PyTorchKR Papers

최신 논문

총 7,085편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2407.04842공식 코드 · Papers with Code

MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?

While text-to-image models like DALLE-3 and Stable Diffusion are rapidly proliferating, they often encounter challenges such as hallucination, bias, and the production of unsafe, low-quality output. To effectively address these issues, it is crucial to align these models with desired behaviors based on feedback from a multimodal judge. Despite their significance, current multimodal judges frequently undergo inadequate evaluation of their capabilities and limitations, potentially leading to misalignment and unsafe fine-tuning outcomes. To address this issue, we introduce MJ-Bench, a novel benchmark which incorporates a comprehensive preference dataset to evaluate multimodal judges in providing feedback for image generation models across four key perspectives: alignment, safety, image quality, and bias. Specifically, we evaluate a large variety of multimodal judges including smaller-sized CLIP-based scoring models, open-source VLMs (e.g. LLaVA family), and close-source VLMs (e.g. GPT-4o, Claude 3) on each decomposed subcategory of our preference dataset. Experiments reveal that close-source VLMs generally provide better feedback, with GPT-4o outperforming other judges in average. Compared with open-source VLMs, smaller-sized scoring models can provide better feedback regarding text-image alignment and image quality, while VLMs provide more accurate feedback regarding safety and generation bias due to their stronger reasoning capabilities. Further studies in feedback scale reveal that VLM judges can generally provide more accurate and stable feedback in natural language (Likert-scale) than numerical scales. Notably, human evaluations on end-to-end fine-tuned models using separate feedback from these multimodal judges provide similar conclusions, further confirming the effectiveness of MJ-Bench. All data, code, models are available at https://huggingface.co/MJ-Bench.

arXiv:2407.06109공식 코드 · Papers with Code

PerLDiff: Controllable Street View Synthesis Using Perspective-Layout Diffusion Models

Controllable generation is considered a potentially vital approach to address the challenge of annotating 3D data, and the precision of such controllable generation becomes particularly imperative in the context of data production for autonomous driving. Existing methods focus on the integration of diverse generative information into controlling inputs, utilizing frameworks such as GLIGEN or ControlNet, to produce commendable outcomes in controllable generation. However, such approaches intrinsically restrict generation performance to the learning capacities of predefined network architectures. In this paper, we explore the integration of controlling information and introduce PerLDiff (\textbf{Per}spective-\textbf{L}ayout \textbf{Diff}usion Models), a method for effective street view image generation that fully leverages perspective 3D geometric information. Our PerLDiff employs 3D geometric priors to guide the generation of street view images with precise object-level control within the network learning process, resulting in a more robust and controllable output. Moreover, it demonstrates superior controllability compared to alternative layout control methods. Empirical results justify that our PerLDiff markedly enhances the precision of generation on the NuScenes and KITTI datasets.

arXiv:2407.05842공식 코드 · Papers with Code

3D Vessel Graph Generation Using Denoising Diffusion

Blood vessel networks, represented as 3D graphs, help predict disease biomarkers, simulate blood flow, and aid in synthetic image generation, relevant in both clinical and pre-clinical settings. However, generating realistic vessel graphs that correspond to an anatomy of interest is challenging. Previous methods aimed at generating vessel trees mostly in an autoregressive style and could not be applied to vessel graphs with cycles such as capillaries or specific anatomical structures such as the Circle of Willis. Addressing this gap, we introduce the first application of \textit{denoising diffusion models} in 3D vessel graph generation. Our contributions include a novel, two-stage generation method that sequentially denoises node coordinates and edges. We experiment with two real-world vessel datasets, consisting of microscopic capillaries and major cerebral vessels, and demonstrate the generalizability of our method for producing diverse, novel, and anatomically plausible vessel graphs.

arXiv:2407.05600

GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editing

Despite the success achieved by existing image generation and editing methods, current models still struggle with complex problems including intricate text prompts, and the absence of verification and self-correction mechanisms makes the generated images unreliable. Meanwhile, a single model tends to specialize in particular tasks and possess the corresponding capabilities, making it inadequate for fulfilling all user requirements. We propose GenArtist, a unified image generation and editing system, coordinated by a multimodal large language model (MLLM) agent. We integrate a comprehensive range of existing models into the tool library and utilize the agent for tool selection and execution. For a complex problem, the MLLM agent decomposes it into simpler sub-problems and constructs a tree structure to systematically plan the procedure of generation, editing, and self-correction with step-by-step verification. By automatically generating missing position-related inputs and incorporating position information, the appropriate tool can be effectively employed to address each sub-problem. Experiments demonstrate that GenArtist can perform various generation and editing tasks, achieving state-of-the-art performance and surpassing existing models such as SDXL and DALL-E 3, as can be seen in Fig. 1. Project page is https://zhenyuw16.github.io/GenArtist_page.

arXiv:2407.05527

Rethinking Image Skip Connections in StyleGAN2

Various models based on StyleGAN have gained significant traction in the field of image synthesis, attributed to their robust training stability and superior performances. Within the StyleGAN framework, the adoption of image skip connection is favored over the traditional residual connection. However, this preference is just based on empirical observations; there has not been any in-depth mathematical analysis on it yet. To rectify this situation, this brief aims to elucidate the mathematical meaning of the image skip connection and introduce a groundbreaking methodology, termed the image squeeze connection, which significantly improves the quality of image synthesis. Specifically, we analyze the image skip connection technique to reveal its problem and introduce the proposed method which not only effectively boosts the GAN performance but also reduces the required number of network parameters. Extensive experiments on various datasets demonstrate that the proposed method consistently enhances the performance of state-of-the-art models based on StyleGAN. We believe that our findings represent a vital advancement in the field of image synthesis, suggesting a novel direction for future research and applications.

arXiv:2407.05428공식 코드 · Papers with Code

Diffusion as Sound Propagation: Physics-inspired Model for Ultrasound Image Generation

Deep learning (DL) methods typically require large datasets to effectively learn data distributions. However, in the medical field, data is often limited in quantity, and acquiring labeled data can be costly. To mitigate this data scarcity, data augmentation techniques are commonly employed. Among these techniques, generative models play a pivotal role in expanding datasets. However, when it comes to ultrasound (US) imaging, the authenticity of generated data often diminishes due to the oversight of ultrasound physics. We propose a novel approach to improve the quality of generated US images by introducing a physics-based diffusion model that is specifically designed for this image modality. The proposed model incorporates an US-specific scheduler scheme that mimics the natural behavior of sound wave propagation in ultrasound imaging. Our analysis demonstrates how the proposed method aids in modeling the attenuation dynamics in US imaging. We present both qualitative and quantitative results based on standard generative model metrics, showing that our proposed method results in overall more plausible images. Our code is available at https://github.com/marinadominguez/diffusion-for-us-images

arXiv:2407.06187

JeDi: Joint-Image Diffusion Models for Finetuning-Free Personalized Text-to-Image Generation

Personalized text-to-image generation models enable users to create images that depict their individual possessions in diverse scenes, finding applications in various domains. To achieve the personalization capability, existing methods rely on finetuning a text-to-image foundation model on a user's custom dataset, which can be non-trivial for general users, resource-intensive, and time-consuming. Despite attempts to develop finetuning-free methods, their generation quality is much lower compared to their finetuning counterparts. In this paper, we propose Joint-Image Diffusion (\jedi), an effective technique for learning a finetuning-free personalization model. Our key idea is to learn the joint distribution of multiple related text-image pairs that share a common subject. To facilitate learning, we propose a scalable synthetic dataset generation technique. Once trained, our model enables fast and easy personalization at test time by simply using reference images as input during the sampling process. Our approach does not require any expensive optimization process or additional modules and can faithfully preserve the identity represented by any number of reference images. Experimental results show that our model achieves state-of-the-art generation quality, both quantitatively and qualitatively, significantly outperforming both the prior finetuning-based and finetuning-free personalization baselines.

arXiv:2407.05259

Multi-scale Conditional Generative Modeling for Microscopic Image Restoration

The advance of diffusion-based generative models in recent years has revolutionized state-of-the-art (SOTA) techniques in a wide variety of image analysis and synthesis tasks, whereas their adaptation on image restoration, particularly within computational microscopy remains theoretically and empirically underexplored. In this research, we introduce a multi-scale generative model that enhances conditional image restoration through a novel exploitation of the Brownian Bridge process within wavelet domain. By initiating the Brownian Bridge diffusion process specifically at the lowest-frequency subband and applying generative adversarial networks at subsequent multi-scale high-frequency subbands in the wavelet domain, our method provides significant acceleration during training and sampling while sustaining a high image generation quality and diversity on par with SOTA diffusion models. Experimental results on various computational microscopy and imaging tasks confirm our method's robust performance and its considerable reduction in its sampling steps and time. This pioneering technique offers an efficient image restoration framework that harmonizes efficiency with quality, signifying a major stride in incorporating cutting-edge generative models into computational microscopy workflows.

arXiv:2407.05712

MobilePortrait: Real-Time One-Shot Neural Head Avatars on Mobile Devices

Existing neural head avatars methods have achieved significant progress in the image quality and motion range of portrait animation. However, these methods neglect the computational overhead, and to the best of our knowledge, none is designed to run on mobile devices. This paper presents MobilePortrait, a lightweight one-shot neural head avatars method that reduces learning complexity by integrating external knowledge into both the motion modeling and image synthesis, enabling real-time inference on mobile devices. Specifically, we introduce a mixed representation of explicit and implicit keypoints for precise motion modeling and precomputed visual features for enhanced foreground and background synthesis. With these two key designs and using simple U-Nets as backbones, our method achieves state-of-the-art performance with less than one-tenth the computational demand. It has been validated to reach speeds of over 100 FPS on mobile devices and support both video and audio-driven inputs.

arXiv:2407.06079

Layered Diffusion Model for One-Shot High Resolution Text-to-Image Synthesis

We present a one-shot text-to-image diffusion model that can generate high-resolution images from natural language descriptions. Our model employs a layered U-Net architecture that simultaneously synthesizes images at multiple resolution scales. We show that this method outperforms the baseline of synthesizing images only at the target resolution, while reducing the computational cost per step. We demonstrate that higher resolution synthesis can be achieved by layering convolutions at additional resolution scales, in contrast to other methods which require additional models for super-resolution synthesis.

arXiv:2407.05980

MMIS: Multimodal Dataset for Interior Scene Visual Generation and Recognition

We introduce MMIS, a novel dataset designed to advance MultiModal Interior Scene generation and recognition. MMIS consists of nearly 160,000 images. Each image within the dataset is accompanied by its corresponding textual description and an audio recording of that description, providing rich and diverse sources of information for scene generation and recognition. MMIS encompasses a wide range of interior spaces, capturing various styles, layouts, and furnishings. To construct this dataset, we employed careful processes involving the collection of images, the generation of textual descriptions, and corresponding speech annotations. The presented dataset contributes to research in multi-modal representation learning tasks such as image generation, retrieval, captioning, and classification.

arXiv:2407.03992공식 코드 · Papers with Code

Medical Image Fusion for High-Level Analysis: A Mutual Enhancement Framework for Unaligned PAT and MRI

Photoacoustic tomography (PAT) offers optical contrast, whereas magnetic resonance imaging (MRI) excels in imaging soft tissue and organ anatomy. The fusion of PAT with MRI holds promising application prospects due to their complementary advantages. Existing image fusion have made considerable progress in pre-registered images, yet spatial deformations are difficult to avoid in medical imaging scenarios. More importantly, current algorithms focus on visual quality and statistical metrics, thus overlooking the requirements of high-level tasks. To address these challenges, we propose an unsupervised fusion model, termed PAMRFuse+, which integrates image generation and registration. Specifically, a cross-modal style transfer network is introduced to simplify cross-modal registration to single-modal registration. Subsequently, a multi-level registration network is employed to predict displacement vector fields. Furthermore, a dual-branch feature decomposition fusion network is proposed to address the challenges of cross-modal feature modeling and decomposition by integrating modality-specific and modality-shared features. PAMRFuse+ achieves satisfactory results in registering and fusing unaligned PAT-MRI datasets. Moreover, for the first time, we evaluate the performance of medical image fusion with multi-organ instance segmentation. Extensive experimental demonstrations reveal the advantages of PAMRFuse+ in improving the performance of medical image analysis tasks.

arXiv:2407.04493공식 코드 · Papers with Code

PROUD: PaRetO-gUided Diffusion Model for Multi-objective Generation

Recent advancements in the realm of deep generative models focus on generating samples that satisfy multiple desired properties. However, prevalent approaches optimize these property functions independently, thus omitting the trade-offs among them. In addition, the property optimization is often improperly integrated into the generative models, resulting in an unnecessary compromise on generation quality (i.e., the quality of generated samples). To address these issues, we formulate a constrained optimization problem. It seeks to optimize generation quality while ensuring that generated samples reside at the Pareto front of multiple property objectives. Such a formulation enables the generation of samples that cannot be further improved simultaneously on the conflicting property functions and preserves good quality of generated samples. Building upon this formulation, we introduce the PaRetO-gUided Diffusion model (PROUD), wherein the gradients in the denoising process are dynamically adjusted to enhance generation quality while the generated samples adhere to Pareto optimality. Experimental evaluations on image generation and protein generation tasks demonstrate that our PROUD consistently maintains superior generation quality while approaching Pareto optimality across multiple property functions compared to various baselines.

arXiv:2407.03961공식 코드 · Papers with Code

Leveraging Latent Diffusion Models for Training-Free In-Distribution Data Augmentation for Surface Defect Detection

Defect detection is the task of identifying defects in production samples. Usually, defect detection classifiers are trained on ground-truth data formed by normal samples (negative data) and samples with defects (positive data), where the latter are consistently fewer than normal samples. State-of-the-art data augmentation procedures add synthetic defect data by superimposing artifacts to normal samples to mitigate problems related to unbalanced training data. These techniques often produce out-of-distribution images, resulting in systems that learn what is not a normal sample but cannot accurately identify what a defect looks like. In this work, we introduce DIAG, a training-free Diffusion-based In-distribution Anomaly Generation pipeline for data augmentation. Unlike conventional image generation techniques, we implement a human-in-the-loop pipeline, where domain experts provide multimodal guidance to the model through text descriptions and region localization of the possible anomalies. This strategic shift enhances the interpretability of results and fosters a more robust human feedback loop, facilitating iterative improvements of the generated outputs. Remarkably, our approach operates in a zero-shot manner, avoiding time-consuming fine-tuning procedures while achieving superior performance. We demonstrate the efficacy and versatility of DIAG with respect to state-of-the-art data augmentation approaches on the challenging KSDD2 dataset, with an improvement in AP of approximately 18% when positive samples are available and 28% when they are missing. The source code is available at https://github.com/intelligolabs/DIAG.

arXiv:2407.03901

DiCTI: Diffusion-based Clothing Designer via Text-guided Input

Recent developments in deep generative models have opened up a wide range of opportunities for image synthesis, leading to significant changes in various creative fields, including the fashion industry. While numerous methods have been proposed to benefit buyers, particularly in virtual try-on applications, there has been relatively less focus on facilitating fast prototyping for designers and customers seeking to order new designs. To address this gap, we introduce DiCTI (Diffusion-based Clothing Designer via Text-guided Input), a straightforward yet highly effective approach that allows designers to quickly visualize fashion-related ideas using text inputs only. Given an image of a person and a description of the desired garments as input, DiCTI automatically generates multiple high-resolution, photorealistic images that capture the expressed semantics. By leveraging a powerful diffusion-based inpainting model conditioned on text inputs, DiCTI is able to synthesize convincing, high-quality images with varied clothing designs that viably follow the provided text descriptions, while being able to process very diverse and challenging inputs, captured in completely unconstrained settings. We evaluate DiCTI in comprehensive experiments on two different datasets (VITON-HD and Fashionpedia) and in comparison to the state-of-the-art (SoTa). The results of our experiments show that DiCTI convincingly outperforms the SoTA competitor in generating higher quality images with more elaborate garments and superior text prompt adherence, both according to standard quantitative evaluation measures and human ratings, generated as part of a user study.

arXiv:2407.03604

Lateralization LoRA: Interleaved Instruction Tuning with Modality-Specialized Adaptations

Recent advancements in Vision-Language Models (VLMs) have led to the development of Vision-Language Generalists (VLGs) capable of understanding and generating interleaved images and text. Despite these advances, VLGs still struggle to follow user instructions for interleaved text and image generation. To address this issue, we introduce LeafInstruct, the first open-sourced interleaved instruction tuning data with over 30,000 high-quality instances across more than 10 domains. Due to the extensive size of existing VLGs, we opt for parameter-efficient tuning. However, we observe that VLGs tuned with a standard LoRA typically exhibit inferior performance in interleaved text-image generation. We attribute this problem to modality interference and the lack of modality-specialized adaptation design. Hence, we propose Lateralization LoRA, a novel modality-specialized adaptation method inspired by the concept of brain lateralization. Lateralization LoRA employs a hybrid approach, combining the traditional linear LoRA and a Convolutional LoRA for generating text and images, enabling the generation of high-quality text and images by leveraging modality-specific structures and parameter sets. We perform instruction tuning of the VLG (i.e., EMU2) using Lateralization LoRA on the LeafInstruct dataset. Extensive experiments demonstrate that EMU2 tuned with Lateralization LoRA achieve state-of-the-art performance, significantly surpassing baseline models in complex interleaved tasks.

arXiv:2407.02804공식 코드 · Papers with Code

Mobile Edge Generation-Enabled Digital Twin: Architecture Design and Research Opportunities

A novel paradigm of mobile edge generation (MEG)-enabled digital twin (DT) is proposed, which enables distributed on-device generation at mobile edge networks for real-time DT applications. First, an MEG-DT architecture is put forward to decentralize generative artificial intelligence (GAI) models onto edge servers (ESs) and user equipments (UEs), which has the advantages of low latency, privacy preservation, and individual-level customization. Then, various single-user and multi-user generation mechanisms are conceived for MEG-DT, which strike trade-offs between generation latency, hardware costs, and device coordination. Furthermore, to perform efficient distributed generation, two operating protocols are explored for transmitting interpretable and latent features between ESs and UEs, namely sketch-based generation and seed-based generation, respectively. Based on the proposed protocols, the convergence between MEG and DT are highlighted. Considering the seed-based image generation scenario, numerical case studies are provided to reveal the superiority of MEG-DT over centralized generation. Finally, promising applications and research opportunities are identified. Code is available at https://github.com/xiaoxiaxusummer/MEG_DT

arXiv:2407.02825

Representation learning with CGAN for casual inference

Conditional Generative Adversarial Nets (CGAN) is often used to improve conditional image generation performance. However, there is little research on Representation learning with CGAN for causal inference. This paper proposes a new method for finding representation learning functions by adopting the adversarial idea. We apply the pattern of CGAN and theoretically emonstrate the feasibility of finding a suitable representation function in the context of two distributions being balanced. The theoretical result shows that when two distributions are balanced, the ideal representation function can be found and thus can be used to further research.

arXiv:2407.03314

BACON: Improving Clarity of Image Captions via Bag-of-Concept Graphs

Advancements in large Vision-Language Models have brought precise, accurate image captioning, vital for advancing multi-modal image understanding and processing. Yet these captions often carry lengthy, intertwined contexts that are difficult to parse and frequently overlook essential cues, posing a great barrier for models like GroundingDINO and SDXL, which lack the strong text encoding and syntax analysis needed to fully leverage dense captions. To address this, we propose BACON, a prompting method that breaks down VLM-generated captions into disentangled, structured elements such as objects, relationships, styles, and themes. This approach not only minimizes confusion from handling complex contexts but also allows for efficient transfer into a JSON dictionary, enabling models without linguistic processing capabilities to easily access key information. We annotated 100,000 image-caption pairs using BACON with GPT-4V and trained an LLaVA captioner on this dataset, enabling it to produce BACON-style captions without relying on costly GPT-4V. Evaluations of overall quality, precision, and recall-as well as user studies-demonstrate that the resulting caption model consistently outperforms other SOTA VLM models in generating high-quality captions. Besides, we show that BACON-style captions exhibit better clarity when applied to various models, enabling them to accomplish previously unattainable tasks or surpass existing SOTA solutions without training. For example, BACON-style captions help GroundingDINO achieve 1.51x higher recall scores on open-vocabulary object detection tasks compared to leading methods.

arXiv:2407.03300공식 코드 · Papers with Code

DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latents

Diffusion models (DMs) have revolutionized generative learning. They utilize a diffusion process to encode data into a simple Gaussian distribution. However, encoding a complex, potentially multimodal data distribution into a single continuous Gaussian distribution arguably represents an unnecessarily challenging learning problem. We propose Discrete-Continuous Latent Variable Diffusion Models (DisCo-Diff) to simplify this task by introducing complementary discrete latent variables. We augment DMs with learnable discrete latents, inferred with an encoder, and train DM and encoder end-to-end. DisCo-Diff does not rely on pre-trained networks, making the framework universally applicable. The discrete latents significantly simplify learning the DM's complex noise-to-data mapping by reducing the curvature of the DM's generative ODE. An additional autoregressive transformer models the distribution of the discrete latents, a simple step because DisCo-Diff requires only few discrete variables with small codebooks. We validate DisCo-Diff on toy data, several image synthesis tasks as well as molecular docking, and find that introducing discrete latents consistently improves model performance. For example, DisCo-Diff achieves state-of-the-art FID scores on class-conditioned ImageNet-64/128 datasets with ODE sampler.