PyTorchKR Papers

최신 논문

총 7,086편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2503.00745공식 코드 · Papers with Code

Geodesic Diffusion Models for Medical Image-to-Image Generation

Diffusion models transform an unknown data distribution into a Gaussian prior by progressively adding noise until the data become indistinguishable from pure noise. This stochastic process traces a path in probability space, evolving from the original data distribution (considered as a Gaussian with near-zero variance) to an isotropic Gaussian. The denoiser then learns to reverse this process, generating high-quality samples from random Gaussian noise. However, standard diffusion models, such as the Denoising Diffusion Probabilistic Model (DDPM), do not ensure a geodesic (i.e., shortest) path in probability space. This inefficiency necessitates the use of many intermediate time steps, leading to high computational costs in training and sampling. To address this limitation, we propose the Geodesic Diffusion Model (GDM), which defines a geodesic path under the Fisher-Rao metric with a variance-exploding noise scheduler. This formulation transforms the data distribution into a Gaussian prior with minimal energy, significantly improving the efficiency of diffusion models. We trained GDM by continuously sampling time steps from 0 to 1 and using as few as 15 evenly spaced time steps for model sampling. We evaluated GDM on two medical image-to-image generation tasks: CT image denoising and MRI image super-resolution. Experimental results show that GDM achieved state-of-the-art performance while reducing training time by a 50-fold compared to DDPM and 10-fold compared to Fast-DDPM, with 66 times faster sampling than DDPM and a similar sampling speed to Fast-DDPM. These efficiency gains enable rapid model exploration and real-time clinical applications. Our code is publicly available at: https://github.com/mirthAI/GDM-VE.

arXiv:2502.21291공식 코드 · Papers with Code

MIGE: A Unified Framework for Multimodal Instruction-Based Image Generation and Editing

Despite significant progress in diffusion-based image generation, subject-driven generation and instruction-based editing remain challenging. Existing methods typically treat them separately, struggling with limited high-quality data and poor generalization. However, both tasks require capturing complex visual variations while maintaining consistency between inputs and outputs. Therefore, we propose MIGE, a unified framework that standardizes task representations using multimodal instructions. It treats subject-driven generation as creation on a blank canvas and instruction-based editing as modification of an existing image, establishing a shared input-output formulation. MIGE introduces a novel multimodal encoder that maps free-form multimodal instructions into a unified vision-language space, integrating visual and semantic features through a feature fusion mechanism. This unification enables joint training of both tasks, providing two key advantages: (1) Cross-Task Enhancement: By leveraging shared visual and semantic representations, joint training improves instruction adherence and visual consistency in both subject-driven generation and instruction-based editing. (2) Generalization: Learning in a unified format facilitates cross-task knowledge transfer, enabling MIGE to generalize to novel compositional tasks, including instruction-based subject-driven editing. Experiments show that MIGE excels in both subject-driven generation and instruction-based editing while setting a state-of-the-art in the new task of instruction-based subject-driven editing. Code and model have been publicly available at https://github.com/Eureka-Maggie/MIGE.

arXiv:2503.01261

Towards Improved Text-Aligned Codebook Learning: Multi-Hierarchical Codebook-Text Alignment with Long Text

Image quantization is a crucial technique in image generation, aimed at learning a codebook that encodes an image into a discrete token sequence. Recent advancements have seen researchers exploring learning multi-modal codebook (i.e., text-aligned codebook) by utilizing image caption semantics, aiming to enhance codebook performance in cross-modal tasks. However, existing image-text paired datasets exhibit a notable flaw in that the text descriptions tend to be overly concise, failing to adequately describe the images and provide sufficient semantic knowledge, resulting in limited alignment of text and codebook at a fine-grained level. In this paper, we propose a novel Text-Augmented Codebook Learning framework, named TA-VQ, which generates longer text for each image using the visual-language model for improved text-aligned codebook learning. However, the long text presents two key challenges: how to encode text and how to align codebook and text. To tackle two challenges, we propose to split the long text into multiple granularities for encoding, i.e., word, phrase, and sentence, so that the long text can be fully encoded without losing any key semantic knowledge. Following this, a hierarchical encoder and novel sampling-based alignment strategy are designed to achieve fine-grained codebook-text alignment. Additionally, our method can be seamlessly integrated into existing VQ models. Extensive experiments in reconstruction and various downstream tasks demonstrate its effectiveness compared to previous state-of-the-art approaches.

arXiv:2503.01190

Enhancing Retinal Vessel Segmentation Generalization via Layout-Aware Generative Modelling

Generalization in medical segmentation models is challenging due to limited annotated datasets and imaging variability. To address this, we propose Retinal Layout-Aware Diffusion (RLAD), a novel diffusion-based framework for generating controllable layout-aware images. RLAD conditions image generation on multiple key layout components extracted from real images, ensuring high structural fidelity while enabling diversity in other components. Applied to retinal fundus imaging, we augmented the training datasets by synthesizing paired retinal images and vessel segmentations conditioned on extracted blood vessels from real images, while varying other layout components such as lesions and the optic disc. Experiments demonstrated that RLAD-generated data improved generalization in retinal vessel segmentation by up to 8.1%. Furthermore, we present REYIA, a comprehensive dataset comprising 586 manually segmented retinal images. To foster reproducibility and drive innovation, both our code and dataset will be made publicly accessible.

arXiv:2503.01122

ACCORD: Alleviating Concept Coupling through Dependence Regularization for Text-to-Image Diffusion Personalization

Image personalization has garnered attention for its ability to customize Text-to-Image generation using only a few reference images. However, a key challenge in image personalization is the issue of conceptual coupling, where the limited number of reference images leads the model to form unwanted associations between the personalization target and other concepts. Current methods attempt to tackle this issue indirectly, leading to a suboptimal balance between text control and personalization fidelity. In this paper, we take a direct approach to the concept coupling problem through statistical analysis, revealing that it stems from two distinct sources of dependence discrepancies. We therefore propose two complementary plug-and-play loss functions: Denoising Decouple Loss and Prior Decouple loss, each designed to minimize one type of dependence discrepancy. Extensive experiments demonstrate that our approach achieves a superior trade-off between text control and personalization fidelity.

arXiv:2503.01103공식 코드 · Papers with Code

Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator

While likelihood-based generative models, particularly diffusion and autoregressive models, have achieved remarkable fidelity in visual generation, the maximum likelihood estimation (MLE) objective, which minimizes the forward KL divergence, inherently suffers from a mode-covering tendency that limits the generation quality under limited model capacity. In this work, we propose Direct Discriminative Optimization (DDO) as a unified framework that integrates likelihood-based generative training and GAN-type discrimination to bypass this fundamental constraint by exploiting reverse KL and self-generated negative signals. Our key insight is to parameterize a discriminator implicitly using the likelihood ratio between a learnable target model and a fixed reference model, drawing parallels with the philosophy of Direct Preference Optimization (DPO). Unlike GANs, this parameterization eliminates the need for joint training of generator and discriminator networks, allowing for direct, efficient, and effective finetuning of a well-trained model to its full potential beyond the limits of MLE. DDO can be performed iteratively in a self-play manner for progressive model refinement, with each round requiring less than 1% of pretraining epochs. Our experiments demonstrate the effectiveness of DDO by significantly advancing the previous SOTA diffusion model EDM, reducing FID scores from 1.79/1.58/1.96 to new records of 1.30/0.97/1.26 on CIFAR-10/ImageNet-64/ImageNet 512x512 datasets without any guidance mechanisms, and by consistently improving both guidance-free and CFG-enhanced FIDs of visual autoregressive models on ImageNet 256x256.

arXiv:2503.00811공식 코드 · Papers with Code

Evaluating and Predicting Distorted Human Body Parts for Generated Images

Recent advancements in text-to-image (T2I) models enable high-quality image synthesis, yet generating anatomically accurate human figures remains challenging. AI-generated images frequently exhibit distortions such as proliferated limbs, missing fingers, deformed extremities, or fused body parts. Existing evaluation metrics like Inception Score (IS) and Fr\'echet Inception Distance (FID) lack the granularity to detect these distortions, while human preference-based metrics focus on abstract quality assessments rather than anatomical fidelity. To address this gap, we establish the first standards for identifying human body distortions in AI-generated images and introduce Distortion-5K, a comprehensive dataset comprising 4,700 annotated images of normal and malformed human figures across diverse styles and distortion types. Based on this dataset, we propose ViT-HD, a Vision Transformer-based model tailored for detecting human body distortions in AI-generated images, which outperforms state-of-the-art segmentation models and visual language models, achieving an F1 score of 0.899 and IoU of 0.831 on distortion localization. Additionally, we construct the Human Distortion Benchmark with 500 human-centric prompts to evaluate four popular T2I models using trained ViT-HD, revealing that nearly 50\% of generated images contain distortions. This work pioneers a systematic approach to evaluating anatomical accuracy in AI-generated humans, offering tools to advance the fidelity of T2I models and their real-world applicability. The Distortion-5K dataset, trained ViT-HD will soon be released in our GitHub repository: \href{https://github.com/TheRoadQaQ/Predicting-Distortion}{https://github.com/TheRoadQaQ/Predicting-Distortion}.

arXiv:2503.00665

Development of an Unpaired Deep Neural Network for Synthesizing X-ray Fluoroscopic Images from Digitally Reconstructed Tomography in Image Guided Radiotherapy

Purpose The purpose of this study was to develop and evaluate a deep neural network (DNN) capable of generating flat-panel detector (FPD) images from digitally reconstructed radiography (DRR) images in lung cancer treatment, with the aim of improving clinical workflows in image-guided radiotherapy. Methods A modified CycleGAN architecture was trained on paired DRR-FPD image data obtained from patients with lung tumors. The training dataset consisted of over 400 DRR-FPD image pairs, and the final model was evaluated on an independent set of 100 FPD images. Mean absolute error (MAE), peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and Kernel Inception Distance (KID) were used to quantify the similarity between synthetic and ground-truth FPD images. Computation time for generating synthetic images was also measured. Results Despite some positional mismatches in the DRR-FPD pairs, the synthetic FPD images closely resembled the ground-truth FPD images. The proposed DNN achieved notable improvements over both input DRR images and a U-Net-based method in terms of MAE, PSNR, SSIM, and KID. The average image generation time was on the order of milliseconds per image, indicating its potential for real-time application. Qualitative evaluations showed that the DNN successfully reproduced image noise patterns akin to real FPD images, reducing the need for manual noise adjustments. Conclusions The proposed DNN effectively converted DRR images into realistic FPD images for thoracic cases, offering a fast and practical method that could streamline patient setup verification and enhance overall clinical workflow. Future work should validate the model across different imaging systems and address remaining challenges in marker visualization, thereby fostering broader clinical adoption.

arXiv:2503.00266공식 코드 · Papers with Code

Flow Matching for Medical Image Synthesis: Bridging the Gap Between Speed and Quality

Deep learning models have emerged as a powerful tool for various medical applications. However, their success depends on large, high-quality datasets that are challenging to obtain due to privacy concerns and costly annotation. Generative models, such as diffusion models, offer a potential solution by synthesizing medical images, but their practical adoption is hindered by long inference times. In this paper, we propose the use of an optimal transport flow matching approach to accelerate image generation. By introducing a straighter mapping between the source and target distribution, our method significantly reduces inference time while preserving and further enhancing the quality of the outputs. Furthermore, this approach is highly adaptable, supporting various medical imaging modalities, conditioning mechanisms (such as class labels and masks), and different spatial dimensions, including 2D and 3D. Beyond image generation, it can also be applied to related tasks such as image enhancement. Our results demonstrate the efficiency and versatility of this framework, making it a promising advancement for medical imaging applications. Code with checkpoints and a synthetic dataset (beneficial for classification and segmentation) is now available on: https://github.com/milad1378yz/MOTFM.

arXiv:2503.01019

MedUnifier: Unifying Vision-and-Language Pre-training on Medical Data with Vision Generation Task using Discrete Visual Representations

Despite significant progress in Vision-Language Pre-training (VLP), current approaches predominantly emphasize feature extraction and cross-modal comprehension, with limited attention to generating or transforming visual content. This gap hinders the model's ability to synthesize coherent and novel visual representations from textual prompts, thereby reducing the effectiveness of multi-modal learning. In this work, we propose MedUnifier, a unified VLP framework tailored for medical data. MedUnifier seamlessly integrates text-grounded image generation capabilities with multi-modal learning strategies, including image-text contrastive alignment, image-text matching and image-grounded text generation. Unlike traditional methods that reply on continuous visual representations, our approach employs visual vector quantization, which not only facilitates a more cohesive learning strategy for cross-modal understanding but also enhances multi-modal generation quality by effectively leveraging discrete representations. Our framework's effectiveness is evidenced by the experiments on established benchmarks, including uni-modal tasks (supervised fine-tuning), cross-modal tasks (image-text retrieval and zero-shot image classification), and multi-modal tasks (medical report generation, image synthesis), where it achieves state-of-the-art performance across various tasks. MedUnifier also offers a highly adaptable tool for a wide range of language and vision tasks in healthcare, marking advancement toward the development of a generalizable AI model for medical applications.

arXiv:2503.00945

Cross Modality Medical Image Synthesis for Improving Liver Segmentation

Deep learning-based computer-aided diagnosis (CAD) of medical images requires large datasets. However, the lack of large publicly available labeled datasets limits the development of deep learning-based CAD systems. Generative Adversarial Networks (GANs), in particular, CycleGAN, can be used to generate new cross-domain images without paired training data. However, most CycleGAN-based synthesis methods lack the potential to overcome alignment and asymmetry between the input and generated data. We propose a two-stage technique for the synthesis of abdominal MRI using cross-modality translation of abdominal CT. We show that the synthetic data can help improve the performance of the liver segmentation network. We increase the number of abdominal MRI images through cross-modality image transformation of unpaired CT images using a CycleGAN inspired deformation invariant network called EssNet. Subsequently, we combine the synthetic MRI images with the original MRI images and use them to improve the accuracy of the U-Net on a liver segmentation task. We train the U-Net on real MRI images and then on real and synthetic MRI images. Consequently, by comparing both scenarios, we achieve an improvement in the performance of U-Net. In summary, the improvement achieved in the Intersection over Union (IoU) is 1.17%. The results show potential to address the data scarcity challenge in medical imaging.

arXiv:2502.20904

DiffBrush:Just Painting the Art by Your Hands

The rapid development of image generation and editing algorithms in recent years has enabled ordinary user to produce realistic images. However, the current AI painting ecosystem predominantly relies on text-driven diffusion models (T2I), which pose challenges in accurately capturing user requirements. Furthermore, achieving compatibility with other modalities incurs substantial training costs. To this end, we introduce DiffBrush, which is compatible with T2I models and allows users to draw and edit images. By manipulating and adapting the internal representation of the diffusion model, DiffBrush guides the model-generated images to converge towards the user's hand-drawn sketches for user's specific needs without additional training. DiffBrush achieves control over the color, semantic, and instance of objects in images by continuously guiding the latent and instance-level attention map during the denoising process of the diffusion model. Besides, we propose a latent regeneration, which refines the randomly sampled noise in the diffusion model, obtaining a better image generation layout. Finally, users only need to roughly draw the mask of the instance (acceptable colors) on the canvas, DiffBrush can naturally generate the corresponding instance at the corresponding location.

arXiv:2502.20650공식 코드 · Papers with Code

Gungnir: Exploiting Stylistic Features in Images for Backdoor Attacks on Diffusion Models

In recent years, Diffusion Models (DMs) have demonstrated significant advances in the field of image generation. However, according to current research, DMs are vulnerable to backdoor attacks, which allow attackers to control the model's output by inputting data containing covert triggers, such as a specific visual patch or phrase. Existing defense strategies are well equipped to thwart such attacks through backdoor detection and trigger inversion because previous attack methods are constrained by limited input spaces and low-dimensional triggers. For example, visual triggers are easily observed by defenders, text-based or attention-based triggers are more susceptible to neural network detection. To explore more possibilities of backdoor attack in DMs, we propose Gungnir, a novel method that enables attackers to activate the backdoor in DMs through style triggers within input images. Our approach proposes using stylistic features as triggers for the first time and implements backdoor attacks successfully in image-to-image tasks by introducing Reconstructing-Adversarial Noise (RAN) and Short-Term Timesteps-Retention (STTR). Our technique generates trigger-embedded images that are perceptually indistinguishable from clean images, thus bypassing both manual inspection and automated detection neural networks. Experiments demonstrate that Gungnir can easily bypass existing defense methods. Among existing DM defense frameworks, our approach achieves a 0 backdoor detection rate (BDR). Our codes are available at https://github.com/paoche11/Gungnir.

arXiv:2502.20623

SafeText: Safe Text-to-image Models via Aligning the Text Encoder

Text-to-image models can generate harmful images when presented with unsafe prompts, posing significant safety and societal risks. Alignment methods aim to modify these models to ensure they generate only non-harmful images, even when exposed to unsafe prompts. A typical text-to-image model comprises two main components: 1) a text encoder and 2) a diffusion module. Existing alignment methods mainly focus on modifying the diffusion module to prevent harmful image generation. However, this often significantly impacts the model's behavior for safe prompts, causing substantial quality degradation of generated images. In this work, we propose SafeText, a novel alignment method that fine-tunes the text encoder rather than the diffusion module. By adjusting the text encoder, SafeText significantly alters the embedding vectors for unsafe prompts, while minimally affecting those for safe prompts. As a result, the diffusion module generates non-harmful images for unsafe prompts while preserving the quality of images for safe prompts. We evaluate SafeText on multiple datasets of safe and unsafe prompts, including those generated through jailbreak attacks. Our results show that SafeText effectively prevents harmful image generation with minor impact on the images for safe prompts, and SafeText outperforms six existing alignment methods. We will publish our code and data after paper acceptance.

arXiv:2502.20388공식 코드 · Papers with Code

Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation

Autoregressive (AR) modeling, known for its next-token prediction paradigm, underpins state-of-the-art language and visual generative models. Traditionally, a ``token'' is treated as the smallest prediction unit, often a discrete symbol in language or a quantized patch in vision. However, the optimal token definition for 2D image structures remains an open question. Moreover, AR models suffer from exposure bias, where teacher forcing during training leads to error accumulation at inference. In this paper, we propose xAR, a generalized AR framework that extends the notion of a token to an entity X, which can represent an individual patch token, a cell (a $k\times k$ grouping of neighboring patches), a subsample (a non-local grouping of distant patches), a scale (coarse-to-fine resolution), or even a whole image. Additionally, we reformulate discrete token classification as \textbf{continuous entity regression}, leveraging flow-matching methods at each AR step. This approach conditions training on noisy entities instead of ground truth tokens, leading to Noisy Context Learning, which effectively alleviates exposure bias. As a result, xAR offers two key advantages: (1) it enables flexible prediction units that capture different contextual granularity and spatial structures, and (2) it mitigates exposure bias by avoiding reliance on teacher forcing. On ImageNet-256 generation benchmark, our base model, xAR-B (172M), outperforms DiT-XL/SiT-XL (675M) while achieving 20$\times$ faster inference. Meanwhile, xAR-H sets a new state-of-the-art with an FID of 1.24, running 2.2$\times$ faster than the previous best-performing model without relying on vision foundation modules (\eg, DINOv2) or advanced guidance interval sampling.

arXiv:2502.20313공식 코드 · Papers with Code

FlexVAR: Flexible Visual Autoregressive Modeling without Residual Prediction

This work challenges the residual prediction paradigm in visual autoregressive modeling and presents FlexVAR, a new Flexible Visual AutoRegressive image generation paradigm. FlexVAR facilitates autoregressive learning with ground-truth prediction, enabling each step to independently produce plausible images. This simple, intuitive approach swiftly learns visual distributions and makes the generation process more flexible and adaptable. Trained solely on low-resolution images ($\leq$ 256px), FlexVAR can: (1) Generate images of various resolutions and aspect ratios, even exceeding the resolution of the training images. (2) Support various image-to-image tasks, including image refinement, in/out-painting, and image expansion. (3) Adapt to various autoregressive steps, allowing for faster inference with fewer steps or enhancing image quality with more steps. Our 1.0B model outperforms its VAR counterpart on the ImageNet 256$\times$256 benchmark. Moreover, when zero-shot transfer the image generation process with 13 steps, the performance further improves to 2.08 FID, outperforming state-of-the-art autoregressive models AiM/VAR by 0.25/0.28 FID and popular diffusion models LDM/DiT by 1.52/0.19 FID, respectively. When transferring our 1.0B model to the ImageNet 512$\times$512 benchmark in a zero-shot manner, FlexVAR achieves competitive results compared to the VAR 2.3B model, which is a fully supervised model trained at 512$\times$512 resolution.

arXiv:2502.19828

Analyzing CLIP's Performance Limitations in Multi-Object Scenarios: A Controlled High-Resolution Study

Contrastive Language-Image Pre-training (CLIP) models have demonstrated remarkable performance in zero-shot classification tasks, yet their efficacy in handling complex multi-object scenarios remains challenging. This study presents a comprehensive analysis of CLIP's performance limitations in multi-object contexts through controlled experiments. We introduce two custom datasets, SimCO and CompCO, to evaluate CLIP's image and text encoders in various multi-object configurations. Our findings reveal significant biases in both encoders: the image encoder favors larger objects, while the text encoder prioritizes objects mentioned first in descriptions. We hypothesize these biases originate from CLIP's training process and provide evidence through analyses of the COCO dataset and CLIP's training progression. Additionally, we extend our investigation to Stable Diffusion models, revealing that biases in the CLIP text encoder significantly impact text-to-image generation tasks. Our experiments demonstrate how these biases affect CLIP's performance in image-caption matching and generation tasks, particularly when manipulating object sizes and their order in captions. This work contributes valuable insights into CLIP's behavior in complex visual environments and highlights areas for improvement in future vision-language models.

arXiv:2502.19754공식 코드 · Papers with Code

Finding Local Diffusion Schrödinger Bridge using Kolmogorov-Arnold Network

In image generation, Schr\"odinger Bridge (SB)-based methods theoretically enhance the efficiency and quality compared to the diffusion models by finding the least costly path between two distributions. However, they are computationally expensive and time-consuming when applied to complex image data. The reason is that they focus on fitting globally optimal paths in high-dimensional spaces, directly generating images as next step on the path using complex networks through self-supervised training, which typically results in a gap with the global optimum. Meanwhile, most diffusion models are in the same path subspace generated by weights $f_A(t)$ and $f_B(t)$, as they follow the paradigm ($x_t = f_A(t)x_{Img} + f_B(t)\epsilon$). To address the limitations of SB-based methods, this paper proposes for the first time to find local Diffusion Schr\"odinger Bridges (LDSB) in the diffusion path subspace, which strengthens the connection between the SB problem and diffusion models. Specifically, our method optimizes the diffusion paths using Kolmogorov-Arnold Network (KAN), which has the advantage of resistance to forgetting and continuous output. The experiment shows that our LDSB significantly improves the quality and efficiency of image generation using the same pre-trained denoising network and the KAN for optimising is only less than 0.1MB. The FID metric is reduced by \textbf{more than 15\%}, especially with a reduction of 48.50\% when NFE of DDIM is $5$ for the CelebA dataset. Code is available at https://github.com/Qiu-XY/LDSB.

arXiv:2502.19623

3D Nephrographic Image Synthesis in CT Urography with the Diffusion Model and Swin Transformer

Purpose: This study aims to develop and validate a method for synthesizing 3D nephrographic phase images in CT urography (CTU) examinations using a diffusion model integrated with a Swin Transformer-based deep learning approach. Materials and Methods: This retrospective study was approved by the local Institutional Review Board. A dataset comprising 327 patients who underwent three-phase CTU (mean $\pm$ SD age, 63 $\pm$ 15 years; 174 males, 153 females) was curated for deep learning model development. The three phases for each patient were aligned with an affine registration algorithm. A custom deep learning model coined dsSNICT (diffusion model with a Swin transformer for synthetic nephrographic phase images in CT) was developed and implemented to synthesize the nephrographic images. Performance was assessed using Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), Mean Absolute Error (MAE), and Fr\'{e}chet Video Distance (FVD). Qualitative evaluation by two fellowship-trained abdominal radiologists was performed. Results: The synthetic nephrographic images generated by our proposed approach achieved high PSNR (26.3 $\pm$ 4.4 dB), SSIM (0.84 $\pm$ 0.069), MAE (12.74 $\pm$ 5.22 HU), and FVD (1323). Two radiologists provided average scores of 3.5 for real images and 3.4 for synthetic images (P-value = 0.5) on a Likert scale of 1-5, indicating that our synthetic images closely resemble real images. Conclusion: The proposed approach effectively synthesizes high-quality 3D nephrographic phase images. This model can be used to reduce radiation dose in CTU by 33.3\% without compromising image quality, which thereby enhances the safety and diagnostic utility of CT urography.

arXiv:2502.20172공식 코드 · Papers with Code

Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control Is Easier Than You Think

The field of advanced text-to-image generation is witnessing the emergence of unified frameworks that integrate powerful text encoders, such as CLIP and T5, with Diffusion Transformer backbones. Although there have been efforts to control output images with additional conditions, like canny and depth map, a comprehensive framework for arbitrary text-image interleaved control is still lacking. This gap is especially evident when attempting to merge concepts or visual elements from multiple images in the generation process. To mitigate the gap, we conducted preliminary experiments showing that large multimodal models (LMMs) offer an effective shared representation space, where image and text can be well-aligned to serve as a condition for external diffusion models. Based on this discovery, we propose Dream Engine, an efficient and unified framework designed for arbitrary text-image interleaved control in image generation models. Building on powerful text-to-image models like SD3.5, we replace the original text-only encoders by incorporating versatile multimodal information encoders such as QwenVL. Our approach utilizes a two-stage training paradigm, consisting of joint text-image alignment and multimodal interleaved instruction tuning. Our experiments demonstrate that this training method is effective, achieving a 0.69 overall score on the GenEval benchmark, and matching the performance of state-of-the-art text-to-image models like SD3.5 and FLUX.