Diffusion-based Methods Research Articles

PtosisDiffusion: a training-free workflow for precisely predicting post-operative appearance in blepharoptosis patients based on diffusion models.

This study aims to develop a diffusion-based workflow to precisely predict postoperative appearance in blepharoptosis patients. We developed PtosisDiffusion, a training-free workflow that combines face mesh with ControlNet for accurate post-operative predictions, and evaluated it using 39 preoperative photos from blepharoptosis patients. The performance of PtosisDiffusion was compared against three other diffusion-based methods: Conditional Diffusion, Repaint, and Dragon Diffusion. PtosisDiffusion demonstrated superior performance in subjective evaluations, including overall rating, correction, and double eyelid formation. Statistical analyses confirmed that PtosisDiffusion achieved the highest overlap ratio (0.87 0.07) and an MPLPD ratio close to 1 (1.01 0.10). The model also showed robustness in extreme cases, and ablation studies confirmed the necessity of each model component. PtosisDiffusion generates accurate postoperative appearance predictions for ptosis patients using only preoperative photographs. Among the four models tested, PtosisDiffusion consistently outperformed the others in both subjective and statistical evaluation.

Scalable protein design using optimization in a relaxed sequence space.

Machine learning (ML)-based design approaches have advanced the field of de novo protein design, with diffusion-based generative methods increasingly dominating protein design pipelines. Here, we report a "hallucination"-based protein design approach that functions in relaxed sequence space, enabling the efficient design of high-quality protein backbones over multiple scales and with broad scope of application without the need for any form of retraining. We experimentally produced and characterized more than 100 proteins. Three high-resolution crystal structures and two cryo-electron microscopy density maps of designed single-chain proteins comprising up to 1000 amino acids validate the accuracy of the method. Our pipeline can also be used to design synthetic protein-protein interactions, as validated experimentally by a set of protein heterodimers. Relaxed sequence optimization offers attractive performance with respect to designability, scope of applicability for different design problems, and scalability across protein sizes.

Phenotypic and genotypic identification of class C and D β-lactamases in clinical isolates of Pseudomonas aeruginosa: a cross-sectional study.

The emergence of Pseudomonas aeruginosa (P. aeruginosa) antibiotic resistance is an important public health problem worldwide that can negatively affect infection control. Therefore, obtaining knowledge about antibiotic resistance mechanisms is necessary for infection control policies. This study aimed to determine the frequency of class C and D β-lactamases in P. aeruginosa strains isolated from patients referred to Ardabil hospitals using phenotypic and genotypic tests. Phenotypic detection of β-lactamases including AmpC cephalosporinase, oxacillinase (OXA)-type extended-spectrum β-lactamases (ESBLs), and OXA-type carbapenemases were performed using the disk diffusion-based methods. Amplification of genes encoding classes C (ampC and FOX genes) and D (OXA-1, OXA-2, OXA-10, OXA-23, and OXA-48 genes) β-lactamases was performed using the polymerase chain reaction (PCR) method. A quantitative reverse transcription PCR (qRT-PCR) method was used to determine the expression level of the ampC gene among multiple drug-resistant and imipenem-resistant P. aeruginosa strains. In phenotypic tests, the prevalence of AmpC cephalosporinase, OXA-type ESBLs, and OXA-type carbapenemases were 52.5%, 7.2%, and 95.8%, respectively. In genotypic tests, the prevalence of ampC, FOX, OXA-1, OXA-2, OXA-10, OXA-23, and OXA-48 genes were 100%, 0%, 4.3%, 60.8%, 42%, 29.7%, and 2.9%, respectively. In addition, the ampC gene overexpression was seen in 16 (33.3%) drug-resistant P. aeruginosa clinical isolates. Given the presence of class C and D β-lactamases in clinical isolates of P. aeruginosa in Ardabil hospitals, early detection of these strains can help prevent the spread of resistant strains in hospital environments and subsequent treatment failure.

Explicit-implicit priori knowledge-based diffusion model for generative medical image segmentation

The diffusion probabilistic model (DPM) has achieved unparalleled results in current image generation tasks, and some recent research works employed it in several computer vision tasks, such as image super-resolution, object detection, etc. Thanks to DPM's superior ability to generate fine-grained details, these research efforts have yielded significant successes. In this paper, we propose a new DPM-based generative medical image segmentation method, named EIDiffuSeg. Specifically, we first construct an explicit-implicit aggregation priori knowledge with directional supervision ability by mining the semantic distribution pattern in the frequency and spatial domains. Then, the explicit-implicit aggregation priori knowledge is integrated into the different encoding stages of the denoising backbone network using a novel unsupervised priori knowledge induction strategy, which can guide the model to generate a segmentation mask of the region of interest directionally from a random inference process. We evaluate our method on three medical image segmentation benchmark datasets with different modalities and achieve the best segmentation results compared to state-of-the-art methods. Especially, compared to several current diffusion-based image segmentation methods, we achieved a 9% Dice improvement in the polyp segmentation benchmark. Our code will be available at https://github.com/Notmezhan/EIDiffuSeg.

Structure-Based Drug Design with a Deep Hierarchical Generative Model.

Recently, the remarkable growth of available crystal structure data and libraries of commercially available or readily synthesizable molecules have unlocked previously inaccessible regions of chemical space for drug development. Paired with improvements in virtual ligand screening methods, these expanded libraries are having a notable impact on early drug design efforts. Yet screening-based methods still face scalability limits, due to computational constraints and the sheer scale of drug-like space. Machine learning approaches are overcoming these limitations by learning the fundamental intra- and intermolecular relationships in drug-target systems from existing data. Here, we introduce DrugHIVE, a deep hierarchical variational autoencoder that outperforms state-of-the-art autoregressive and diffusion-based methods in both speed and performance on common generative benchmarks. DrugHIVE's hierarchical design enables improved control over molecular generation. Its capabilities include dramatically increasing virtual screening efficiency and accelerating a wide range of common drug design tasks, including de novo generation, molecular optimization, scaffold hopping, linker design, and high-throughput pattern replacement. Our highly scalable method can even be applied to receptors with high-confidence AlphaFold-predicted structures, extending the ability to generate high-quality drug-like molecules to a majority of the unsolved human proteome.

Commercially available tests for determining cefiderocol susceptibility display variable performance in the Achromobacter genus

BackgroundCefiderocol is a siderophore-conjugated cephalosporin increasingly used in the management of Achromobacter infections. Testing for cefiderocol susceptibility is challenging with distinct recommendations depending on the pathogens.ObjectivesWe evaluated the performance of commercial tests for testing cefiderocol susceptibility in the Achromobacter genus and reviewed the literature.MethodsDiffusion (disks, MIC gradient test strips [MTS], Liofilchem) and broth microdilution (BMD) methods (ComASP™, Liofilchem; UMIC®, Bruker) were compared with the BMD reference method according to the EUCAST guidelines on 143 Achromobacter strains from 14 species with MIC50/90 of ≤ 0.015/0.5 mg/L. A literature search was conducted regardless of method or species.ResultsNone of the methods tested fulfilled an acceptable essential agreement (EA). MTS displayed the lowest EA (30.8%) after UMIC® (49%) and ComASP™ (76.9%). All methods achieved an acceptable bias, with MICs either underestimated using MTS (-1.3%) and ComASP™ (-14.2%) or overestimated with UMIC® (+ 9.1%). Inhibition zone diameters ranged from 6 to 38 mm (IZD50/90=33/30 mm). UMIC® and ComASP™ failed to categorize one or the two cefiderocol-resistant strains of this study as resistant unlike the diffusion-based methods. The literature review highlighted distinct performance of the available methods according to pathogens and testing conditions.ConclusionsThe use of MTS is discouraged for Achromobacter spp. Disk diffusion can be used to screen for susceptible strains by setting a threshold diameter of 30 mm. UMIC® and ComASP™ should not be used as the sole method but have to be systematically associated with disk diffusion to detect the yet rarely described cefiderocol-resistant Achromobacter sp. strains.

Coarse-to-fine mechanisms mitigate diffusion limitations on image restoration

Recent years have witnessed the remarkable performance of diffusion models in various vision tasks. However, for image restoration that aims to recover clear images with sharper details from given degraded observations, diffusion-based methods may fail to recover promising results due to inaccurate noise estimation. Moreover, simple constraining noises cannot effectively learn complex degradation information, which subsequently hinders the model capacity. To solve the above problems, we propose a coarse-to-fine diffusion Transformer (C2F-DFT) to mitigate diffusion limitations mentioned before on image restoration. Specifically, the proposed C2F-DFT contains diffusion self-attention (DFSA) and diffusion feed-forward network (DFN) within a new coarse-to-fine training mechanism. The DFSA and DFN with embedded diffusion steps respectively capture the long-range diffusion dependencies and learn hierarchy diffusion representation to guide the restoration process in different time steps. In the coarse training stage, our C2F-DFT estimates noises and then generates the final clean image by a sampling algorithm. To further improve the restoration quality, we propose a simple yet effective fine training pipeline. It first exploits the coarse-trained diffusion model with fixed steps to generate restoration results, which then would be constrained with corresponding ground-truth ones to optimize the models to remedy the unsatisfactory results affected by inaccurate noise estimation. Extensive experiments show that C2F-DFT significantly outperforms diffusion-based restoration method IR-SDE and achieves competitive performance compared with Transformer-based state-of-the-art methods on 3 tasks, including image deraining, image deblurring, and real image denoising. The source codes and visual results are available at https://github.com/wlydlut/C2F-DFT.

Assessing biological self-organization patterns using statistical complexity characteristics: a tool for diffusion tensor imaging analysis.

Diffusion-weighted imaging (DWI) and diffusion tensor imaging (DTI) are well-known and powerful imaging techniques for MRI. Although DTI evaluation has evolved continually in recent years, there are still struggles regarding quantitative measurements that can benefit brain areas that are consistently difficult to measure via diffusion-based methods, e.g., gray matter (GM). The present study proposes a new image processing technique based on diffusion distribution evaluation of López-Ruiz, Mancini and Calbet (LMC) complexity called diffusion complexity (DC). The OASIS-3 and TractoInferno open-science databases for healthy individuals were used, and all the codes are provided as open-source materials. The DC map showed relevant signal characterization in brain tissues and structures, achieving contrast-to-noise ratio (CNR) gains of approximately 39% and 93%, respectively, compared to those of the FA and ADC maps. In the special case of GM tissue, the DC map obtains its maximum signal level, showing the possibility of studying cortical and subcortical structures challenging for classical DTI quantitative formalism. The ability to apply the DC technique, which requires the same imaging acquisition for DTI and its potential to provide complementary information to study the brain's GM structures, can be a rich source of information for further neuroscience research and clinical practice.

Sampling with flows, diffusion, and autoregressive neural networks from a spin-glass perspective

Recent years witnessed the development of powerful generative models based on flows, diffusion, or autoregressive neural networks, achieving remarkable success in generating data from examples with applications in a broad range of areas. A theoretical analysis of the performance and understanding of the limitations of these methods remain, however, challenging. In this paper, we undertake a step in this direction by analyzing the efficiency of sampling by these methods on a class of problems with a known probability distribution and comparing it with the sampling performance of more traditional methods such as the Monte Carlo Markov chain and Langevin dynamics. We focus on a class of probability distribution widely studied in the statistical physics of disordered systems that relate to spin glasses, statistical inference, and constraint satisfaction problems. We leverage the fact that sampling via flow-based, diffusion-based, or autoregressive networks methods can be equivalently mapped to the analysis of a Bayes optimal denoising of a modified probability measure. Our findings demonstrate that these methods encounter difficulties in sampling stemming from the presence of a first-order phase transition along the algorithm's denoising path. Our conclusions go both ways: We identify regions of parameters where these methods are unable to sample efficiently, while that is possible using standard Monte Carlo or Langevin approaches. We also identify regions where the opposite happens: standard approaches are inefficient while the discussed generative methods work well.

Text to Image Conversion using Stable Diffusion

In this paper, we introduce a pioneering technique for translating textual descriptions into visually compelling images using stable diffusion methods, with a particular emphasis on the latent diffusion model (LDM). Our approach represents a departure from conventional methods like Generative Adversarial Networks (GANs) and AttnGAN, offering enhanced accuracy and diversity in the generated images. Through extensive experimentation and comparative analysis, we validate the efficacy of our method. Leveraging the LAION-5B dataset, we fine-tune the stable diffusion model, resulting in superior performance in text-to-image conversion tasks. Our findings underscore substantial advancements in accuracy, showcasing the promise of stable diffusion-based approaches across a spectrum of applications. By embracing stable diffusion techniques, we overcome some of the limitations encountered in previous methodologies. This enables us to achieve a higher fidelity in image generation while maintaining a diverse output spectrum. Our method excels in capturing intricate details and nuances specified in textual descriptions, facilitating a more faithful translation from text to image. The significance of our work extends beyond mere technical improvements. By pushing the boundaries of image synthesis, we contribute to the evolution of artificial intelligence, fostering new possibilities for creative expression and content generation. Our approach not only enhances the capabilities of AI systems but also democratizes the process of image creation, empowering users to effortlessly translate their ideas into visually stunning representations. Through our research, we aim to inspire further exploration and innovation in the realm of text-to-image conversion. The success of stable diffusion-based methods underscores their potential to revolutionize various domains, including computer vision, graphic design, and multimedia content creation. As we continue to refine and optimize these techniques, we anticipate even greater strides in the field of AI, ushering in a new era of intelligent image synthesis and interpretation.

Color and Luminance Separated Enhancement for Low-Light Images with Brightness Guidance.

Existing retinex-based low-light image enhancement strategies focus heavily on crafting complex networks for Retinex decomposition but often result in imprecise estimations. To overcome the limitations of previous methods, we introduce a straightforward yet effective strategy for Retinex decomposition, dividing images into colormaps and graymaps as new estimations for reflectance and illumination maps. The enhancement of these maps is separately conducted using a diffusion model for improved restoration. Furthermore, we address the dual challenge of perturbation removal and brightness adjustment in illumination maps by incorporating brightness guidance. This guidance aids in precisely adjusting the brightness while eliminating disturbances, ensuring a more effective enhancement process. Extensive quantitative and qualitative experimental analyses demonstrate that our proposed method improves the performance by approximately 4.4% on the LOL dataset compared to other state-of-the-art diffusion-based methods, while also validating the model's generalizability across multiple real-world datasets.

Efficient Conditional Diffusion Model with Probability Flow Sampling for Image Super-resolution

Image super-resolution is a fundamentally ill-posed problem because multiple valid high-resolution images exist for one low-resolution image. Super-resolution methods based on diffusion probabilistic models can deal with the ill-posed nature by learning the distribution of high-resolution images conditioned on low-resolution images, avoiding the problem of blurry images in PSNR-oriented methods. However, existing diffusion-based super-resolution methods have high time consumption with the use of iterative sampling, while the quality and consistency of generated images are less than ideal due to problems like color shifting. In this paper, we propose Efficient Conditional Diffusion Model with Probability Flow Sampling (ECDP) for image super-resolution. To reduce the time consumption, we design a continuous-time conditional diffusion model for image super-resolution, which enables the use of probability flow sampling for efficient generation. Additionally, to improve the consistency of generated images, we propose a hybrid parametrization for the denoiser network, which interpolates between the data-predicting parametrization and the noise-predicting parametrization for different noise scales. Moreover, we design an image quality loss as a complement to the score matching loss of diffusion models, further improving the consistency and quality of super-resolution. Extensive experiments on DIV2K, ImageNet, and CelebA demonstrate that our method achieves higher super-resolution quality than existing diffusion-based image super-resolution methods while having lower time consumption. Our code is available at https://github.com/Yuan-Yutao/ECDP.

Geometric-Facilitated Denoising Diffusion Model for 3D Molecule Generation

Denoising diffusion models have shown great potential in multiple research areas. Existing diffusion-based generative methods on de novo 3D molecule generation face two major challenges. Since majority heavy atoms in molecules allow connections to multiple atoms through single bonds, solely using pair-wise distance to model molecule geometries is insufficient. Therefore, the first one involves proposing an effective neural network as the denoising kernel that is capable to capture complex multi-body interatomic relationships and learn high-quality features. Due to the discrete nature of graphs, mainstream diffusion-based methods for molecules heavily rely on predefined rules and generate edges in an indirect manner. The second challenge involves accommodating molecule generation to diffusion and accurately predicting the existence of bonds. In our research, we view the iterative way of updating molecule conformations in diffusion process is consistent with molecular dynamics and introduce a novel molecule generation method named Geometric-Facilitated Molecular Diffusion (GFMDiff). For the first challenge, we introduce a Dual-track Transformer Network (DTN) to fully excevate global spatial relationships and learn high quality representations which contribute to accurate predictions of features and geometries. As for the second challenge, we design Geometric-facilitated Loss (GFLoss) which intervenes the formation of bonds during the training period, instead of directly embedding edges into the latent space. Comprehensive experiments on current benchmarks demonstrate the superiority of GFMDiff.

Disentangled Diffusion-Based 3D Human Pose Estimation with Hierarchical Spatial and Temporal Denoiser

Recently, diffusion-based methods for monocular 3D human pose estimation have achieved state-of-the-art (SOTA) performance by directly regressing the 3D joint coordinates from the 2D pose sequence. Although some methods decompose the task into bone length and bone direction prediction based on the human anatomical skeleton to explicitly incorporate more human body prior constraints, the performance of these methods is significantly lower than that of the SOTA diffusion-based methods. This can be attributed to the tree structure of the human skeleton. Direct application of the disentangled method could amplify the accumulation of hierarchical errors, propagating through each hierarchy. Meanwhile, the hierarchical information has not been fully explored by the previous methods. To address these problems, a Disentangled Diffusion-based 3D human Pose Estimation method with Hierarchical Spatial and Temporal Denoiser is proposed, termed DDHPose. In our approach: (1) We disentangle the 3d pose and diffuse the bone length and bone direction during the forward process of the diffusion model to effectively model the human pose prior. A disentanglement loss is proposed to supervise diffusion model learning. (2) For the reverse process, we propose Hierarchical Spatial and Temporal Denoiser (HSTDenoiser) to improve the hierarchical modelling of each joint. Our HSTDenoiser comprises two components: the Hierarchical-Related Spatial Transformer (HRST) and the Hierarchical-Related Temporal Transformer (HRTT). HRST exploits joint spatial information and the influence of the parent joint on each joint for spatial modeling, while HRTT utilizes information from both the joint and its hierarchical adjacent joints to explore the hierarchical temporal correlations among joints. Extensive experiments on the Human3.6M and MPI-INF-3DHP datasets show that our method outperforms the SOTA disentangled-based, non-disentangled based, and probabilistic approaches by 10.0%, 2.0%, and 1.3%, respectively.

Shallow Diffusion for Fast Speech Enhancement (Student Abstract)

Recently, the field of Speech Enhancement has witnessed the success of diffusion-based generative models. However, these diffusion-based methods used to take multiple iterations to generate high-quality samples, leading to high computational costs and inefficiency. In this paper, we propose SDFEN (Shallow Diffusion for Fast spEech eNhancement), a novel approach for addressing the inefficiency problem while enhancing the quality of generated samples by reducing the iterative steps in the reverse process of diffusion method. Specifically, we introduce the shallow diffusion strategy initiating the reverse process with an adaptive time step to accelerate inference. In addition, a dedicated noisy predictor is further proposed to guide the adaptive selection of time step. Experiment results demonstrate the superiority of the proposed SDFEN in effectiveness and efficiency.

Controllable Mind Visual Diffusion Model

Brain signal visualization has emerged as an active research area, serving as a critical interface between the human visual system and computer vision models. Diffusion-based methods have recently shown promise in analyzing functional magnetic resonance imaging (fMRI) data, including the reconstruction of high-quality images consistent with original visual stimuli. Nonetheless, it remains a critical challenge to effectively harness the semantic and silhouette information extracted from brain signals. In this paper, we propose a novel approach, termed as Controllable Mind Visual Diffusion Model (CMVDM). Specifically, CMVDM first extracts semantic and silhouette information from fMRI data using attribute alignment and assistant networks. Then, a control model is introduced in conjunction with a residual block to fully exploit the extracted information for image synthesis, generating high-quality images that closely resemble the original visual stimuli in both semantic content and silhouette characteristics. Through extensive experimentation, we demonstrate that CMVDM outperforms existing state-of-the-art methods both qualitatively and quantitatively. Our code is available at https://github.com/zengbohan0217/CMVDM.

Brush Your Text: Synthesize Any Scene Text on Images via Diffusion Model

Recently, diffusion-based image generation methods are credited for their remarkable text-to-image generation capabilities, while still facing challenges in accurately generating multilingual scene text images. To tackle this problem, we propose Diff-Text, which is a training-free scene text generation framework for any language. Our model outputs a photo-realistic image given a text of any language along with a textual description of a scene. The model leverages rendered sketch images as priors, thus arousing the potential multilingual-generation ability of the pre-trained Stable Diffusion. Based on the observation from the influence of the cross-attention map on object placement in generated images, we propose a localized attention constraint into the cross-attention layer to address the unreasonable positioning problem of scene text. Additionally, we introduce contrastive image-level prompts to further refine the position of the textual region and achieve more accurate scene text generation. Experiments demonstrate that our method outperforms the existing method in both the accuracy of text recognition and the naturalness of foreground-background blending.

ResDiff: Combining CNN and Diffusion Model for Image Super-resolution

Adapting the Diffusion Probabilistic Model (DPM) for direct image super-resolution is wasteful, given that a simple Convolutional Neural Network (CNN) can recover the main low-frequency content. Therefore, we present ResDiff, a novel Diffusion Probabilistic Model based on Residual structure for Single Image Super-Resolution (SISR). ResDiff utilizes a combination of a CNN, which restores primary low-frequency components, and a DPM, which predicts the residual between the ground-truth image and the CNN predicted image. In contrast to the common diffusion-based methods that directly use LR space to guide the noise towards HR space, ResDiff utilizes the CNN’s initial prediction to direct the noise towards the residual space between HR space and CNN-predicted space, which not only accelerates the generation process but also acquires superior sample quality. Additionally, a frequency-domain-based loss function for CNN is introduced to facilitate its restoration, and a frequency-domain guided diffusion is designed for DPM on behalf of predicting high-frequency details. The extensive experiments on multiple benchmark datasets demonstrate that ResDiff outperforms previous diffusion based methods in terms of shorter model convergence time, superior generation quality, and more diverse samples.

Multiclass AI-Generated Deepfake Face Detection Using Patch-Wise Deep Learning Model

In response to the rapid advancements in facial manipulation technologies, particularly facilitated by Generative Adversarial Networks (GANs) and Stable Diffusion-based methods, this paper explores the critical issue of deepfake content creation. The increasing accessibility of these tools necessitates robust detection methods to curb potential misuse. In this context, this paper investigates the potential of Vision Transformers (ViTs) for effective deepfake image detection, leveraging their capacity to extract global features. Objective: The primary goal of this study is to assess the viability of ViTs in detecting multiclass deepfake images compared to traditional Convolutional Neural Network (CNN)-based models. By framing the deepfake problem as a multiclass task, this research introduces a novel approach, considering the challenges posed by Stable Diffusion and StyleGAN2. The objective is to enhance understanding and efficacy in detecting manipulated content within a multiclass context. Novelty: This research distinguishes itself by approaching the deepfake detection problem as a multiclass task, introducing new challenges associated with Stable Diffusion and StyleGAN2. The study pioneers the exploration of ViTs in this domain, emphasizing their potential to extract global features for enhanced detection accuracy. The novelty lies in addressing the evolving landscape of deepfake creation and manipulation. Results and Conclusion: Through extensive experiments, the proposed method exhibits high effectiveness, achieving impressive detection accuracy, precision, and recall, and an F1 rate of 99.90% on a multiclass-prepared dataset. The results underscore the significant potential of ViTs in contributing to a more secure digital landscape by robustly addressing the challenges posed by deepfake content, particularly in the presence of Stable Diffusion and StyleGAN2. The proposed model outperformed when compared with state-of-the-art CNN-based models, i.e., ResNet-50 and VGG-16.

Protein-Assisted Large-Scale Assembly and Differential Patterning of DNA Origami Lattices.

Nanofabrication has experienced a big boost with the invention of DNA origami, enabling the production and assembly of complex nanoscale structures that may be able to unlock fully new functionalities in biology and beyond. The remarkable precision with which these structures can be designed and produced is, however, not yet matched by their assembly dynamics, which can be extremely slow, particularly when attached to biological templates, such as membranes. Here, the rapid and controlled formation of DNA origami lattices on the scale of hundreds of micrometers in as little as 30minutes is demonstrated, utilizing active patterning by the E.coli Min protein system, thereby yielding a remarkable improvement over conventional passive diffusion-based assembly methods. Various patterns, including spots, inverse spots, mazes, and meshes can be produced at different scales, tailored through the shape and density of the assembled structures. The differential positioning accomplished by Min-induced diffusiophoresis even allows the introduction of "pseudo-colors", i.e., complex core-shell patterns, by simultaneously patterning different DNA origami species. Beyond the targeted functionalization of biological surfaces, this approach may also be promising for applications in plasmonics, catalysis, and molecular sensing.