Vision-Language Models (VLMs) have recently demonstrated remarkable capabilities in comprehending complex visual content. However, the mechanisms underlying how VLMs process visual information remain largely unexplored. In this paper, we conduct a thorough empirical analysis, focusing on the attention modules across layers, by which we reveal several key insights about how these models process visual data: (i) the internal representation of the query tokens (e.g., representations of "describe the image"), is utilized by the model to store global image information; we demonstrate that the model generates surprisingly descriptive responses solely from these tokens, without direct access to image tokens. (ii) Cross-modal information flow is predominantly influenced by the middle layers (approximately 25% of all layers), while early and late layers contribute only marginally. (iii) Fine-grained visual attributes and object details are directly extracted from image tokens in a spatially localized manner, i.e., the generated tokens associated with specific object or attribute attend strongly to their corresponding regions in the image. We propose novel quantitative evaluation to validate our observations, leveraging real-world complex visual scenes. Finally, we demonstrate the potential of our findings in facilitating efficient visual processing in state-of-the-art VLMs.

Given a video and a set of input object masks, an omnimatte method aims to decompose the video into semantically meaningful layers containing individual objects along with their associated effects, such as shadows and reflections. Existing omnimatte methods assume a static background or accurate pose and depth estimation and produce poor decompositions when these assumptions are violated. Furthermore, due to the lack of generative prior on natural videos, existing methods cannot complete dynamic occluded regions. We present a novel generative layered video decomposition framework to address the omnimatte problem. Our method does not assume a stationary scene or require camera pose or depth information and produces clean, complete layers, including convincing completions of occluded dynamic regions. Our core idea is to train a video diffusion model to identify and remove scene effects caused by a specific object. We show that this model can be finetuned from an existing video inpainting model with a small, carefully curated dataset, and demonstrate high-quality decompositions and editing results for a wide range of casually captured videos containing soft shadows, glossy reflections, splashing water, and more.

We present a method for augmenting real-world videos with newly generated dynamic content. Given an input video and a simple user-provided text instruction describing the desired content, our method synthesizes dynamic objects or complex scene effects that naturally interact with the existing scene over time. The position, appearance, and motion of the new content are seamlessly integrated into the original footage while accounting for camera motion, occlusions, and interactions with other dynamic objects in the scene, resulting in a cohesive and realistic output video. We achieve this via a zero-shot, training-free framework that harnesses a pre-trained text-to-video diffusion transformer to synthesize the new content and a pre-trained vision-language model to envision the augmented scene in detail. Specifically, we introduce a novel inference-based method that manipulates features within the attention mechanism, enabling accurate localization and seamless integration of the new content while preserving the integrity of the original scene. Our method is fully automated, requiring only a simple user instruction. We demonstrate its effectiveness on a wide range of edits applied to real-world videos, encompassing diverse objects and scenarios involving both camera and object motion. Code for this paper will be available soon at https://github.com/DynVFX/dynvfx.

We present TokenVerse - a method for multi-concept personalization, leveraging a pre-trained text-to-image diffusion model. Our framework can disentangle complex visual elements and attributes from as little as a single image, while enabling seamless plug-and-play generation of combinations of concepts extracted from multiple images. As opposed to existing works, TokenVerse can handle multiple images with multiple concepts each, and supports a wide-range of concepts, including objects, accessories, materials, pose, and lighting. Our work exploits a DiT-based text-to-image model, in which the input text affects the generation through both attention and modulation (shift and scale). We observe that the modulation space is semantic and enables localized control over complex concepts. Building on this insight, we devise an optimization-based framework that takes as input an image and a text description, and finds for each word a distinct direction in the modulation space. These directions can then be used to generate new images that combine the learned concepts in a desired configuration. We demonstrate the effectiveness of TokenVerse in challenging personalization settings, and showcase its advantages over existing methods.

We present a new method for text-driven motion transfer - synthesizing a video that complies with an input text prompt describing the target objects and scene while maintaining an input video's motion and scene layout. Prior methods are confined to transferring motion across two subjects within the same or closely related object categories and are applicable for limited domains (e.g., humans). In this work, we consider a significantly more challenging setting in which the target and source objects differ drastically in shape and fine-grained motion characteristics (e.g., translating a jumping dog into a dolphin). To this end, we leverage a pre-trained and fixed text-to-video diffusion model, which provides us with generative and motion priors. The pillar of our method is a new space-time feature loss derived directly from the model. This loss guides the generation process to preserve the overall motion of the input video while complying with the target object in terms of shape and fine-grained motion traits.11Code will be made publicly available. Project page: https://diffusion-motion-transfer.github.io/

The generative AI revolution has recently expanded to videos. Nevertheless, current state-of-the-art video models are still lagging behind image models in terms of visual quality and user control over the generated content. In this work, we present a framework that harnesses the power of a text-to-image diffusion model for the task of text-driven video editing. Specifically, given a source video and a target text-prompt, our method generates a high-quality video that adheres to the target text, while preserving the spatial layout and motion of the input video. Our method is based on a key observation that consistency in the edited video can be obtained by enforcing consistency in the diffusion feature space. We achieve this by explicitly propagating diffusion features based on inter-frame correspondences, readily available in the model. Thus, our framework does not require any training or fine-tuning, and can work in conjunction with any off-the-shelf text-to-image editing method. We demonstrate state-of-the-art editing results on a variety of real-world videos.

Abstract The field of visual computing is rapidly advancing due to the emergence of generative artificial intelligence (AI), which unlocks unprecedented capabilities for the generation, editing, and reconstruction of images, videos, and 3D scenes. In these domains, diffusion models are the generative AI architecture of choice. Within the last year alone, the literature on diffusion‐based tools and applications has seen exponential growth and relevant papers are published across the computer graphics, computer vision, and AI communities with new works appearing daily on arXiv. This rapid growth of the field makes it difficult to keep up with all recent developments. The goal of this state‐of‐the‐art report (STAR) is to introduce the basic mathematical concepts of diffusion models, implementation details and design choices of the popular Stable Diffusion model, as well as overview important aspects of these generative AI tools, including personalization, conditioning, inversion, among others. Moreover, we give a comprehensive overview of the rapidly growing literature on diffusion‐based generation and editing, categorized by the type of generated medium, including 2D images, videos, 3D objects, locomotion, and 4D scenes. Finally, we discuss available datasets, metrics, open challenges, and social implications. This STAR provides an intuitive starting point to explore this exciting topic for researchers, artists, and practitioners alike.

Customizing text-to-image (T2I) models has seen tremendous progress recently, particularly in areas such as personalization, stylization, and conditional generation. However, expanding this progress to video generation is still in its infancy, primarily due to the lack of customized video data. In this work, we introduce Still-Moving, a novel generic framework for customizing a text-to-video (T2V) model, without requiring any customized video data. The framework applies to the prominent T2V design where the video model is built over a T2I model (e.g., via inflation). We assume access to a customized version of the T2I model, trained only on still image data (e.g., using DreamBooth). Naively plugging in the weights of the customized T2I model into the T2V model often leads to significant artifacts or insufficient adherence to the customization data. To overcome this issue, we train lightweight Spatial Adapters that adjust the features produced by the injected T2I layers. Importantly, our adapters are trained on "frozen videos" (i.e., repeated images), constructed from image samples generated by the customized T2I model. This training is facilitated by a novel Motion Adapter module, which allows us to train on such static videos while preserving the motion prior of the video model. At test time, we remove the Motion Adapter modules and leave in only the trained Spatial Adapters. This restores the motion prior of the T2V model while adhering to the spatial prior of the customized T2I model. We demonstrate the effectiveness of our approach on diverse tasks including personalized, stylized, and conditional generation. In all evaluated scenarios, our method seamlessly integrates the spatial prior of the customized T2I model with a motion prior supplied by the T2V model.

We present a method for semantically transferring the visual appearance of one natural image to another. Specifically, our goal is to generate an image in which objects in a source structure image are “painted” with the visual appearance of their semantically related objects in a target appearance image. To integrate semantic information into our framework, our key idea is to leverage a pre-trained and fixed Vision Transformer (ViT) model. Specifically, we derive novel disentangled representations of structure and appearance extracted from deep ViT features. We then establish an objective function that splices the desired structure and appearance representations, interweaving them together in the space of ViT features. Based on our objective function, we propose two frameworks of semantic appearance transfer – “Splice”, which works by training a generator on a single and arbitrary pair of structure-appearance images, and “SpliceNet”, a feed-forward real-time appearance transfer model trained on a dataset of images from a specific domain . Our frameworks do not involve adversarial training, nor do they require any additional input information such as semantic segmentation or correspondences. We demonstrate high-resolution results on a variety of in-the-wild image pairs, under significant variations in the number of objects, pose, and appearance. Code and supplementary material are available in our project page: splice-vit.github.io.

Text-conditioned image editing has recently attracted considerable interest. However, most methods are currently limited to one of the following: specific editing types (e.g., object overlay, style transfer), synthetically generated images, or requiring multiple input images of a common object. In this paper we demonstrate, for the very first time, the ability to apply complex (e.g., non-rigid) text-based semantic edits to a single real image. For example, we can change the posture and composition of one or multiple objects inside an image, while preserving its original characteristics. Our method can make a standing dog sit down, cause a bird to spread its wings, etc. – each within its single high-resolution user-provided natural image. Contrary to previous work, our proposed method requires only a single input image and a target text (the desired edit). It operates on real images, and does not require any additional inputs (such as image masks or additional views of the object). Our method, called Imagic, leverages a pre-trained text-to-image diffusion model for this task. It produces a text embedding that aligns with both the input image and the target text, while fine-tuning the diffusion model to capture the image-specific appearance. We demonstrate the quality and versatility of Imagic on numerous inputs from various domains, showcasing a plethora of high quality complex semantic image edits, all within a single unified framework. To better assess performance, we introduce TEdBench, a highly challenging image editing benchmark. We conduct a user study, whose findings show that human raters prefer Imagic to previous leading editing methods on TEdBench.

We present Neural Congealing – a zero-shot self-supervised framework for detecting and jointly aligning semantically-common content across a given set of images. Our approach harnesses the power of pre-trained DINO-ViT features to learn: (i) a joint semantic atlas – a 2D grid that captures the mode of DINO-ViT features in the input set, and (ii) dense mappings from the unified atlas to each of the input images. We derive a new robust self-supervised framework that optimizes the atlas representation and mappings per image set, requiring only a few real-world images as input without any additional input information (e.g., segmentation masks). Notably, we design our losses and training paradigm to account only for the shared content under severe variations in appearance, pose, background clutter or other distracting objects. We demonstrate results on a plethora of challenging image sets including sets of mixed domains (e.g., aligning images depicting sculpture and artwork of cats), sets depicting related yet different object categories (e.g., dogs and tigers), or domains for which large-scale training data is scarce (e.g., coffee mugs). We thoroughly evaluate our method and show that our test-time optimization approach performs favorably compared to a state-of-the-art method that requires extensive training on large-scale datasets. Project webpage: https://neural-congealing.github.io/

Large-scale text-to-image generative models have been a revolutionary breakthrough in the evolution of generative AI, synthesizing diverse images with highly complex visual concepts. However, a pivotal challenge in leveraging such models for real-world content creation is providing users with control over the generated content. In this paper, we present a new framework that takes text-to- image synthesis to the realm of image-to-image translation - given a guidance image and a target text prompt as input, our method harnesses the power of a pre-trained text-to-image diffusion model to generate a new image that complies with the target text, while preserving the semantic layout of the guidance image. Specifically, we observe and empirically demonstrate that fine-grained control over the generated structure can be achieved by manipulating spatial features and their self-attention inside the model. This results in a simple and effective approach, where features extracted from the guidance image are directly injected into the generation process of the translated image, requiring no training or fine-tuning. We demonstrate high-quality results on versatile text-guided image translation tasks, including translating sketches, rough drawings and animations into realistic images, changing the class and appearance of objects in a given image, and modifying global qualities such as lighting and color.

Large vision-language models (VLMs), such as CLIP, learn rich joint image-text representations, facilitating advances in numerous downstream tasks, including zero-shot classification and text-to-image generation. Nevertheless, existing VLMs exhibit a prominent well-documented limitation – they fail to encapsulate compositional concepts such as counting. We introduce a simple yet effective method to improve the quantitative understanding of VLMs, while maintaining their overall performance on common benchmarks. Specifically, we propose a new counting-contrastive loss used to finetune a pre-trained VLM in tandem with its original objective. Our counting loss is deployed over automatically-created counterfactual examples, each consisting of an image and a caption containing an incorrect object count. For example, an image depicting three dogs is paired with the caption "Six dogs playing in the yard" as a negative example. Our loss encourages discrimination between the correct caption and its counterfactual variant which serves as a hard negative example. To the best of our knowledge, this work is the first to extend CLIP’s capabilities to object counting. Furthermore, we introduce "CountBench" – a new image-text counting benchmark for evaluating object counting capabilities. We demonstrate a significant improvement over state-of-the-art baseline models on this task. Finally, we leverage our counting-aware CLIP model for image retrieval and text-conditioned image generation, demonstrating that our model can produce specific counts of objects more reliably than existing ones.

Recent advances in text-to-image generation with diffusion models present transformative capabilities in image quality. However, user controllability of the generated image, and fast adaptation to new tasks still remains an open challenge, currently mostly addressed by costly and long re-training and fine-tuning or ad-hoc adaptations to specific image generation tasks. In this work, we present MultiDiffusion, a unified framework that enables versatile and controllable image generation, using a pre-trained text-to-image diffusion model, without any further training or finetuning. At the center of our approach is a new generation process, based on an optimization task that binds together multiple diffusion generation processes with a shared set of parameters or constraints. We show that MultiDiffusion can be readily applied to generate high quality and diverse images that adhere to user-provided controls, such as desired aspect ratio (e.g., panorama), and spatial guiding signals, ranging from tight segmentation masks to bounding boxes.

We present a method for text-driven perpetual view generation -- synthesizing long-term videos of various scenes solely, given an input text prompt describing the scene and camera poses. We introduce a novel framework that generates such videos in an online fashion by combining the generative power of a pre-trained text-to-image model with the geometric priors learned by a pre-trained monocular depth prediction model. To tackle the pivotal challenge of achieving 3D consistency, i.e., synthesizing videos that depict geometrically-plausible scenes, we deploy an online test-time training to encourage the predicted depth map of the current frame to be geometrically consistent with the synthesized scene. The depth maps are used to construct a \emph{unified} mesh representation of the scene, which is progressively constructed along the video generation process. In contrast to previous works, which are applicable only to limited domains, our method generates diverse scenes, such as walkthroughs in spaceships, caves, or ice castles.

Current perceptual similarity metrics operate at the level of pixels and patches. These metrics compare images in terms of their low-level colors and textures, but fail to capture mid-level similarities and differences in image layout, object pose, and semantic content. In this paper, we develop a perceptual metric that assesses images holistically. Our first step is to collect a new dataset of human similarity judgments over image pairs that are alike in diverse ways. Critical to this dataset is that judgments are nearly automatic and shared by all observers. To achieve this we use recent text-to-image models to create synthetic pairs that are perturbed along various dimensions. We observe that popular perceptual metrics fall short of explaining our new data, and we introduce a new metric, DreamSim, tuned to better align with human perception. We analyze how our metric is affected by different visual attributes, and find that it focuses heavily on foreground objects and semantic content while also being sensitive to color and layout. Notably, despite being trained on synthetic data, our metric generalizes to real images, giving strong results on retrieval and reconstruction tasks. Furthermore, our metric outperforms both prior learned metrics and recent large vision models on these tasks. Our project page: https://dreamsim-nights.github.io/

We present a method for semantically transferring the visual appearance of one natural image to another. Specifically, our goal is to generate an image in which objects in a source structure image are “painted” with the visual appearance of their semantically related objects in a target appearance image. Our method works by training a generator given only a single structure/appearance image pair as input. To integrate semantic information into our framework—a pivotal component in tackling this task-our key idea is to leverage a pre-trained and fixed Vision Transformer (ViT) model which serves as an external semantic prior. Specifically, we derive novel representations of structure and appearance extracted from deep ViT features, untwisting them from the learned self-attention modules. We then establish an objective function that splices the desired structure and appearance representations, interweaving them together in the space of ViT features. Our framework, which we term “Splice”, does not involve adversarial training, nor does it require any additional input information such as semantic segmentation or correspondences, and can generate high resolution results, e.g., work in HD. We demonstrate high quality results on a variety of in-the-wild image pairs, under significant variations in the number of objects, their pose and appearance.

We explore a feed-forward approach for decomposing a video into layers, where each layer contains an object of interest along with its associated shadows, reflections, and other visual effects. This problem is challenging since associated effects vary widely with the 3D geometry and lighting conditions in the scene, and ground-truth labels for visual effects are difficult (and in some cases impractical) to collect. We take a self-supervised approach and train a neural network to produce a foreground image and alpha matte from a rough object segmentation mask under a reconstruction and sparsity loss. Under reconstruction loss, the layer decomposition problem is underdetermined: many combinations of layers may reconstruct the input video.Inspired by the game theory concept of focal points---or \emph{Schelling points}---we pose the problem as a coordination game, where each player (network) predicts the effects for a single object without knowledge of the other players' choices. The players learn to converge on the ``natural'' layer decomposition in order to maximize the likelihood of their choices aligning with the other players'. We train the network to play this game with itself, and show how to design the rules of this game so that the focal point lies at the correct layer decomposition. We demonstrate feed-forward results on a challenging synthetic dataset, then show that pretraining on this dataset significantly reduces optimization time for real videos.

Computer vision is increasingly effective at segmenting objects in images and videos; however, scene effects related to the objects—shadows, reflections, generated smoke, etc.—are typically overlooked. Identifying such scene effects and associating them with the objects producing them is important for improving our fundamental understanding of visual scenes, and can also assist a variety of applications such as removing, duplicating, or enhancing objects in video. In this work, we take a step towards solving this novel problem of automatically associating objects with their effects in video. Given an ordinary video and a rough segmentation mask over time of one or more subjects of interest, we estimate an omnimatte for each subject—an alpha matte and color image that includes the subject along with all its related time-varying scene elements. Our model is trained only on the input video in a self-supervised manner, without any manual labels, and is generic—it produces omnimattes automatically for arbitrary objects and a variety of effects. We show results on real-world videos containing interactions between different types of subjects (cars, animals, people) and complex effects, ranging from semitransparent elements such as smoke and reflections, to fully opaque effects such as objects attached to the subject.1

We present a method for predicting dense depth in scenarios where both a monocular camera and people in the scene are freely moving (right). Existing methods for recovering depth for dynamic, non-rigid objects from monocular video impose strong assumptions on the objects' motion and may only recover sparse depth. In this paper, we take a data-driven approach and learn human depth priors from a new source of data: thousands of Internet videos of people imitating mannequins, i.e., freezing in diverse, natural poses, while a hand-held camera tours the scene (left). Because people are stationary, geometric constraints hold, thus training data can be generated using multi-view stereo reconstruction. At inference time, our method uses motion parallax cues from the static areas of the scenes to guide the depth prediction. We evaluate our method on real-world sequences of complex human actions captured by a moving hand-held camera, show improvement over state-of-the-art monocular depth prediction methods, and demonstrate various 3D effects produced using our predicted depth.

We present a method that decomposes, and "unwraps", an input video into a set of layered 2D atlases , each providing a unified representation of the appearance of an object (or background) over the video. For each pixel in the video, our method estimates its corresponding 2D coordinate in each of the atlases, giving us a consistent parameterization of the video, along with an associated alpha (opacity) value. Importantly, we design our atlases to be interpretable and semantic, which facilitates easy and intuitive editing in the atlas domain, with minimal manual work required. Edits applied to a single 2D atlas (or input video frame) are automatically and consistently mapped back to the original video frames, while preserving occlusions, deformation, and other complex scene effects such as shadows and reflections. Our method employs a coordinate-based Multilayer Perceptron (MLP) representation for mappings, atlases, and alphas, which are jointly optimized on a per-video basis, using a combination of video reconstruction and regularization losses. By operating purely in 2D, our method does not require any prior 3D knowledge about scene geometry or camera poses, and can handle complex dynamic real world videos. We demonstrate various video editing applications, including texture mapping, video style transfer, image-to-video texture transfer, and segmentation/labeling propagation, all automatically produced by editing a single 2D atlas image.

We present a method to estimate depth of a dynamic scene, containing arbitrary moving objects, from an ordinary video captured with a moving camera. We seek a geometrically and temporally consistent solution to this under-constrained problem: the depth predictions of corresponding points across frames should induce plausible, smooth motion in 3D. We formulate this objective in a new test-time training framework where a depth-prediction CNN is trained in tandem with an auxiliary scene-flow prediction MLP over the entire input video. By recursively unrolling the scene-flow prediction MLP over varying time steps, we compute both short-range scene flow to impose local smooth motion priors directly in 3D, and long-range scene flow to impose multi-view consistency constraints with wide baselines. We demonstrate accurate and temporally coherent results on a variety of challenging videos containing diverse moving objects (pets, people, cars), as well as camera motion. Our depth maps give rise to a number of depth-and-motion aware video editing effects such as object and lighting insertion.

We wish to automatically predict the “speediness” of moving objects in videos - whether they move faster, at, or slower than their “natural” speed. The core component in our approach is SpeedNet - a novel deep network trained to detect if a video is playing at normal rate, or if it is sped up. SpeedNet is trained on a large corpus of natural videos in a self-supervised manner, without requiring any manual annotations. We show how this single, binary classification network can be used to detect arbitrary rates of speediness of objects. We demonstrate prediction results by SpeedNet on a wide range of videos containing complex natural motions, and examine the visual cues it utilizes for making those predictions. Importantly, we show that through predicting the speed of videos, the model learns a powerful and meaningful space-time representation that goes beyond simple motion cues. We demonstrate how those learned features can boost the performance of self supervised action recognition, and can be used for video retrieval. Furthermore, we also apply SpeedNet for generating time-varying, adaptive video speedups, which can allow viewers to watch videos faster, but with less of the jittery, unnatural motions typical to videos that are sped up uniformly.

We present a novel GAN-based model that utilizes the space of deep features learned by a pre-trained classification model. Inspired by classical image pyramid representations, we construct our model as a Semantic Generation Pyramid -- a hierarchical framework which leverages the continuum of semantic information encapsulated in such deep features; this ranges from low level information contained in fine features to high level, semantic information contained in deeper features. More specifically, given a set of features extracted from a reference image, our model generates diverse image samples, each with matching features at each semantic level of the classification model. We demonstrate that our model results in a versatile and flexible framework that can be used in various classic and novel image generation tasks. These include: generating images with a controllable extent of semantic similarity to a reference image, and different manipulation tasks such as semantically-controlled inpainting and compositing; all achieved with the same model, with no further training.

We present a method for retiming people in an ordinary, natural video --- manipulating and editing the time in which different motions of individuals in the video occur. We can temporally align different motions, change the speed of certain actions (speeding up/slowing down, or entirely "freezing" people), or "erase" selected people from the video altogether. We achieve these effects computationally via a dedicated learning-based layered video representation, where each frame in the video is decomposed into separate RGBA layers, representing the appearance of different people in the video. A key property of our model is that it not only disentangles the direct motions of each person in the input video, but also correlates each person automatically with the scene changes they generate---e.g., shadows, reflections, and motion of loose clothing. The layers can be individually retimed and recombined into a new video, allowing us to achieve realistic, high-quality renderings of retiming effects for real-world videos depicting complex actions and involving multiple individuals, including dancing, trampoline jumping, or group running.

We present a method for predicting dense depth in scenarios where both a monocular camera and people in the scene are freely moving. Existing methods for recovering depth for dynamic, non-rigid objects from monocular video impose strong assumptions on the objects’ motion and may only recover sparse depth. In this paper, we take a data-driven approach and learn human depth priors from a new source of data: thousands of Internet videos of people imitating mannequins, i.e., freezing in diverse, natural poses, while a hand-held camera tours the scene. Since the people are stationary, training data can be created from these videos using multi-view stereo reconstruction. At inference time, our method uses motion parallax cues from the static areas of the scenes, and shows clear improvement over state-of-the-art monocular depth prediction methods. We demonstrate our method on real-world sequences of complex human actions captured by a moving hand-held camera, and show various 3D effects produced using our predicted depth.

How much can we infer about a person’s looks from the way they speak? In this paper, we study the task of reconstructing a facial image of a person from a short audio recording of that person speaking. We design and train a deep neural network to perform this task using millions of natural Internet/Youtube videos of people speaking. During training, our model learns voice-face correlations that allow it to produce images that capture various physical attributes of the speakers such as age, gender and ethnicity. This is done in a self-supervised manner, by utilizing the natural co-occurrence of faces and speech in Internet videos, without the need to model attributes explicitly. We evaluate and numerically quantify how–-and in what manner–-our Speech2Face reconstructions, obtained directly from audio, resemble the true face images of the speakers.

We introduce SinGAN, an unconditional generative model that can be learned from a single natural image. Our model is trained to capture the internal distribution of patches within the image, and is then able to generate high quality, diverse samples that carry the same visual content as the image. SinGAN contains a pyramid of fully convolutional GANs, each responsible for learning the patch distribution at a different scale of the image. This allows generating new samples of arbitrary size and aspect ratio, that have significant variability, yet maintain both the global structure and the fine textures of the training image. In contrast to previous single image GAN schemes, our approach is not limited to texture images, and is not conditional (i.e. it generates samples from noise). User studies confirm that the generated samples are commonly confused to be real images. We illustrate the utility of SinGAN in a wide range of image manipulation tasks.

We study the problem of reconstructing an image from information stored at contour locations. We show that high-quality reconstructions with high fidelity to the source image can be obtained from sparse input, e.g., comprising less than 6% of image pixels. This is a significant improvement over existing contour-based reconstruction methods that require much denser input to capture subtle texture information and to ensure image quality. Our model, based on generative adversarial networks, synthesizes texture and details in regions where no input information is provided. The semantic knowledge encoded into our model and the sparsity of the input allows to use contours as an intuitive interface for semantically-aware image manipulation: local edits in contour domain translate to long-range and coherent changes in pixel space. We can perform complex structural changes such as changing facial expression by simple edits of contours. Our experiments demonstrate that humans as well as a face recognition system mostly cannot distinguish between our reconstructions and the source images.

We present an algorithm for modifying small non-local variations between repeating structures and patterns in multiple images of the same scene. The modification is consistent across views, even-though the images could have been photographed from different view points and under different lighting conditions. We show that when modifying each image independently the correspondence between them breaks and the geometric structure of the scene gets distorted. Our approach modifies the views while maintaining correspondence, hence, we succeed in modifying appearance and structure variations consistently. We demonstrate our methods on a number of challenging examples, photographed in different lighting, scales and view points.

We present a system that visualizes complex human motion via 3D motion sculptures-a representation that conveys the 3D structure swept by a human body as it moves through space. Our system computes a motion sculpture from an input video, and then embeds it back into the scene in a 3D-aware fashion. The user may also explore the sculpture directly in 3D or physically print it. Our interactive interface allows users to customize the sculpture design, for example, by selecting materials and lighting conditions. To provide this end-to-end workflow, we introduce an algorithm that estimates a human's 3D geometry over time from a set of 2D images, and develop a 3D-aware image-based rendering approach that inserts the sculpture back into the original video. By automating the process, our system takes motion sculpture creation out of the realm of professional artists, and makes it applicable to a wide range of existing video material. By conveying 3D information to users, motion sculptures reveal space-time motion information that is difficult to perceive with the naked eye, and allow viewers to interpret how different parts of the object interact over time. We validate the effectiveness of motion sculptures with user studies, finding that our visualizations are more informative about motion than existing stroboscopic and space-time visualization methods.

We propose a novel method for template matching in unconstrained environments. Its essence is the Best-Buddies Similarity (BBS), a useful, robust, and parameter-free similarity measure between two sets of points. BBS is based on counting the number of Best-Buddies Pairs (BBPs)-pairs of points in source and target sets that are mutual nearest neighbours, i.e., each point is the nearest neighbour of the other. BBS has several key features that make it robust against complex geometric deformations and high levels of outliers, such as those arising from background clutter and occlusions. We study these properties, provide a statistical analysis that justifies them, and demonstrate the consistent success of BBS on a challenging real-world dataset while using different types of features.

We present a joint audio-visual model for isolating a single speech signal from a mixture of sounds such as other speakers and background noise. Solving this task using only audio as input is extremely challenging and does not provide an association of the separated speech signals with speakers in the video. In this paper, we present a deep network-based model that incorporates both visual and auditory signals to solve this task. The visual features are used to "focus" the audio on desired speakers in a scene and to improve the speech separation quality. To train our joint audio-visual model, we introduce AVS peech , a new dataset comprised of thousands of hours of video segments from the Web. We demonstrate the applicability of our method to classic speech separation tasks, as well as real-world scenarios involving heated interviews, noisy bars, and screaming children, only requiring the user to specify the face of the person in the video whose speech they want to isolate. Our method shows clear advantage over state-of-the-art audio-only speech separation in cases of mixed speech. In addition, our model, which is speaker-independent (trained once, applicable to any speaker), produces better results than recent audio-visual speech separation methods that are speaker-dependent (require training a separate model for each speaker of interest).

Visible watermarking is a widely-used technique for marking and protecting copyrights of many millions of images on the web, yet it suffers from an inherent security flaw-watermarks are typically added in a consistent manner to many images. We show that this consistency allows to automatically estimate the watermark and recover the original images with high accuracy. Specifically, we present a generalized multi-image matting algorithm that takes a watermarked image collection as input and automatically estimates the foreground (watermark), its alpha matte, and the background (original) images. Since such an attack relies on the consistency of watermarks across image collection, we explore and evaluate how it is affected by various types of inconsistencies in the watermark embedding that could potentially be used to make watermarking more secured. We demonstrate the algorithm on stock imagery available on the web, and provide extensive quantitative analysis on synthetic watermarked data. A key takeaway message of this paper is that visible watermarks should be designed to not only be robust against removal from a single image, but to be more resistant to mass-scale removal from image collections as well.

We propose a novel method for template matching in unconstrained environments. Its essence is the Best-Buddies Similarity (BBS), a useful, robust, and parameter-free similarity measure between two sets of points. BBS is based on counting the number of Best-Buddies Pairs (BBPs)-pairs of points in source and target sets, where each point is the nearest neighbor of the other. BBS has several key features that make it robust against complex geometric deformations and high levels of outliers, such as those arising from background clutter and occlusions. We study these properties, provide a statistical analysis that justifies them, and demonstrate the consistent success of BBS on a challenging real-world dataset.

We present an algorithm for automatically detecting and visualizing small non-local variations between repeating structures in a single image. Our method allows to automatically correct these variations, thus producing an 'idealized' version of the image in which the resemblance between recurring structures is stronger. Alternatively, it can be used to magnify these variations, thus producing an exaggerated image which highlights the various variations that are difficult to spot in the input image. We formulate the estimation of deviations from perfect recurrence as a general optimization problem, and demonstrate it in the particular cases of geometric deformations and color variations.

Structures and objects are often supposed to have idealized geometries such as straight lines or circles. Although not always visible to the naked eye, in reality, these objects deviate from their idealized models. Our goal is to reveal and visualize such subtle geometric deviations, which can contain useful, surprising information about our world. Our framework, termed Deviation Magnification , takes a still image as input, fits parametric models to objects of interest, computes the geometric deviations, and renders an output image in which the departures from ideal geometries are exaggerated. We demonstrate the correctness and usefulness of our method through quantitative evaluation on a synthetic dataset and by application to challenging natural images.

Photo-sequencing is the problem of recovering the temporal order of a set of still images of a dynamic event, taken asynchronously by a set of uncalibrated cameras. Solving this problem is a first, crucial step for analyzing (or visualizing) the dynamic content of the scene captured by a large number of freely moving spectators. We propose a geometric based solution, followed by rank aggregation to the photo-sequencing problem. Our algorithm trades spatial certainty for temporal certainty. Whereas the previous solution proposed by [4] relies on two images taken from the same static camera to eliminate uncertainty in space, we drop the static-camera assumption and replace it with temporal information available from images taken from the same (moving) camera. Our method thus overcomes the limitation of the static-camera assumption, and scales much better with the duration of the event and the spread of cameras in space. We present successful results on challenging real data sets and large scale synthetic data (250 images).

Image retargeting algorithms attempt to adapt the image content to the screen without distorting the important objects in the scene. Existing methods address retargeting of a single image. In this paper, we propose a novel method for retargeting a pair of stereo images. Naively retargeting each image independently will distort the geometric structure and hence will impair the perception of the 3D structure of the scene. We show how to extend a single image seam carving to work on a pair of images. Our method minimizes the visual distortion in each of the images as well as the depth distortion. A key property of the proposed method is that it takes into account the visibility relations between pixels in the image pair (occluded and occluding pixels). As a result, our method guarantees, as we formally prove, that the retargeted pair is geometrically consistent with a feasible 3D scene, similar to the original one. Hence, the retargeted stereo pair can be viewed on a stereoscopic display or further processed by any computer vision algorithm. We demonstrate our method on a number of challenging indoor and outdoor stereo images.

We propose a method for estimating the 3D structure and the dense 3D motion (scene flow) of a dynamic nonrigid 3D scene, using a camera array. The core idea is to use a dense multi-camera array to construct a novel, dense 3D volumetric representation of the 3D space where each voxel holds an estimated intensity value and a confidence measure of this value. The problem of 3D structure and 3D motion estimation of a scene is thus reduced to a nonrigid registration of two volumes - hence the term ”Scene Registration”. Registering two dense 3D scalar volumes does not require recovering the 3D structure of the scene as a preprocessing step, nor does it require explicit reasoning about occlusions. From this nonrigid registration we accurately extract the 3D scene flow and the 3D structure of the scene, and successfully recover the sharp discontinuities in both time and space. We demonstrate the advantages of our method on a number of challenging synthetic and real data sets.

Image retargeting algorithms attempt to adapt the image content to the screen without distorting the important objects in the scene. Existing methods address retargeting of a single image. In this paper we propose a novel method for retargeting a pair of stereo images. Naively retargeting each image independently will distort the geometric structure and make it impossible to perceive the 3D structure of the scene. We show how to extend a single image seam carving to work on a pair of images. Our method minimizes the visual distortion in each of the images as well as the depth distortion. A key property of the proposed method is that it takes into account the visibility relations between pixels in the image pair (occluded and occluding pixels). As a result, our method guarantees, as we formally prove, that the retargeted pair is geometrically consistent with a feasible 3D scene, similar to the original one. Hence, the retargeted stereo pair can be viewed on a stereoscopic display or processed by any computer vision algorithm. We demonstrate our method on a number of challenging indoor and outdoor stereo images.

We present a novel method for recovering the 3D structure and scene flow from calibrated multi-view sequences. We propose a 3D point cloud parametrization of the 3D structure and scene flow that allows us to directly estimate the desired unknowns. A unified global energy functional is proposed to incorporate the information from the available sequences and simultaneously recover both depth and scene flow. The functional enforces multi-view geometric consistency and imposes brightness constancy and piece-wise smoothness assumptions directly on the 3D unknowns. It inherently handles the challenges of discontinuities, occlusions, and large displacements. The main contribution of this work is the fusion of a 3D representation and an advanced variational framework that directly uses the available multi-view information. The minimization of the functional is successfully obtained despite the non-convex optimization problem. The proposed method was tested on real and synthetic data.