression, and specify texts for automatic reading with optional voices as they like.