As scaling laws in generative AI push performance, they simultaneously concentrate the development of these models among actors with large computational resources. With a focus on text-to-image (T2I) generative models, we aim to unlock this bottleneck by demonstrating very low-cost training of large-scale T2I diffusion transformer models. As the computational cost of transformers increases with the number of patches in each image, we propose randomly masking up to 75% of the image patches during training. We propose a deferred masking strategy that preprocesses all patches using a patch-mixer before masking, thus significantly reducing the performance degradation with masking, making it superior to model downscaling in reducing computational cost. We also incorporate the latest improvements in transformer architecture, such as the use of mixture-of-experts layers, to improve performance and further identify the critical benefit of using synthetic images in micro-budget training. Finally, using only 37M publicly available real and synthetic images, we train a 1.16 billion parameter sparse transformer with only 1,890 USD economical cost and achieve a 12.7 FID in zero-shot generation on the COCO dataset. Notably, our model achieves competitive performance across both automated and human-centric evaluations, as well as high-quality generations, while incurring 118xlower costs than Stable Diffusion models and 14xlower costs than the current state-of-the-art approach, which costs \28,400. We also further investigate the influence of synthetic images on performance and demonstrate that micro-budget training on only synthetic images is sufficient for achieving high-quality data generation. Our end-to-end training pipeline and model checkpoints are available at https://github.com/SonyResearch/micro_diffusion.
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
Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregression
PDF ↗Since 2023, Vector Quantization (VQ)-based discrete generation methods have rapidly dominated human motion generation, primarily surpassing diffusion-based continuous generation methods in standard performance metrics. However, VQ-based methods have inherent limitations. Representing continuous motion data as limited discrete tokens leads to inevitable information loss, reduces the diversity of generated motions, and restricts their ability to function effectively as motion priors or generation guidance. In contrast, the continuous space generation nature of diffusion-based methods makes them well-suited to address these limitations and with even potential for model scalability. In this work, we systematically investigate why current VQ-based methods perform well and explore the limitations of existing diffusion-based methods from the perspective of motion data representation and distribution. Drawing on these insights, we preserve the inherent strengths of a diffusion-based human motion generation model and gradually optimize it with inspiration from VQ-based approaches. Our approach introduces a human motion diffusion model enabled to perform masked autoregression, optimized with a reformed data representation and distribution. Additionally, we propose a more robust evaluation method to assess different approaches. Extensive experiments on various datasets demonstrate our method outperforms previous methods and achieves state-of-the-art performances.
FreeUV: Ground-Truth-Free Realistic Facial UV Texture Recovery via Cross-Assembly Inference Strategy
PDF ↗Recovering high-quality 3D facial textures from single-view 2D images is a challenging task, especially under constraints of limited data and complex facial details such as makeup, wrinkles, and occlusions. In this paper, we introduce FreeUV, a novel ground-truth-free UV texture recovery framework that eliminates the need for annotated or synthetic UV data. FreeUV leverages pre-trained stable diffusion model alongside a Cross-Assembly inference strategy to fulfill this objective. In FreeUV, separate networks are trained independently to focus on realistic appearance and structural consistency, and these networks are combined during inference to generate coherent textures. Our approach accurately captures intricate facial features and demonstrates robust performance across diverse poses and occlusions. Extensive experiments validate FreeUV's effectiveness, with results surpassing state-of-the-art methods in both quantitative and qualitative metrics. Additionally, FreeUV enables new applications, including local editing, facial feature interpolation, and multi-view texture recovery. By reducing data requirements, FreeUV offers a scalable solution for generating high-fidelity 3D facial textures suitable for real-world scenarios.
Advancing Generalizable Tumor Segmentation with Anomaly-Aware Open-Vocabulary Attention Maps and Frozen Foundation Diffusion Models
PDF ↗We explore Generalizable Tumor Segmentation, aiming to train a single model for zero-shot tumor segmentation across diverse anatomical regions. Existing methods face limitations related to segmentation quality, scalability, and the range of applicable imaging modalities. In this paper, we uncover the potential of the internal representations within frozen medical foundation diffusion models as highly efficient zero-shot learners for tumor segmentation by introducing a novel framework named DiffuGTS. DiffuGTS creates anomaly-aware open-vocabulary attention maps based on text prompts to enable generalizable anomaly segmentation without being restricted by a predefined training category list. To further improve and refine anomaly segmentation masks, DiffuGTS leverages the diffusion model, transforming pathological regions into high-quality pseudo-healthy counterparts through latent space inpainting, and applies a novel pixel-level and feature-level residual learning approach, resulting in segmentation masks with significantly enhanced quality and generalization. Comprehensive experiments on four datasets and seven tumor categories demonstrate the superior performance of our method, surpassing current state-of-the-art models across multiple zero-shot settings. Codes are available at https://github.com/Yankai96/DiffuGTS.
In this work, we introduce Prometheus, a 3D-aware latent diffusion model for text-to-3D generation at both object and scene levels in seconds. We formulate 3D scene generation as multi-view, feed-forward, pixel-aligned 3D Gaussian generation within the latent diffusion paradigm. To ensure generalizability, we build our model upon pre-trained text-to-image generation model with only minimal adjustments and further train it using a large number of images from both single-view and multi-view datasets. Furthermore, we introduce an RGB-D latent space into 3D Gaussian generation to disentangle appearance and geometry information, enabling efficient feed-forward generation of 3D Gaussians with better fidelity and geometry. Extensive experimental results demonstrate the effectiveness of our method in both feed-forward 3D Gaussian reconstruction and text-to-3D generation.
MotionStone: Decoupled Motion Intensity Modulation with Diffusion Transformer for Image-to-Video Generation
PDF ↗The image-to-video (I2V) generation is conditioned on the static image, which has been enhanced recently by the motion intensity as an additional control signal. These motion-aware models are appealing to generate diverse motion patterns, yet there lacks a reliable motion estimator for training such models on large-scale video set in the wild. Traditional metrics, e.g., SSIM or optical flow, are hard to generalize to arbitrary videos, while, it is very tough for human annotators to label the abstract motion intensity neither. Furthermore, the motion intensity shall reveal both local object motion and global camera movement, which has not been studied before. This paper addresses the challenge with a new motion estimator, capable of measuring the decoupled motion intensities of objects and cameras in video. We leverage the contrastive learning on randomly paired videos and distinguish the video with greater motion intensity. Such a paradigm is friendly for annotation and easy to scale up to achieve stable performance on motion estimation. We then present a new I2V model, named MotionStone, developed with the decoupled motion estimator. Experimental results demonstrate the stability of the proposed motion estimator and the state-of-the-art performance of MotionStone on I2V generation. These advantages warrant the decoupled motion estimator to serve as a general plug-in enhancer for both data processing and video generation training.
Can objects that are not visible in an image---but are in the vicinity of the camera---be detected? This study introduces the novel tasks of 2D, 2.5D and 3D unobserved object detection for predicting the location of nearby objects that are occluded or lie outside the image frame. We adapt several state-of-the-art pre-trained generative models to address this task, including 2D and 3D diffusion models and vision-language models, and show that they can be used to infer the presence of objects that are not directly observed. To benchmark this task, we propose a suite of metrics that capture different aspects of performance. Our empirical evaluation on indoor scenes from the RealEstate10k and NYU Depth v2 datasets demonstrate results that motivate the use of generative models for the unobserved object detection task.
Training Data Provenance Verification: Did Your Model Use Synthetic Data from My Generative Model for Training?
PDF ↗High-quality open-source text-to-image models have lowered the threshold for obtaining photorealistic images significantly, but also face potential risks of misuse. Specifically, suspects may use synthetic data generated by these generative models to train models for specific tasks without permission, when lacking real data resources especially. Protecting these generative models is crucial for the well-being of their owners. In this work, we propose the first method to this important yet unresolved issue, called Training data Provenance Verification (TrainProVe). The rationale behind TrainProVe is grounded in the principle of generalization error bound, which suggests that, for two models with the same task, if the distance between their training data distributions is smaller, their generalization ability will be closer. We validate the efficacy of TrainProVe across four text-to-image models (Stable Diffusion v1.4, latent consistency model, PixArt-\alpha, and Stable Cascade). The results show that TrainProVe achieves a verification accuracy of over 99% in determining the provenance of suspicious model training data, surpassing all previous methods. Code is available at https://github.com/xieyc99/TrainProVe.
Recently, diffusion models have achieved significant advances in vision, text, and robotics. However, they still face slow generation speeds due to sequential denoising processes. To address this, a parallel sampling method based on Picard iteration was introduced, effectively reducing sequential steps while ensuring exact convergence to the original output. Nonetheless, Picard iteration does not guarantee faster convergence, which can still result in slow generation in practice. In this work, we propose a new parallelization scheme, the Picard Consistency Model (PCM), which significantly reduces the number of generation steps in Picard iteration. Inspired by the consistency model, PCM is directly trained to predict the fixed-point solution, or the final output, at any stage of the convergence trajectory. Additionally, we introduce a new concept called model switching, which addresses PCM's limitations and ensures exact convergence. Extensive experiments demonstrate that PCM achieves up to a 2.71x speedup over sequential sampling and a 1.77x speedup over Picard iteration across various tasks, including image generation and robotic control.
Diffusion models achieved unprecedented fidelity and diversity for synthesizing image, video, 3D assets, etc. However, subject mixing is an unresolved issue for diffusion-based image synthesis, particularly for synthesizing multiple similar-looking subjects. We propose Self-Cross Diffusion Guidance to penalize the overlap between cross-attention maps and the aggregated self-attention map. Compared to previous methods based on self-attention or cross-attention alone, our guidance is more effective in eliminating subject mixing. What's more, our guidance addresses subject mixing for all relevant patches beyond the most discriminant one, e.g., the beak of a bird. For each subject, we aggregate self-attention maps of patches with higher cross-attention values. Thus, the aggregated self-attention map forms a region that the whole subject attends to. Our training-free method boosts the performance of both Unet-based and Transformer-based diffusion models such as the Stable Diffusion series. We also release a similar subjects dataset (SSD), a challenging benchmark, and utilize GPT-4o for automatic and reliable evaluation. Extensive qualitative and quantitative results demonstrate the effectiveness of our self-cross diffusion guidance.
Despite the typical inversion-then-editing paradigm using text-to-image (T2I) models has demonstrated promising results, directly extending it to text-to-video (T2V) models still suffers severe artifacts such as color flickering and content distortion. Consequently, current video editing methods primarily rely on T2I models, which inherently lack temporal-coherence generative ability, often resulting in inferior editing results. In this paper, we attribute the failure of the typical editing paradigm to: 1) Tightly Spatial-temporal Coupling. The vanilla pivotal-based inversion strategy struggles to disentangle spatial-temporal information in the video diffusion model; 2) Complicated Spatial-temporal Layout. The vanilla cross-attention control strategy is deficient in preserving the unedited content. To address these limitations, we propose a spatial-temporal decoupled guidance (STDG) and multi-frame null-text optimization strategy to provide pivotal temporal cues for more precise pivotal inversion. Furthermore, we introduce a self-attention control strategy to maintain higher fidelity for precise partial content editing. Experimental results demonstrate that our method (termed VideoDirector) effectively harnesses the powerful temporal generation capabilities of T2V models, producing edited videos with state-of-the-art performance in accuracy, motion smoothness, realism, and fidelity to unedited content.
Recent 3D face reconstruction methods have made remarkable advancements, yet achieving high-quality facial reflectance from monocular input remains challenging. Existing methods rely on the light-stage captured data to learn facial reflectance models. However, limited subject diversity in these datasets poses challenges in achieving good generalization and broad applicability. This motivates us to explore whether the extensive priors captured in recent generative diffusion models (e.g., Stable Diffusion) can enable more generalizable facial reflectance estimation as these models have been pre-trained on large-scale internet image collections containing rich visual patterns. In this paper, we introduce the use of Stable Diffusion as a prior for facial reflectance estimation, achieving robust results with minimal captured data for fine-tuning. We present S^3-Face, a comprehensive framework capable of producing SSS-compliant skin reflectance from in-the-wild images. Our method adopts a two-stage training approach: in the first stage, DSN-Net is trained to predict diffuse albedo, specular albedo, and normal maps from in-the-wild images using a novel joint reflectance attention module. In the second stage, HM-Net is trained to generate hemoglobin and melanin maps based on the diffuse albedo predicted in the first stage, yielding SSS-compliant and detailed reflectance maps. Extensive experiments demonstrate that our method achieves strong generalization and produces high-fidelity, SSS-compliant facial reflectance reconstructions.
Medical Visual Question Answering (Med-VQA) systems benefit the interpretation of medical images containing critical clinical information. However, the challenge of noisy labels and limited high-quality datasets remains underexplored. To address this, we establish the first benchmark for noisy labels in Med-VQA by simulating human mislabeling with semantically designed noise types. More importantly, we introduce the DiN framework, which leverages a diffusion model to handle noisy labels in Med-VQA. Unlike the dominant classification-based VQA approaches that directly predict answers, our Answer Diffuser (AD) module employs a coarse-to-fine process, refining answer candidates with a diffusion model for improved accuracy. The Answer Condition Generator (ACG) further enhances this process by generating task-specific conditional information via integrating answer embeddings with fused image-question features. To address label noise, our Noisy Label Refinement(NLR) module introduces a robust loss function and dynamic answer adjustment to further boost the performance of the AD module. Our DiN framework consistently outperforms existing methods across multiple benchmarks with varying noise levels.
The rapid advancement of generative models has significantly improved the quality of generated images. Meanwhile, it challenges information authenticity and credibility. Current generated image detection methods based on large-scale pre-trained multimodal models have achieved impressive results. Although these models provide abundant features, the authentication task-related features are often submerged. Consequently, those authentication task-irrelated features cause models to learn superficial biases, thereby harming their generalization performance across different model genera (e.g., GANs and Diffusion Models). To this end, we proposed VIB-Net, which uses Variational Information Bottlenecks to enforce authentication task-related feature learning. We tested and analyzed the proposed method and existing methods on samples generated by 17 different generative models. Compared to SOTA methods, VIB-Net achieved a 5.55% improvement in mAP and a 9.33% increase in accuracy. Notably, in generalization tests on unseen generative models from different series, VIB-Net improved mAP by 12.48% and accuracy by 23.59% over SOTA methods. The code is available at https://github.com/oceanzhf/VIBAIGCDetect.
Text-driven motion generation has advanced significantly with the rise of denoising diffusion models. However, previous methods often oversimplify representations for the skeletal joints, temporal frames, and textual words, limiting their ability to fully capture the information within each modality and their interactions. Moreover, when using pre-trained models for downstream tasks, such as editing, they typically require additional efforts, including manual interventions, optimization, or fine-tuning. In this paper, we introduce a skeleton-aware latent diffusion (SALAD), a model that explicitly captures the intricate inter-relationships between joints, frames, and words. Furthermore, by leveraging cross-attention maps produced during the generation process, we enable the attention-based zero-shot text-driven motion editing using a pre-trained SALAD model, requiring no additional user input beyond text prompts. Our approach significantly outperforms previous methods in terms of text-motion alignment without compromising generation quality, and demonstrates practical versatility by providing diverse editing capabilities beyond generation. Code is available at project page.
Real-world image super-resolution (Real-ISR) aims to reconstruct high-resolution images from low-resolution inputs degraded by complex, unknown processes. While many Stable Diffusion (SD)-based Real-ISR methods have achieved remarkable success, their slow, multi-step inference hinders practical deployment. Recent SD-based one-step networks like OSEDiff and S3Diff alleviate this issue but still incur high computational costs due to their reliance on large pretrained SD models. This paper proposes a novel Real-ISR method, AdcSR, by distilling the one-step diffusion network OSEDiff into a streamlined diffusion-GAN model under our Adversarial Diffusion Compression (ADC) framework. We meticulously examine the modules of OSEDiff, categorizing them into two types: (1) Removable (VAE encoder, prompt extractor, text encoder, etc.) and (2) Prunable (denoising UNet and VAE decoder). Since direct removal and pruning can degrade the model's generation capability, we pretrain our pruned VAE decoder to restore its ability to decode images and employ adversarial distillation to compensate for performance loss. This ADC-based diffusion-GAN hybrid design effectively reduces complexity by 73% in inference time, 78% in computation, and 74% in parameters, while preserving the model's generation capability. Experiments manifest that our proposed AdcSR achieves competitive recovery quality on both synthetic and real-world datasets, offering up to 9.3x speedup over previous one-step diffusion-based methods. Code and models are available at https://github.com/Guaishou74851/AdcSR.
Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference Optimization
PDF ↗Generating visually appealing images is fundamental to modern text-to-image generation models. A potential solution to better aesthetics is direct preference optimization (DPO), which has been applied to diffusion models to improve general image quality including prompt alignment and aesthetics. Popular DPO methods propagate preference labels from clean image pairs to all the intermediate steps along the two generation trajectories. However, preference labels provided in existing datasets are blended with layout and aesthetic opinions, which would disagree with aesthetic preference. Even if aesthetic labels were provided (at substantial cost), it would be hard for the two-trajectory methods to capture nuanced visual differences at different steps. To improve aesthetics economically, this paper uses existing generic preference data and introduces step-by-step preference optimization (SPO) that discards the propagation strategy and allows fine-grained image details to be assessed. Specifically, at each denoising step, we 1) sample a pool of candidates by denoising from a shared noise latent, 2) use a step-aware preference model to find a suitable win-lose pair to supervise the diffusion model, and 3) randomly select one from the pool to initialize the next denoising step. This strategy ensures that diffusion models focus on the subtle, fine-grained visual differences instead of layout aspect. We find that aesthetics can be significantly enhanced by accumulating these improved minor differences. When fine-tuning Stable Diffusion v1.5 and SDXL, SPO yields significant improvements in aesthetics compared with existing DPO methods while not sacrificing image-text alignment compared with vanilla models. Moreover, SPO converges much faster than DPO methods due to the use of more correct preference labels provided by the step-aware preference model. Code and models are available at https://github.com/RockeyCoss/SPO.
Styled Handwritten Text Generation (HTG) has recently received attention from the computer vision and document analysis communities, which have developed several solutions, either GAN- or diffusion-based, that achieved promising results. Nonetheless, these strategies fail to generalize to novel styles and have technical constraints, particularly in terms of maximum output length and training efficiency. To overcome these limitations, in this work, we propose a novel framework for text-image generation, dubbed Emuru. Our approach leverages a powerful text-image representation model (a variational autoencoder) combined with an autoregressive Transformer. Our approach enables the generation of styled text images conditioned on textual content and style examples, such as specific fonts or handwriting styles. We train our model solely on a diverse, synthetic dataset of English text rendered in over 100,000 typewritten and calligraphy fonts, which gives it the capability to reproduce unseen styles (both fonts and users' handwriting) in zero-shot. To the best of our knowledge, Emuru is the first autoregressive model for HTG, and the first designed specifically for generalization to novel styles. Moreover, our model generates images without background artifacts, which are easier to use for downstream applications. Extensive evaluation on both typewritten and handwritten, any-length text image generation scenarios demonstrates the effectiveness of our approach.
This paper presents the Large Vision Diffusion Transformer (LaVin-DiT), a scalable and unified foundation model designed to tackle over 20 computer vision tasks in a generative framework. Unlike existing large vision models directly adapted from natural language processing architectures, which rely on less efficient autoregressive techniques and disrupt spatial relationships essential for vision data, LaVin-DiT introduces key innovations to optimize generative performance for vision tasks. First, to address the high dimensionality of visual data, we incorporate a spatial-temporal variational autoencoder that encodes data into a continuous latent space. Second, for generative modeling, we develop a joint diffusion transformer that progressively produces vision outputs. Third, for unified multi-task training, in-context learning is implemented. Input-target pairs serve as task context, which guides the diffusion transformer to align outputs with specific tasks within the latent space. During inference, a task-specific context set and test data as queries allow LaVin-DiT to generalize across tasks without fine-tuning. Trained on extensive vision datasets, the model is scaled from 0.1B to 3.4B parameters, demonstrating substantial scalability and state-of-the-art performance across diverse vision tasks. This work introduces a novel pathway for large vision foundation models, underscoring the promising potential of diffusion transformers. The code and models are available at https://derrickwang005.github.io/LaVin-DiT.
As interest grows in world models that predict future states from current observations and actions, accurately modeling part-level dynamics has become increasingly relevant for various applications. Existing approaches, such as Puppet-Master, rely on fine-tuning large-scale pre-trained video diffusion models, which are impractical for real-world use due to the limitations of 2D video representation and slow processing times. To overcome these challenges, we present PartRM, a novel 4D reconstruction framework that simultaneously models appearance, geometry, and part-level motion from multi-view images of a static object. PartRM builds upon large 3D Gaussian reconstruction models, leveraging their extensive knowledge of appearance and geometry in static objects. To address data scarcity in 4D, we introduce the PartDrag-4D dataset, providing multi-view observations of part-level dynamics across over 20,000 states. We enhance the model's understanding of interaction conditions with a multi-scale drag embedding module that captures dynamics at varying granularities. To prevent catastrophic forgetting during fine-tuning, we implement a two-stage training process that focuses sequentially on motion and appearance learning. Experimental results show that PartRM establishes a new state-of-the-art in part-level motion learning and can be applied in manipulation tasks in robotics. Our code, data, and models are publicly available to facilitate future research.