Text-to-image generation has recently seen remarkable success, granting users with the ability to create high-quality images through the use of text. However, contemporary methods face challenges in capturing the precise semantics conveyed by complex multi-object prompts. Consequently, many works have sought to mitigate such semantic mis-alignments, typically via inference-time schemes that modify the attention layers of the denoising networks. However, prior work has mostly utilized coarse metrics, such as the cosine similarity between text and image CLIP embeddings, or human evaluations, which are challenging to conduct on a larger-scale. In this work, we perform a case study on colors—a fundamental attribute commonly associated with objects in text prompts, which offer a rich test bed for rigorous evaluation. Our analysis reveals that pretrained models struggle to generate images that faithfully reflect multiple color attributes—far more so than with single-color prompts—and that neither inference-time techniques nor existing editing methods reliably resolve these semantic misalignments. Accordingly, we introduce a dedicated image editing technique, mitigating the issue of multi-object semantic alignment for prompts containing multiple colors. We demonstrate that our approach significantly boosts performance over a wide range of metrics, considering images generated by various text-to-image diffusion-based techniques. Our code, benchmark and evaluation protocol is publicly available on our project webpage.

We present a technique and benchmark dataset for estimating the relative 3D orientation between a pair of Internet images captured in an extreme setting, where the images have limited or non-overlapping field of views. Prior work targeting extreme rotation estimation assume constrained 3D environments and emulate perspective images by cropping regions from panoramic views. However, real images captured in the wild are highly diverse, exhibiting variation in both appearance and camera intrinsics. In this work, we propose a Transformer-based method for estimating relative rotations in extreme real-world settings, and contribute the ExtremeLandmarkPairs dataset, assembled from scene-level Internet photo collections. Our evaluation demonstrates that our approach succeeds in estimating the relative rotations in a wide variety of extreme-view Internet image pairs, outperforming various baselines, including dedicated rotation estimation techniques and contemporary 3D reconstruction methods.

Natural language offers a highly intuitive interface for enabling localized fine-grained edits of 3D shapes. However, prior works face challenges in preserving global coherence while locally modifying the input 3D shape. In this work, we introduce an inpainting-based framework for editing shapes represented as point clouds. Our approach leverages foundation 3D diffusion models for achieving localized shape edits, adding structural guidance in the form of a partial conditional shape, ensuring that other regions correctly preserve the shape's identity. Furthermore, to encourage identity preservation also within the local edited region, we propose an inference-time coordinate blending algorithm which balances reconstruction of the full shape with inpainting at a progression of noise levels during the inference process. Our coordinate blending algorithm seamlessly blends the original shape with its edited version, enabling a fine-grained editing of 3D shapes, all while circumventing the need for computationally expensive and often inaccurate inversion. Extensive experiments show that our method outperforms alternative techniques across a wide range of metrics that evaluate both fidelity to the original shape and also adherence to the textual description.

The cuneiform writing system served as the medium for transmitting knowledge in the ancient Near East for a period of over three thousand years. Cuneiform signs have a complex internal structure which is the subject of expert paleographic analysis, as variations in sign shapes bear witness to historical developments and transmission of writing and culture over time. However, prior automated techniques mostly treat sign types as categorical and do not explicitly model their highly varied internal configurations. In this work, we present an unsupervised approach for recovering the fine-grained internal configuration of cuneiform signs by leveraging powerful generative models and the appearance and structure of prototype font images as priors. Our approach, ProtoSnap, enforces structural consistency on matches found with deep image features to estimate the diverse configurations of cuneiform characters, snapping a skeleton-based template to photographed cuneiform signs. We provide a new benchmark of expert annotations and evaluate our method on this task. Our evaluation shows that our approach succeeds in aligning prototype skeletons to a wide variety of cuneiform signs. Moreover, we show that conditioning on structures produced by our method allows for generating synthetic data with correct structural configurations, significantly boosting the performance of cuneiform sign recognition beyond existing techniques, in particular over rare signs. Our code, data, and trained models are available at the project page: https://tau-vailab.github.io/ProtoSnap/

Despite recent advances in sparse novel view synthesis (NVS) applied to object-centric scenes, scene-level NVS remains a challenge. A central issue is the lack of available clean multi-view training data, beyond manually curated datasets with limited diversity, camera variation, or licensing issues. On the other hand, an abundance of diverse and permissively-licensed data exists in the wild, consisting of scenes with varying appearances (illuminations, transient occlusions, etc.) from sources such as tourist photos. To this end, we present WildCAT3D, a framework for generating novel views of scenes learned from diverse 2D scene image data cap tured in the wild. We unlock training on these data sources by explicitly modeling global appearance conditions in images, extending the state-of-the-art multi-view diffusion paradigm to learn from scene views of varying appearances. Our trained model generalizes to new scenes at inference time, enabling the generation of multiple consistent novel views. WildCAT3D provides state-of-the-art results on single-view NVS in object- and scene-level settings, while training on strictly fewer data sources than prior methods. Additionally, it enables novel applications by providing global appearance control during generation.

Embedding a language field in a 3D representation enables richer semantic understanding of spatial environments by linking geometry with descriptive meaning. This allows for a more intuitive human-computer interaction, enabling querying or editing scenes using natural language, and could potentially improve tasks like scene retrieval, navigation, and multimodal reasoning. While such capabilities could be transformative, in particular for large-scale scenes, we find that recent feature distillation approaches cannot effectively learn over massive Internet data due to challenges in semantic feature misalignment and inefficiency in memory and runtime. To this end, we propose a novel approach to address these challenges. First, we introduce extremely low-dimensional semantic bottleneck features as part of the underlying 3D Gaussian representation. These are processed by rendering and passing them through a multi-resolution, feature-based, hash encoder. This significantly improves efficiency both in runtime and GPU memory. Second, we introduce an Attenuated Downsampler module and propose several regularizations addressing the semantic misalignment of ground truth 2D features. We evaluate our method on the in-the-wild HolyScenes dataset and demonstrate that it surpasses existing approaches in both performance and efficiency.

Buildings are a central feature of human culture and require significant work to design, build, and maintain. As such, the fundamental element defining their structure - the floorplan - has increasingly become an object of computational analysis. Existing works on automatic floorplan understanding are extremely limited in scope, often focusing on a single semantic category and region (e.g. apartments from a single country). This contrasts with the wide vari-ety of shapes and sizes of real-world buildings which reflect their diverse purposes. In this work, we introduce WAF-FLE, a novel multimodal floorplan understanding dataset of nearly 20K floorplan images and metadata curatedfrom In-ternet data spanning diverse building types, locations, and data formats. By using a large language model and multimodal foundation models, we curate and extract semantic information from these images and their accompanying noisy metadata. We show that WAFFLE serves as a challenging benchmark for prior computational methods, while enabling progress on new floorplan understanding tasks. We will publicly release WAFFLE along with our code and trained models, providing the research community with a new foundation for learning the semantics of buildings.

Abstract The emergence of neural representations has revolutionized our means for digitally viewing a wide range of 3D scenes, enabling the synthesis of photorealistic images rendered from novel views. Recently, several techniques have been proposed for connecting these low‐level representations with the high‐level semantics understanding embodied within the scene. These methods elevate the rich semantic understanding from 2D imagery to 3D representations, distilling high‐dimensional spatial features onto 3D space. In our work, we are interested in connecting language with a dynamic modeling of the world. We show how to lift spatio‐temporal features to a 4D representation based on 3D Gaussian Splatting. This enables an interactive interface where the user can spatiotemporally localize events in the video from text prompts. We demonstrate our system on public 3D video datasets of people and animals performing various actions.

While recent years have seen rapid progress in image-conditioned text generation, image captioning still suffers from the fundamental issue of hallucinations, namely, the generation of spurious details that cannot be inferred from the given image.Existing methods largely use closed-vocabulary object lists to mitigate or evaluate hallucinations in image captioning, ignoring the long-tailed nature of hallucinations that occur in practice.To this end, we propose a framework for addressing hallucinations in image captioning in the open-vocabulary setting.Our framework includes a new benchmark, OpenCHAIR, that leverages generative foundation models to evaluate open-vocabulary object hallucinations for image captioning, surpassing the popular and similarly-sized CHAIR benchmark in both diversity and accuracy.Furthermore, to mitigate open-vocabulary hallucinations without using a closed object list, we propose MOCHa, an approach harnessing advancements in reinforcement learning.Our multi-objective reward function explicitly targets the trade-off between fidelity and adequacy in generations without requiring any strong supervision.MOCHa improves a large variety of image captioning models, as captured by our OpenCHAIR benchmark and other existing metrics.Code and models can be found in:

Abstract Internet image collections containing photos captured by crowds of photographers show promise for enabling digital exploration of large‐scale tourist landmarks. However, prior works focus primarily on geometric reconstruction and visualization, neglecting the key role of language in providing a semantic interface for navigation and fine‐grained understanding. In more constrained 3D domains, recent methods have leveraged modern vision‐and‐language models as a strong prior of 2D visual semantics. While these models display an excellent understanding of broad visual semantics, they struggle with unconstrained photo collections depicting such tourist landmarks, as they lack expert knowledge of the architectural domain and fail to exploit the geometric consistency of images capturing multiple views of such scenes. In this work, we present a localization system that connects neural representations of scenes depicting large‐scale landmarks with text describing a semantic region within the scene, by harnessing the power of SOTA vision‐and‐language models with adaptations for understanding landmark scene semantics. To bolster such models with fine‐grained knowledge, we leverage large‐scale Internet data containing images of similar landmarks along with weakly‐related textual information. Our approach is built upon the premise that images physically grounded in space can provide a powerful supervision signal for localizing new concepts, whose semantics may be unlocked from Internet textual metadata with large language models. We use correspondences between views of scenes to bootstrap spatial understanding of these semantics, providing guidance for 3D‐compatible segmentation that ultimately lifts to a volumetric scene representation. To evaluate our method, we present a new benchmark dataset containing large‐scale scenes with ground‐truth segmentations for multiple semantic concepts. Our results show that HaLo‐NeRF can accurately localize a variety of semantic concepts related to architectural landmarks, surpassing the results of other 3D models as well as strong 2D segmentation baselines. Our code and data are publicly available at https://tau‐vailab.github.io/HaLo‐NeRF/ .

Most humans use visual imagination to understand and reason about language, but models such as BERT reason about language using knowledge acquired during text-only pretraining. In this work, we investigate whether vision-and-language pretraining can improve performance on text-only tasks that involve implicit visual reasoning, focusing primarily on zero-shot probing methods. We propose a suite of visual language understanding (VLU) tasks for probing the visual reasoning abilities of text encoder models, as well as various non-visual natural language understanding (NLU) tasks for comparison. We also contribute a novel zero-shot knowledge probing method, Stroop probing, for applying models such as CLIP to text-only tasks without needing a prediction head such as the masked language modelling head of models like BERT. We show that SOTA multimodally trained text encoders outperform unimodally trained text encoders on the VLU tasks while being under-performed by them on the NLU tasks, lending new context to previously mixed results regarding the NLU capabilities of multimodal models. We conclude that exposure to images during pretraining affords inherent visual reasoning knowledge that is reflected in language-only tasks that require implicit visual reasoning. Our findings bear importance in the broader context of multimodal learning, providing principled guidelines for the choice of text encoders used in such contexts11Our code will be made available at https://isbertblind.github.io/.

In this work, we aim to reconstruct a time-varying 3D model, capable of rendering photo-realistic renderings with independent control of viewpoint, illumination, and time, from Internet photos of large-scale landmarks. The core challenges are twofold. First, different types of temporal changes, such as illumination and changes to the underlying scene itself (such as replacing one graffiti artwork with another) are entangled together in the imagery. Second, scene-level temporal changes are often discrete and sporadic over time, rather than continuous. To tackle these problems, we propose a new scene representation equipped with a novel temporal step function encoding method that can model discrete scene-level content changes as piece-wise constant functions over time. Specifically, we represent the scene as a space-time radiance field with a per-image illumination embedding, where temporally-varying scene changes are encoded using a set of learned step functions. To facilitate our task of chronology reconstruction from Internet imagery, we also collect a new dataset of four scenes that exhibit various changes over time. We demonstrate that our method exhibits state-of-the-art view synthesis results on this dataset, while achieving independent control of view-point, time, and illumination. Code and data are available at https://zju3dv.github.io/NeuSC/

Interactions between humans are diverse and context-dependent, but previous works have treated them as categorical, disregarding the heavy tail of possible interactions. We propose a new paradigm of learning human-human interactions as free text from a single still image, allowing for flexibility in modeling the unlimited space of situations and relationships between people. To overcome the absence of data labelled specifically for this task, we use knowledge distillation applied to synthetic caption data produced by a large language model without explicit supervision. We show that the pseudo-labels produced by this procedure can be used to train a captioning model to effectively understand human-human interactions in images, as measured by a variety of metrics that measure textual and semantic faithfulness and factual groundedness of our predictions. We further show that our approach outperforms SOTA image captioning and situation recognition models on this task. We will releas1our code and pseudo-labels along with Waldo and Wenda, a manually-curated test set for still image human-human interaction understanding.

We consider the visual disambiguation task of determining whether a pair of visually similar images depict the same or distinct 3D surfaces (e.g., the same or opposite sides of a symmetric building). Illusory image matches, where two images observe distinct but visually similar 3D surfaces, can be challenging for humans to differentiate, and can also lead 3D reconstruction algorithms to produce erroneous results. We propose a learning-based approach to visual disambiguation, formulating it as a binary classification task on image pairs. To that end, we introduce a new dataset for this problem, Doppelgangers, which includes image pairs of similar structures with ground truth labels. We also design a network architecture that takes the spatial distribution of local keypoints and matches as input, allowing for better reasoning about both local and global cues. Our evaluation shows that our method can distinguish illusory matches in difficult cases, and can be integrated into SfM pipelines to produce correct, disambiguated 3D reconstructions. See our project page for our code, datasets, and more results: doppelgangers-3d.github.io.

Text-to-image models give rise to workflows which often begin with an exploration step, where users sift through a large collection of generated images. The global nature of the text-to-image generation process prevents users from narrowing their exploration to a particular object in the image. In this paper, we present a technique to generate a collection of images that depicts variations in the shape of a specific object, enabling an object-level shape exploration process. Creating plausible variations is challenging as it requires control over the shape of the generated object while respecting its semantics. A particular challenge when generating object variations is accurately localizing the manipulation applied over the object’s shape. We introduce a prompt-mixing technique that switches between prompts along the denoising process to attain a variety of shape choices. To localize the image-space operation, we present two techniques that use the self-attention layers in conjunction with the cross-attention layers. Moreover, we show that these localization techniques are general and effective beyond the scope of generating object variations. Extensive results and comparisons demonstrate the effectiveness of our method in generating object variations, and the competence of our localization techniques.

Large scale text-guided diffusion models have garnered significant attention due to their ability to synthesize diverse images that convey complex visual concepts. This generative power has more recently been leveraged to perform text-to-3D synthesis. In this work, we present a technique that harnesses the power of latent diffusion models for editing existing 3D objects. Our method takes oriented 2D images of a 3D object as input and learns a grid-based volumetric representation of it. To guide the volumetric representation to conform to a target text prompt, we follow unconditional text-to-3D methods and optimize a Score Distillation Sampling (SDS) loss. However, we observe that combining this diffusion-guided loss with an image-based regularization loss that encourages the representation not to deviate too strongly from the input object is challenging, as it requires achieving two conflicting goals while viewing only structure-and-appearance coupled 2D projections. Thus, we introduce a novel volumetric regularization loss that operates directly in 3D space, utilizing the explicit nature of our 3D representation to enforce correlation between the global structure of the original and edited object. Furthermore, we present a technique that optimizes cross-attention volumetric grids to refine the spatial extent of the edits. Extensive experiments and comparisons demonstrate the effectiveness of our approach in creating a myriad of edits which cannot be achieved by prior works1.

Although the mapping between sound and meaning in human language is assumed to be largely arbitrary, research in cognitive science has shown that there are non-trivial correlations between particular sounds and meanings across languages and demographic groups, a phenomenon known as sound symbolism. Among the many dimensions of meaning, sound symbolism is particularly salient and well-demonstrated with regards to cross-modal associations between language and the visual domain. In this work, we address the question of whether sound symbolism is reflected in vision-and-language models such as CLIP and Stable Diffusion. Using zero-shot knowledge probing to investigate the inherent knowledge of these models, we find strong evidence that they do show this pattern, paralleling the well-known kiki-bouba effect in psycholinguistics. Our work provides a novel method for demonstrating sound symbolism and understanding its nature using computational tools. Our code will be made publicly available.

Abstract How can one visually characterize photographs of people over time? In this work, we describe theFaces Through Timedataset, which contains over a thousand portrait images per decade from the 1880s to the present day. Using our new dataset, we devise a framework for resynthesizing portrait images across time, imagining how a portrait taken during a particular decade might have looked like had it been taken in other decades. Our framework optimizes a family of per‐decade generators that reveal subtle changes that differentiate decades—such as different hairstyles or makeup—while maintaining the identity of the input portrait. Experiments show that our method can more effectively resynthesizing portraits across time compared to state‐of‐the‐art image‐to‐image translation methods, as well as attribute‐based and language‐guided portrait editing models. Our code and data will be available at facesthroughtime.github.io.

As image generation techniques mature, there is a growing interest in explainable representations that are easy to understand and intuitive to manipulate. In this work, we turn to co-occurrence statistics, which have long been used for texture analysis, to learn a controllable texture synthesis model. We propose a fully convolutional generative adversarial network, conditioned locally on co-occurrence statistics, to generate arbitrarily large images while having local, interpretable control over texture appearance. To encourage fidelity to the input condition, we introduce a novel differentiable co-occurrence loss that is integrated seamlessly into our framework in an end-to-end fashion. We demonstrate that our solution offers a stable, intuitive, and interpretable latent representation for texture synthesis, which can be used to generate smooth texture morphs between different textures. We further show an interactive texture tool that allows a user to adjust local characteristics of the synthesized texture by directly using the co-occurrence values.

We present a technique for estimating the relative 3D rotation of an RGB image pair in an extreme setting, where the images have little or no overlap. We observe that, even when images do not overlap, there may be rich hidden cues as to their geometric relationship, such as light source directions, vanishing points, and symmetries present in the scene. We propose a network design that can automatically learn such implicit cues by comparing all pairs of points between the two input images. Our method therefore constructs dense feature correlation volumes and processes these to predict relative 3D rotations. Our predictions are formed over a fine-grained discretization of rotations, bypassing difficulties associated with regressing 3D rotations. We demonstrate our approach on a large variety of extreme RGB image pairs, including indoor and outdoor images captured under different lighting conditions and geographic locations. Our evaluation shows that our model can successfully estimate relative rotations among non-overlapping images without compromising performance over overlapping image pairs.1

We present a task and benchmark dataset for person-centric visual grounding, the problem of linking between people named in a caption and people pictured in an image. In contrast to prior work in visual grounding, which is predominantly object-based, our new task masks out the names of people in captions in order to encourage methods trained on such image–caption pairs to focus on contextual cues, such as the rich interactions between multiple people, rather than learning associations between names and appearances. To facilitate this task, we introduce a new dataset, Who’s Waldo, mined automatically from image–caption data on Wikimedia Commons. We propose a Transformer-based method that outperforms several strong baselines on this task, and release our data to the research community to spur work on contextual models that consider both vision and language. Code and data are available at: https://whoswaldo.github.io

The abundance and richness of Internet photos of landmarks and cities has led to significant progress in 3D vision over the past two decades, including automated 3D reconstructions of the world’s landmarks from tourist photos. However, a major source of information available for these 3D-augmented collections—namely language, e.g., from image captions—has been virtually untapped. In this work, we present WikiScenes, a new, large-scale dataset of landmark photo collections that contains descriptive text in the form of captions and hierarchical category names. WikiScenes forms a new testbed for multimodal reasoning involving images, text, and 3D geometry. We demonstrate the utility of WikiScenes for learning semantic concepts over images and 3D models. Our weakly-supervised framework connects images, 3D structure, and semantics—utilizing the strong constraints provided by 3D geometry—to associate semantic concepts to image pixels and 3D points.1

Nowadays, as cameras are rapidly adopted in our daily routine, images of documents are becoming both abundant and prevalent. Unlike natural images that capture physical objects, document-images contain a significant amount of text with critical semantics and complicated layouts. In this work, we devise a generic unsupervised technique to learn multimodal affinities between textual entities in a document-image, considering their visual style, the content of their underlying text, and their geometric context within the image. We then use these learned affinities to automatically cluster the textual entities in the image into different semantic groups. The core of our approach is a deep optimization scheme dedicated for an image provided by the user that detects and leverages reliable pairwise connections in the multimodal representation of the textual elements to properly learn the affinities. We show that our technique can operate on highly varying images spanning a wide range of documents and demonstrate its applicability for various editing operations manipulating the content, appearance, and geometry of the image.

Visual features are a promising signal for learning bootstrap textual models.However, blackbox learning models make it difficult to isolate the specific contribution of visual components.In this analysis, we consider the case study of the Visually Grounded Neural Syntax Learner (Shi et al., 2019), a recent approach for learning syntax from a visual training signal.By constructing simplified versions of the model, we isolate the core factors that yield the model's strong performance.Contrary to what the model might be capable of learning, we find significantly less expressive versions produce similar predictions and perform just as well, or even better.We also find that a simple lexical signal of noun concreteness plays the main role in the model's predictions as opposed to more complex syntactic reasoning.

Optical character recognition (OCR) systems performance have improved significantly in the deep learning era. This is especially true for handwritten text recognition (HTR), where each author has a unique style, unlike printed text, where the variation is smaller by design. That said, deep learning based HTR is limited, as in every other task, by the number of training examples. Gathering data is a challenging and costly task, and even more so, the labeling task that follows, of which we focus here. One possible approach to reduce the burden of data annotation is semi-supervised learning. Semi supervised methods use, in addition to labeled data, some unlabeled samples to improve performance, compared to fully supervised ones. Consequently, such methods may adapt to unseen images during test time. We present ScrabbleGAN, a semi-supervised approach to synthesize handwritten text images that are versatile both in style and lexicon. ScrabbleGAN relies on a novel generative model which can generate images of words with an arbitrary length. We show how to operate our approach in a semi-supervised manner, enjoying the aforementioned benefits such as performance boost over state of the art supervised HTR. Furthermore, our generator can manipulate the resulting text style. This allows us to change, for instance, whether the text is cursive, or how thin is the pen stroke.

We are seeing a Cambrian explosion of 3D shape representations for use in machine learning. Some representations seek high expressive power in capturing high-resolution detail. Other approaches seek to represent shapes as compositions of simple parts, which are intuitive for people to understand and easy to edit and manipulate. However, it is difficult to achieve both fidelity and interpretability in the same representation. We propose DualSDF, a representation expressing shapes at two levels of granularity, one capturing fine details and the other representing an abstracted proxy shape using simple and semantically consistent shape primitives. To achieve a tight coupling between the two representations, we use a variational objective over a shared latent space. Our two-level model gives rise to a new shape manipulation technique in which a user can interactively manipulate the coarse proxy shape and see the changes instantly mirrored in the high-resolution shape. Moreover, our model actively augments and guides the manipulation towards producing semantically meaningful shapes, making complex manipulations possible with minimal user input.

In this paper, we present a novel non-parametric clustering technique. Our technique is based on the notion that each latent cluster is comprised of layers that surround its core, where the external layers, or border points, implicitly separate the clusters. Unlike previous techniques, such as DBSCAN, where the cores of the clusters are defined directly by their densities, here the latent cores are revealed by a progressive peeling of the border points. Analyzing the density of the local neighborhoods allows identifying the border points and associating them with points of inner layers. We show that the peeling process adapts to the local densities and characteristics to successfully separate adjacent clusters (of possibly different densities). We extensively tested our technique on large sets of labeled data, including high-dimensional datasets of deep features that were trained by a convolutional neural network. We show that our technique is competitive to other state-of-the-art non-parametric methods using a fixed set of parameters throughout the experiments.

In image-to-image translation the goal is to learn a mapping from one image domain to another. In the case of supervised approaches the mapping is learned from paired samples. However, collecting large sets of image pairs is often either prohibitively expensive or not possible. As a result, in recent years more attention has been given to techniques that learn the mapping from unpaired sets. In our work, we show that injecting implicit pairs into unpaired sets strengthens the mapping between the two domains, improves the compatibility of their distributions, and leads to performance boosting of unsupervised techniques by up to 12% across several measurements. The competence of the implicit pairs is further displayed with the use of pseudo-pairs, i.e., paired samples which only approximate a real pair. We demonstrate the effect of the approximated implicit samples on image-to-image translation problems, where such pseudo-pairs may be synthesized in one direction, but not in the other. We further show that pseudo-pairs are significantly more effective as implicit pairs in an unpaired setting, than directly using them explicitly in a paired setting.

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.

We present a technique to automatically animate a still portrait, making it possible for the subject in the photo to come to life and express various emotions. We use a driving video (of a different subject) and develop means to transfer the expressiveness of the subject in the driving video to the target portrait. In contrast to previous work that requires an input video of the target face to reenact a facial performance, our technique uses only a single target image. We animate the target image through 2D warps that imitate the facial transformations in the driving video. As warps alone do not carry the full expressiveness of the face, we add fine-scale dynamic details which are commonly associated with facial expressions such as creases and wrinkles. Furthermore, we hallucinate regions that are hidden in the input target face, most notably in the inner mouth. Our technique gives rise to reactive profiles , where people in still images can automatically interact with their viewers. We demonstrate our technique operating on numerous still portraits from the internet.

Abstract Smoothness is a quality that feels aesthetic and pleasing to the human eye. We present an algorithm for finding “as‐smooth‐as‐possible” sequences in image collections. In contrast to previous work, our method does not assume that the images show a common 3D scene, but instead may depict different object instances with varying deformations, and significant variation in lighting, texture, and color appearance. Our algorithm does not rely on a notion of camera pose, view direction, or 3D representation of an underlying scene, but instead directly optimizes the smoothness of the apparent motion of local point matches among the collection images. We increase the smoothness of our sequences by performing a global similarity transform alignment, as well as localized geometric wobble reduction and appearance stabilization. Our technique gives rise to a new kind of image morphing algorithm, in which the in‐between motion is derived in a data‐driven manner from a smooth sequence of real images without any user intervention. This new type of morph can go far beyond the ability of traditional techniques. We also demonstrate that our smooth sequences allow exploring large image collections in a stable manner.

In this paper, we introduce a spherical embedding technique to position a given set of silhouettes of an object as observed from a set of cameras arbitrarily positioned around the object. Our technique estimates dissimilarities among the silhouettes and embeds them directly in the rotation space SO(3). The embedding is obtained by an optimization scheme applied over the rotations represented with exponential maps. Since the measure for inter-silhouette dissimilarities contains many outliers, our key idea is to perform the embedding by only using a subset of the estimated dissimilarities. We present a technique that carefully screens for inlier-distances, and the pairwise scaled dissimilarities are embedded in a spherical space, diffeomorphic to SO(3). We show that our method outperforms spherical MDS embedding, demonstrate its performance on various multi-view sets, and highlight its robustness to outliers.

Abstract We present a distillation algorithm which operates on a large, unstructured, and noisy collection of internet images returned from an online object query. We introduce the notion of a distilled set, which is a clean, coherent, and structured subset of inlier images. In addition, the object of interest is properly segmented out throughout the distilled set. Our approach is unsupervised, built on a novel clustering scheme, and solves the distillation and object segmentation problems simultaneously. In essence, instead of distilling the collection of images, we distill a collection of loosely cutout foreground “shapes”, which may or may not contain the queried object. Our key observation, which motivated our clustering scheme, is that outlier shapes are expected to be random in nature, whereas, inlier shapes, which do tightly enclose the object of interest, tend to be well supported by similar shapes captured in similar views. We analyze the commonalities among candidate foreground segments, without aiming to analyze their semantics, but simply by clustering similar shapes and considering only the most significant clusters representing non‐trivial shapes. We show that when tuned conservatively, our distillation algorithm is able to extract a near perfect subset of true inliers. Furthermore, we show that our technique scales well in the sense that the precision rate remains high, as the collection grows. We demonstrate the utility of our distillation results with a number of interesting graphics applications.

The multitude of cameras constantly present nowadays redefines the meaning of capturing an event and the meaning of sharing this event with others. The images are frequently uploaded to a common platform, and the image navigation challenge naturally arises. We introduce RingIt : a spectral technique for recovering the spatial order of a set of still images capturing an event taken by a group of people situated around the event. We assume a nearly instantaneous event, such as an interesting moment in a performance captured by the digital cameras and smartphones of the surrounding crowd. The ordering method extracts the K-nearest neighbors (KNN) of each image from a rough all-pairs dissimilarity estimate. The KNN dissimilarities are refined to form a sparse weighted Laplacian, and a spectral analysis then yields a ring angle for each image. The spatial order is recovered by sorting the obtained ring angles. The ordering of the unorganized set of images allows for a sequential display of the captured object. We demonstrate our technique on a number of sets capturing momentary events, where the images were acquired with low-quality consumer cameras by a group of people positioned around the event.