Diffusion models have revolutionized the field of content synthesis and editing. Recent models have replaced the traditional UNet architecture with the Diffusion Transformer (DiT), and employed flow-matching for improved training and sampling. However, they exhibit limited generation diversity. In this work, we leverage this limitation to perform consistent image edits via selective injection of attention features. The main challenge is that, unlike the UNet-based models, DiT lacks a coarse-to-fine synthesis structure, making it unclear in which layers to perform the injection. Therefore, we propose an automatic method to identify "vital layers" within DiT, crucial for image formation, and demonstrate how these layers facilitate a range of controlled stable edits, from non-rigid modifications to object addition, using the same mechanism. Next, to enable real-image editing, we introduce an improved image inversion method for flow models. Finally, we evaluate our approach through qualitative and quantitative comparisons, along with a user study, and demonstrate its effectiveness across multiple applications.

Image tiling—the seamless connection of disparate images to create a coherent visual field—is crucial for applications such as texture creation, video game asset development, and digital art. Traditionally, tiles have been constructed manually, a method that poses significant limitations in scalability and flexibility. Recent research has attempted to automate this process using generative models. However, current approaches primarily focus on tiling textures and manipulating models for single-image generation, without inherently supporting the creation of multiple interconnected tiles across diverse domains. This paper presents Tiled Diffusion, a novel approach that extends the capabilities of diffusion models to accommodate the generation of cohesive tiling patterns across various domains of image synthesis that require tiling. Our method supports a wide range of tiling scenarios, from self-tiling to complex many-to-many connections, enabling seamless integration of multiple images. Tiled Diffusion automates the tiling process, eliminating the need for manual intervention and enhancing creative possibilities in various applications, such as seamlessly tiling of existing images, tiled texture creation, and 360° synthesis.

Diffusion models dominate the space of text-to-image generation, yet they may produce undesirable outputs, including explicit content or private data. To mitigate this, concept ablation techniques have been explored to limit the generation of certain concepts. In this paper, we reveal that the erased concept information persists in the model and that erased concept images can be generated using the right latent. Utilizing inversion methods, we show that there exist latent seeds capable of generating high quality images of erased concepts. Moreover, we show that these latents have likelihoods that overlap with those of images outside the erased concept. We extend this to demonstrate that for every image from the erased concept set, we can generate many seeds that generate the erased concept. Given the vast space of latents capable of generating ablated concept images, our results suggest that fully erasing concept information may be intractable, highlighting possible vulnerabilities in current concept ablation techniques.

Abstract While latent diffusion models achieve impressive image editing results, their application to iterative editing of the same image is severely restricted. When trying to apply consecutive edit operations using current models, they accumulate artifacts and noise due to repeated transitions between pixel and latent spaces. Some methods have attempted to address this limitation by performing the entire edit chain within the latent space, sacrificing flexibility by supporting only a limited, predetermined set of diffusion editing operations. We present a re‐encode decode (REED) training scheme for variational autoencoders (VAEs), which promotes image quality preservation even after many iterations. Our work enables multi‐method iterative image editing: users can perform a variety of iterative edit operations, with each operation building on the output of the previous one using both diffusion based operations and conventional editing techniques. We demonstrate the advantage of REED‐VAE across a range of image editing scenarios, including text‐based and mask‐based editing frameworks. In addition, we show how REED‐VAE enhances the overall editability of images, increasing the likelihood of successful and precise edit operations. We hope that this work will serve as a benchmark for the newly introduced task of multi‐method image editing.

Abstract Diffusion models have revolutionized image generation and editing, producing state‐of‐the‐art results in conditioned and unconditioned image synthesis. While current techniques enable user control over the degree of change in an image edit, the controllability is limited to global changes over an entire edited region. This paper introduces a novel framework that enables customization of the amount of change per pixel or per image region. Our framework can be integrated into any existing diffusion model, enhancing it with this capability. Such granular control opens up a diverse array of new editing capabilities, such as control of the extent to which individual objects are modified, or the ability to introduce gradual spatial changes. Furthermore, we showcase the framework's effectiveness in soft‐inpainting—the completion of portions of an image while subtly adjusting the surrounding areas to ensure seamless integration. Additionally, we introduce a new tool for exploring the effects of different change quantities. Our framework operates solely during inference, requiring no model training or fine‐tuning. We demonstrate our method with the current open state‐of‐the‐art models, and validate it via both quantitative and qualitative comparisons, and a user study. Our code is published and integrated into several platforms.

Understanding the 3D world from 2D images involves more than detection and segmentation of the objects within the scene. It also includes the interpretation of the structure and arrangement of the scene elements. Such understanding is often rooted in recognizing the physical world and its limitations, and in prior knowledge as to how similar typical scenes are arranged. In this research, we pose a new challenge for neural networks, or other scene understanding algorithms—can they distinguish plausible scenes from implausible ones? Plausibility is defined both in terms of physical properties and in terms of functional and typical arrangements. Loosely, it can be seen as the probability of encountering a given scene in the real physical world. We have built a dataset of synthetic images containing both plausible and implausible scenes, and test the success of various vision models for the task of classifying and recognizing different types of implausibility. Our code and dataset is publicly available at https://github.com/ornachmias/scene_plusibility_prediction.

Fine-grained visual classification (FGVC) involves classifying closely related subcategories. This task is inherently difficult due to the subtle differences between classes and the high intra-class variance. Moreover, FGVC datasets are typically small and challenging to gather, thus highlighting a significant need for effective data augmentation. Recent advancements in text-to-image diffusion models have introduced new possibilities for data augmentation in image classification. While these models have been used to generate training data for classification tasks, their effectiveness in full-dataset training of FGVC models remains under-explored. Recent techniques that rely on text-to-image generation or Img2Img methods, such as SDEdit, often struggle to generate images that accurately represent the class while modifying them to a degree that significantly increases the dataset's diversity. To address these challenges, we present SaSPA: Structure and Subject Preserving Augmentation. Contrary to recent methods, our method does not use real images as guidance, thereby increasing generation flexibility and promoting greater diversity. To ensure accurate class representation, we employ conditioning mechanisms, specifically by conditioning on image edges and subject representation. We conduct extensive experiments and benchmark SaSPA against both traditional and generative data augmentation techniques. SaSPA consistently outperforms all established baselines across multiple settings, including full dataset training and contextual bias. Additionally, our results reveal interesting patterns in using synthetic data for FGVC models; for instance, we find a relationship between the amount of real data used and the optimal proportion of synthetic data.

We propose an algorithm for taming Normalizing Flow models — changing the probability that the model will produce a specific image or image category. We focus on Normalizing Flows because they can calculate the exact generation probability likelihood for a given image. We demonstrate taming using models that generate human faces, a subdomain with many interesting privacy and bias considerations. Our method can be used in the context of privacy, e.g., removing a specific person from the output of a model, and also in the context of debiasing by forcing a model to output specific image categories according to a given distribution. Taming is achieved with a fast fine-tuning process without retraining from scratch, achieving the goal in a matter of minutes. We evaluate our method qualitatively and quantitatively, showing that the generation quality remains intact, while the desired changes are applied.

The generation of high-quality images has become widely accessible and is a rapidly evolving process. As a result, anyone can generate images that are indistinguishable from real ones. This leads to a wide range of applications, including malicious usage with deceptive intentions. Despite advances in detection techniques for generated images, a robust detection method still eludes us. Furthermore, model personalization techniques might affect the detection capabilities of existing methods. In this work, we utilize the architectural properties of convolutional neural networks (CNNs) to develop a new detection method. Our method can detect images from a known generative model and enable us to establish relationships between fine-tuned generative models. We tested the method on images produced by both Generative Adversarial Networks (GANs) and recent large text-to-image models (LTIMs) that rely on Diffusion Models. Our approach outperforms others trained under identical conditions and achieves comparable performance to state-of-the-art pre-trained detection methods on images generated by Stable Diffusion and MidJourney, with significantly fewer required train samples.

Recent text-to-image diffusion models are able to generate convincing results of unprecedented quality. However, it is nearly impossible to control the shapes of different regions/objects or their layout in a fine-grained fashion. Previous attempts to provide such controls were hindered by their reliance on a fixed set of labels. To this end, we present SpaText — a new method for text-to-image generation using open-vocabulary scene control. In addition to a global text prompt that describes the entire scene, the user provides a segmentation map where each region of interest is annotated by a free-form natural language description. Due to lack of large-scale datasets that have a detailed textual description for each region in the image, we choose to leverage the current large-scale text-to-image datasets and base our approach on a novel CLIP-based spatio-textual representation, and show its effectiveness on two state-of-the-art diffusion models: pixel-based and latent-based. In addition, we show how to extend the classifier-free guidance method in diffusion models to the multi-conditional case and present an alternative accelerated inference algorithm. Finally, we offer several automatic evaluation metrics and use them, in addition to FID scores and a user study, to evaluate our method and show that it achieves state-of-the-art results on image generation with free-form textual scene control.

Translating spoken languages into Sign languages is necessary for open communication between the hearing and hearing-impaired communities. To achieve this goal, we propose the first method for animating a text written in HamNoSys, a lexical Sign language notation, into signed pose sequences. As HamNoSys is universal by design, our proposed method offers a generic solution invariant to the target Sign language. Our method gradually generates pose predictions using transformer encoders that create meaningful representations of the text and poses while considering their spatial and temporal information. We use weak supervision for the training process and show that our method succeeds in learning from partial and inaccurate data. Additionally, we offer a new distance measurement that considers missing keypoints, to measure the distance between pose sequences using DTW-MJE. We validate its correctness using AUTSL, a large-scale Sign language dataset, show that it measures the distance between pose sequences more accurately than existing measurements, and use it to assess the quality of our generated pose sequences. Code for the data pre-processing, the model, and the distance measurement is publicly released for future research.

Text-to-image model personalization aims to introduce a user-provided concept to the model, allowing its synthesis in diverse contexts. However, current methods primarily focus on the case of learning a single concept from multiple images with variations in backgrounds and poses, and struggle when adapted to a different scenario. In this work, we introduce the task of textual scene decomposition: given a single image of a scene that may contain several concepts, we aim to extract a distinct text token for each concept, enabling fine-grained control over the generated scenes. To this end, we propose augmenting the input image with masks that indicate the presence of target concepts. These masks can be provided by the user or generated automatically by a pre-trained segmentation model. We then present a novel two-phase customization process that optimizes a set of dedicated textual embeddings (handles), as well as the model weights, striking a delicate balance between accurately capturing the concepts and avoiding overfitting. We employ a masked diffusion loss to enable handles to generate their assigned concepts, complemented by a novel loss on cross-attention maps to prevent entanglement. We also introduce union-sampling, a training strategy aimed to improve the ability of combining multiple concepts in generated images. We use several automatic metrics to quantitatively compare our method against several baselines, and further affirm the results using a user study. Finally, we showcase several applications of our method.

The colorization of grayscale images is a complex and subjective task with significant challenges. Despite recent progress in employing large-scale datasets with deep neural networks, difficulties with controllability and visual quality persist. To tackle these issues, we present a novel image colorization framework that utilizes image diffusion techniques with granular text prompts. This integration not only produces colorization outputs that are semantically appropriate but also greatly improves the level of control users have over the colorization process. Our method provides a balance between automation and control, outperforming existing techniques in terms of visual quality and semantic coherence. We leverage a pretrained generative Diffusion Model, and show that we can finetune it for the colorization task without losing its generative power or attention to text prompts. Moreover, we present a novel CLIP-based ranking model that evaluates color vividness, enabling automatic selection of the most suitable level of vividness based on the specific scene semantics. Our approach holds potential particularly for color enhancement and historical image colorization.

The field of implicit neural representation has made significant progress. Models such as neural radiance fields (NeRF) [12], which uses relatively small neural networks, can represent high-quality scenes and achieve state-of-the-art results for novel view synthesis. Training these types of networks, however, is still computationally expensive and the model struggles with real life 360° scenes. In this work, we propose the depth distribution neural radiance field (DDNeRF), a new method that significantly increases sampling efficiency along rays during training, while achieving superior results for a given sampling budget. DDNeRF achieves this performance by learning a more accurate representation of the density distribution along rays. More specifically, the proposed framework trains a coarse model to predict the internal distribution of the transparency of an input volume along each ray. This estimated distribution then guides the sampling procedure of the fine model. Our method allows using fewer samples during training while achieving better output quality with the same computational resources.

The tremendous progress in neural image generation, coupled with the emergence of seemingly omnipotent vision-language models has finally enabled text-based interfaces for creating and editing images. Handling generic images requires a diverse underlying generative model, hence the latest works utilize diffusion models, which were shown to surpass GANs in terms of diversity. One major drawback of diffusion models, however, is their relatively slow inference time. In this paper, we present an accelerated solution to the task of local text-driven editing of generic images, where the desired edits are confined to a user-provided mask. Our solution leverages a text-to-image Latent Diffusion Model (LDM), which speeds up diffusion by operating in a lower-dimensional latent space and eliminating the need for resource-intensive CLIP gradient calculations at each diffusion step. We first enable LDM to perform local image edits by blending the latents at each step, similarly to Blended Diffusion. Next we propose an optimization-based solution for the inherent inability of LDM to accurately reconstruct images. Finally, we address the scenario of performing local edits using thin masks. We evaluate our method against the available baselines both qualitatively and quantitatively and demonstrate that in addition to being faster, it produces more precise results.

Natural language offers a highly intuitive interface for image editing. In this paper, we introduce the first solution for performing local (region-based) edits in generic natural images, based on a natural language description along with an ROI mask. We achieve our goal by leveraging and combining a pretrained language-image model (CLIP), to steer the edit towards a user-provided text prompt, with a denoising diffusion probabilistic model (DDPM) to generate natural-looking results. To seamlessly fuse the edited region with the unchanged parts of the image, we spatially blend noised versions of the input image with the local text-guided diffusion latent at a progression of noise levels. In addition, we show that adding augmentations to the diffusion process mitigates adversarial results. We compare against several baselines and related methods, both qualitatively and quantitatively, and show that our method outperforms these solutions in terms of overall realism, ability to preserve the background and matching the text. Finally, we show several text-driven editing applications, including adding a new object to an image, removing/replacing/altering existing objects, background replacement, and image extrapolation.

Learning 3D generative models from a dataset of monocular images enables self-supervised 3D reasoning and controllable synthesis. State-of-the-art 3D generative models are GANs that use neural 3D volumetric representations for synthesis. Images are synthesized by rendering the volumes from a given camera. These models can disentangle the 3D scene from the camera viewpoint in any generated image. However, most models do not disentangle other factors of image formation, such as geometry and appearance. In this paper, we design a 3D GAN which can learn a disentangled model of objects, just from monocular observations. Our model can disentangle the geometry and appearance variations in the scene, i.e., we can independently sample from the geometry and appearance spaces of the generative model. This is achieved using a novel non-rigid deformable scene formulation. A 3D volume that represents an object instance is computed as a non-rigidly deformed canonical 3D volume. Our method learns the canonical volume, as well as its deformations, jointly during training. This formulation also helps us improve the disentanglement between the 3D scene and the camera viewpoints using a novel pose regularization loss defined on the 3D deformation field. In addition, we model the inverse deformations, enabling the computation of dense correspondences between images generated by our model. Finally, we design an approach to embed real images into the latent space of our model, enabling editing of real images.

Unwanted clutter in a photo can be incredibly distracting. However in the moment, photographers have so many things to simultaneously consider, it can be hard to catch every detail. Designers have long known the benefits of abstraction for seeing a more holistic view of their design. We wondered if, similarly, some form of image abstraction might be helpful for photographers as an alternative perspective or “lens” with which to see their image. Specifically, we wondered if such abstraction might draw the photographer’s attention away from details in the subject to noticing objects in the background, such as unwanted clutter. We present our process for designing such a camera overlay, based on the idea of using abstraction to recognize clutter. Our final design uses object-based saliency and edge detection to highlight contrast along subject and image borders, outlining potential distractors in these regions. We describe the implementation and evaluation of a capture-time tool that interactively displays these overlays and find that the tool is helpful for making users more confident in their ability to take decluttered photos that clearly convey their intended story.

We present an algorithm for producing a seamless animated loop from a single image. The algorithm detects periodic structures, such as the windows of a building or the steps of a staircase, and generates a non-trivial displacement vector field that maps each segment of the structure onto a neighboring segment along a user- or auto-selected main direction of motion. This displacement field is used, together with suitable temporal and spatial smoothing, to warp the image and produce the frames of a continuous animation loop. Our cinemagraphs are created in under a second on a mobile device. Over 140,000 users downloaded our app and exported over 350,000 cinemagraphs. Moreover, we conducted two user studies that show that users prefer our method for creating surreal and structured cinemagraphs compared to more manual approaches and compared to previous methods.

We present a text-based tool for editing talking-head video that enables an iterative editing workflow. On each iteration users can edit the wording of the speech, further refine mouth motions if necessary to reduce artifacts, and manipulate non-verbal aspects of the performance by inserting mouth gestures (e.g., a smile) or changing the overall performance style (e.g., energetic, mumble). Our tool requires only 2 to 3 minutes of the target actor video and it synthesizes the video for each iteration in about 40 seconds, allowing users to quickly explore many editing possibilities as they iterate. Our approach is based on two key ideas. (1) We develop a fast phoneme search algorithm that can quickly identify phoneme-level subsequences of the source repository video that best match a desired edit. This enables our fast iteration loop. (2) We leverage a large repository of video of a source actor and develop a new self-supervised neural retargeting technique for transferring the mouth motions of the source actor to the target actor. This allows us to work with relatively short target actor videos, making our approach applicable in many real-world editing scenarios. Finally, our, refinement and performance controls give users the ability to further fine-tune the synthesized results.

Photographic composition is often taught as alignment with composition grids-most commonly, the rule of thirds. Professional photographers use more complex grids, like the harmonic armature, to achieve more diverse dynamic compositions. We are interested in understanding whether these complex grids are helpful to amateurs.

Abstract Efficient rendering of photo‐realistic virtual worlds is a long standing effort of computer graphics. Modern graphics techniques have succeeded in synthesizing photo‐realistic images from hand‐crafted scene representations. However, the automatic generation of shape, materials, lighting, and other aspects of scenes remains a challenging problem that, if solved, would make photo‐realistic computer graphics more widely accessible. Concurrently, progress in computer vision and machine learning have given rise to a new approach to image synthesis and editing, namely deep generative models. Neural rendering is a new and rapidly emerging field that combines generative machine learning techniques with physical knowledge from computer graphics, e.g., by the integration of differentiable rendering into network training. With a plethora of applications in computer graphics and vision, neural rendering is poised to become a new area in the graphics community, yet no survey of this emerging field exists. This state‐of‐the‐art report summarizes the recent trends and applications of neural rendering. We focus on approaches that combine classic computer graphics techniques with deep generative models to obtain controllable and photorealistic outputs. Starting with an overview of the underlying computer graphics and machine learning concepts, we discuss critical aspects of neural rendering approaches. Specifically, our emphasis is on the type of control, i.e., how the control is provided, which parts of the pipeline are learned, explicit vs. implicit control, generalization, and stochastic vs. deterministic synthesis. The second half of this state‐of‐the‐art report is focused on the many important use cases for the described algorithms such as novel view synthesis, semantic photo manipulation, facial and body reenactment, relighting, free‐viewpoint video, and the creation of photo‐realistic avatars for virtual and augmented reality telepresence. Finally, we conclude with a discussion of the social implications of such technology and investigate open research problems.

We present a capture-time tool designed to help casual photographers orient their subject to achieve a user-specified target facial appearance. The inputs to our tool are an HDR environment map of the scene captured using a 360 camera, and a target facial appearance, selected from a gallery of common studio lighting styles. Our tool computes the optimal orientation for the subject to achieve the target lighting using a computationally efficient precomputed radiance transfer-based approach. It then tells the photographer how far to rotate about the subject. Optionally, our tool can suggest how to orient a secondary external light source (e.g. a phone screen) about the subject's face to further improve the match to the target lighting. We demonstrate the effectiveness of our approach in a variety of indoor and outdoor scenes using many different subjects to achieve a variety of looks. A user evaluation suggests that our tool reduces the mental effort required by photographers to produce well-lit portraits.

A metric for natural image patches is an important tool for analyzing images. An efficient means of learning one is to train a deep network to map an image patch to a vector space, in which the Euclidean distance reflects patch similarity. Previous attempts learned such an embedding in a supervised manner, requiring the availability of many annotated images. In this paper, we present an unsupervised embedding of natural image patches, avoiding the need for annotated images. The key idea is that the similarity of two patches can be learned from the prevalence of their spatial proximity in natural images. Clearly, relying on this simple principle, many spatially nearby pairs are outliers. However, as we show, these outliers do not harm the convergence of the metric learning. We show that our unsupervised embedding approach is more effective than a supervised one or one that uses deep patch representations. Moreover, we show that it naturally lends itself to an efficient self-supervised domain adaptation technique onto a target domain that contains a common foreground object.

Editing talking-head video to change the speech content or to remove filler words is challenging. We propose a novel method to edit talking-head video based on its transcript to produce a realistic output video in which the dialogue of the speaker has been modified, while maintaining a seamless audio-visual flow (i.e. no jump cuts). Our method automatically annotates an input talking-head video with phonemes, visemes, 3D face pose and geometry, reflectance, expression and scene illumination per frame. To edit a video, the user has to only edit the transcript, and an optimization strategy then chooses segments of the input corpus as base material. The annotated parameters corresponding to the selected segments are seamlessly stitched together and used to produce an intermediate video representation in which the lower half of the face is rendered with a parametric face model. Finally, a recurrent video generation network transforms this representation to a photorealistic video that matches the edited transcript. We demonstrate a large variety of edits, such as the addition, removal, and alteration of words, as well as convincing language translation and full sentence synthesis.

Abstract Many image editing applications rely on the analysis of image patches. In this paper, we present a method to analyze patches by embedding them to a vector space, in which the Euclidean distance reflects patch similarity. Inspired by Word2Vec, we term our approachPatch2Vec. However, there is a significant difference between words and patches. Words have a fairly small and well defined dictionary. Image patches, on the other hand, have no such dictionary and the number of different patch types is not well defined. The problem is aggravated by the fact that each patch might contain several objects and textures. Moreover, Patch2Vec should be universal because it must be able to map never‐seen‐before texture to the vector space. The mapping is learned by analyzing the distribution of all natural patches. We use Convolutional Neural Networks (CNN) to learn Patch2Vec. In particular, we train a CNN on labeled images with a triplet‐loss objective function. The trained network encodes a given patch to a 128D vector. Patch2Vec is evaluated visually, qualitatively, and quantitatively. We then use several variants of an interactive single‐click image segmentation algorithm to demonstrate the power of our method.

This paper introduces a method to modify the apparent relative pose and distance between camera and subject given a single portrait photo. Our approach fits a full perspective camera and a parametric 3D head model to the portrait, and then builds a 2D warp in the image plane to approximate the effect of a desired change in 3D. We show that this model is capable of correcting objectionable artifacts such as the large noses sometimes seen in "selfies," or to deliberately bring a distant camera closer to the subject. This framework can also be used to re-pose the subject, as well as to create stereo pairs from an input portrait. We show convincing results on both an existing dataset as well as a new dataset we captured to validate our method.

We propose a new computer vision task we call “distractor prediction.” Distractors are the regions of an image that draw attention away from the main subjects and reduce the overall image quality. Removing distractors-for example, using in-painting - can improve the composition of an image. In this work we created two datasets of images with user annotations to identify the characteristics of distractors. We use these datasets to train an algorithm to predict distractor maps. Finally, we use our predictor to automatically enhance images.

Abstract Collections of objects such as images are often presented visually in a grid because it is a compact representation that lends itself well for search and exploration. Most grid layouts are sorted using very basic criteria, such as date or filename. In this work we present a method to arrange collections of objects respecting an arbitrary distance measure. Pairwise distances are preserved as much as possible, while still producing the specific target arrangement which may be a 2D grid, the surface of a sphere, a hierarchy, or any other shape. We show that our method can be used for infographics, collection exploration, summarization, data visualization, and even for solving problems such as where to seat family members at a wedding. We present a fast algorithm that can work on large collections and quantitatively evaluate how well distances are preserved.

Image editing applications offer a wide array of tools for color manipulation. Some of these tools are easy to understand but offer a limited range of expressiveness. Other more powerful tools are time consuming for experts and inscrutable to novices. Researchers have described a variety of more sophisticated methods but these are typically not interactive, which is crucial for creative exploration. This paper introduces a simple, intuitive and interactive tool that allows non-experts to recolor an image by editing a color palette. This system is comprised of several components: a GUI that is easy to learn and understand, an efficient algorithm for creating a color palette from an image, and a novel color transfer algorithm that recolors the image based on a user-modified palette. We evaluate our approach via a user study, showing that it is faster and easier to use than two alternatives, and allows untrained users to achieve results comparable to those of experts using professional software.