Current text-to-image diffusion models excel at generating diverse, high-quality images, yet they struggle to incorporate fine-grained camera metadata such as precise aperture settings. In this work, we introduce a novel text-to-image diffusion framework that leverages camera metadata, or EXIF data, which is often embedded in image files, with an emphasis on generating controllable lens blur. Our method mimics the physical image formation process by first generating an all-in-focus image, estimating its monocular depth, predicting a plausible focus distance with a novel focus distance transformer, and then forming a defocused image with an existing differentiable lens blur model [32]. Gradients flow backwards through this whole process, allowing us to learn without explicit supervision to generate defocus effects based on content elements and the provided EXIF data. At inference time, this enables precise interactive user control over defocus effects while preserving scene contents, which is not achievable with existing diffusion models. Experimental results demonstrate that our model enables superior fine-grained control without altering the depicted scene.

Generating sound effects for videos often requires creating artistic sound effects that diverge significantly from real-life sources and flexible control in the sound design. To address this problem, we introduce MultiFoley, a model designed for video-guided sound generation that supports multimodal conditioning through text, audio, and video. Given a silent video and a text prompt, MultiFoley allows users to create clean sounds (e.g., skateboard wheels spinning without wind noise) or more whimsical sounds (e.g., making a lion’s roar sound like a cat’s meow). MultiFoley also allows users to choose reference audio from sound effects (SFX) libraries or partial videos for conditioning. A key novelty of our model lies in its joint training on both internet video datasets with low-quality audio and professional SFX recordings, enabling high-quality, full-bandwidth (48kHz) audio generation. Through automated evaluations and human studies, we demonstrate that MultiFoley successfully generates synchronized high-quality sounds across varied conditional inputs and outperforms existing methods. Please see our project page for video results: https://ificl.github.io/MultiFoley/

We study the problem of making 3D scene reconstructions interactive by asking the following question: can we predict the sounds of human hands physically interacting with a scene? First, we record a video of a human manipulating objects within a 3D scene using their hands. We then use these action-sound pairs to train a rectified flow model to map 3D hand trajectories to their corresponding audio. At test time, a user can query the model for other actions, parameterized as sequences of hand poses, within the scene to estimate their corresponding sounds. In our experiments, we find that our generated sounds accurately convey material properties and actions, and that they are often indistinguishable to human observers from real sounds. Project page: https://www.yimingdou.com/hearing_hands/.

We show that the GPS tags contained in photo metadata provide a useful control signal for image generation. We train GPS-to-image models and use them for tasks that require a fine-grained understanding of how images vary within a city. In particular, we train a diffusion model to generate images conditioned on both GPS and text. The learned model generates images that capture the distinctive appearance of different neighborhoods, parks, and landmarks. We also extract 3D models from 2D GPS-to-image models through score distillation sampling, using GPS conditioning to constrain the appearance of the reconstruction from each viewpoint. Our evaluations suggest that our GPS-conditioned models successfully learn to generate images that vary based on location, and that GPS conditioning improves estimated 3D structure.

Motion control is crucial for generating expressive and compelling video content; however, most existing video generation models rely mainly on text prompts for control, which struggle to capture the nuances of dynamic actions and temporal compositions. To this end, we train a video generation model conditioned on spatiotemporally sparse or dense motion trajectories. In contrast to prior motion conditioning work, this flexible representation can encode any number of trajectories, object-specific or global scene motion, and temporally sparse motion; due to its flexibility we refer to this conditioning as motion prompts. While users may directly specify sparse trajectories, we also show how to translate high-level user requests into detailed, semi-dense motion prompts, a process we term motion prompt expansion. We demonstrate the versatility of our approach through various applications, including camera and object motion control, "interacting" with an image, motion transfer, and image editing. Our results showcase emergent behaviors, such as realistic physics, suggesting the potential of motion prompts for probing video models and interacting with future generative world models. Finally, we evaluate quantitatively, conduct a human study, and demonstrate strong performance.

We present a method for learning binaural sound localization using egomotion as a supervisory signal. Over the course of a video, the camera’s direction to a sound source will change as the camera moves. We train an audio model to predict sound directions that are consistent with visual estimates of camera motion, which we obtain using traditional methods from multi-view geometry. This provides a weak but plentiful form of supervision that we combine with traditional binaural cues. To evaluate this method, we propose a dataset of real-world audio-visual videos with egomotion. We show that our model can successfully learn from real-world data and that it performs well on sound localization tasks.

One of the key challenges of detecting AI-generated images is spotting images that have been created by previously unseen generative models. We argue that the limited diversity of the training data is a major obstacle to addressing this problem, and we propose a new dataset that is significantly larger and more diverse than prior works. As part of creating this dataset, we systematically download thousands of text-to-image latent diffusion models and sample images from them. We also collect images from dozens of popular open source and commercial models. The resulting dataset contains 2.7M images that have been sampled from 4803 different models. These images collectively capture a wide range of scene content, generator architectures, and image processing settings. Using this dataset, we study the generalization abilities of fake image detectors. Our experiments suggest that detection performance improves as the number of models in the training set increases, even when these models have similar architectures. We also find that increasing the diversity of the models improves detection performance, and that our trained detectors generalize better than those trained on other datasets. The dataset can be found in https://jespark.net/projects/2024/community_forensics

We present a method for finding cross-modal space-time correspondences. Given two images from different visual modalities, such as an RGB image and a depth map, our model identifies which pairs of pixels correspond to the same physical points in the scene. To solve this problem, we extend the contrastive random walk framework to simultaneously learn cycle-consistent feature representations for both cross-modal and intra-modal matching. The resulting model is simple and has no explicit photo-consistency assumptions. It can be trained entirely using unlabeled data, without the need for any spatially aligned multimodal image pairs. We evaluate our method on both geometric and semantic correspondence tasks. For geometric matching, we consider challenging tasks such as RGB-to-depth and RGB-to-thermal matching (and vice versa); for semantic matching, we evaluate on photo-sketch and cross-style image alignment. Our method achieves strong performance across all benchmarks.

Modern incarnations of tactile sensors produce high-dimensional raw sensory feedback such as images, making it challenging to efficiently store, process, and generalize across sensors. To address these concerns, we introduce a novel implicit function representation for tactile sensor feedback. Rather than directly using raw tactile images, we propose neural implicit functions trained to reconstruct the tactile dataset, producing compact representations that capture the underlying structure of the sensory inputs. These representations offer several advantages over their raw counterparts: they are compact, enable probabilistically interpretable inference, and facilitate generalization across different sensors. We demonstrate the efficacy of this representation on the downstream task of in-hand object pose estimation, achieving improved performance over image-based methods while simplifying downstream models. We release code, demos and datasets at https://www.mmintlab.com/tactile-functasets.

Today's tactile sensors have a variety of different designs, making it challenging to develop general-purpose methods for processing touch signals. In this paper, we learn a unified representation that captures the shared information between different tactile sensors. Unlike current approaches that focus on reconstruction or task-specific supervision, we leverage contrastive learning to integrate tactile signals from two different sensors into a shared embedding space, using a dataset in which the same objects are probed with multiple sensors. We apply this approach to paired touch signals from GelSlim and Soft Bubble sensors. We show that our learned features provide strong pretraining for downstream pose estimation and classification tasks. We also show that our embedding enables models trained using one touch sensor to be deployed using another without additional training. Project details can be found at https://www.mmintlab.com/research/cttp/.

We present a new dataset called Real Acoustic Fields (RAF) that captures real acoustic room data from multiple modali-ties. The dataset includes high-quality and densely captured room impulse response data paired with multi-view images, and precise 6DoF pose tracking data for sound emitters and listeners in the rooms. We used this dataset to evaluate existing methods for novel-view acoustic synthesis and impulse re-sponse generation which previously relied on synthetic data. In our evaluation, we thoroughly assessed existing audio and audio- visual models against multiple criteria and proposed settings to enhance their performance on real-world data. We also conducted experiments to investigate the impact of incorporating visual data (i.e., images and depth) into neu-ral acoustic field models. Additionally, we demonstrated the effectiveness of a simple sim2real approach, where a model is pre-trained with simulated data and fine-tuned with sparse real-world data, resulting in significant improvements in the few-shot learning approach. RAF is the first dataset to provide densely captured room acoustic data, making it an ideal resource for researchers working on audio and audio-visual neural acoustic field modeling techniques. Demos and datasets are available on our project page.

We present a scene representation, which we call a tactile-augmented radiance field (TaRF), that brings vision and touch into a shared 3D space. This representation can be used to estimate the visual and tactile signals for a given 3D position within a scene. We capture a scene's TaRF from a collection of photos and sparsely sampled touch probes. Our approach makes use of two insights: (i) common vision-based touch sensors are built on ordinary cameras and thus can be registered to images using meth-ods from multi-view geometry, and (ii) visually and structurally similar regions of a scene share the same tactile features. We use these insights to register touch signals to a captured visual scene, and to train a conditional diffusion model that, provided with an RGB-D image rendered from a neural radiance field, generates its corresponding tactile signal. To evaluate our approach, we collect a dataset of TaRFs. This dataset contains more touch samples than pre-vious real-world datasets, and it provides spatially aligned visual signals for each captured touch signal. We demon-strate the accuracy of our cross-modal generative model and the utility of the captured visual-tactile data on sev-eral downstream tasks. Project page: https://dou-yiming.github.io/TaRF.

We address the problem of synthesizing multi-view optical illusions: images that change appearance upon a transformation, such as a flip or rotation. We propose a simple, zero-shot method for obtaining these illusions from off-the-shelf text-to-image diffusion models. During the reverse diffusion process, we estimate the noise from different views of a noisy image, and then combine these noise estimates together and denoise the image. A theoretical analysis suggests that this method works precisely for views that can be written as orthogonal transformations, of which permutations are a subset. This leads to the idea of a visual anagram-an image that changes appearance under some rearrangement of pixels. This includes rotations and flips, but also more exotic pixel permutations such as a jigsaw rearrangement. Our approach also naturally extends to illusions with more than two views. We provide both qualitative and quantitative results demonstrating the effectiveness and flexibility of our method. Please see our project webpage for additional visualizations and results: https://dangeng.github.io/visual_anagrams/.

We propose a simple strategy for masking image patches during visual-language contrastive learning that improves the quality of the learned representations and the training speed. During each iteration of training, we randomly mask clusters of visually similar image patches, as measured by their raw pixel intensities. This provides an extra learning signal, beyond the contrastive training itself, since it forces a model to predict words for masked visual structures solely from context. It also speeds up training by reducing the amount of data used in each image. We evaluate the effectiveness of our model by pre-training on a number of bench-marks, finding that it outperforms other masking strategies, such as FLIP, on the quality of the learned representation.

Touch provides crucial information about the physical properties of the objects around us. Creating models that capture cross-modal associations between touch and other modalities, however, remains a challenging problem, due to wide variety of touch sensors and the intensive effort required to collect tactile data. We propose UniTouch, a unified model for vision-based touch sensors that connects their tactile signals to other modalities, including vision, language, and sound. We achieve this by aligning our tactile embeddings to pretrained image embeddings already associated with a variety of other modalities. We further propose learnable sensor-specific tokens, allowing the model to learn from a set of heterogeneous tactile sensors, all at the same time. UniTouch is capable of conducting various touch sensing tasks in a zero-shot setting, from robot grasping prediction to touch-based question answering. To the best of our knowledge, UniTouch is the first model to demonstrate these capabilities. Project Page: https://cfeng16.github.io/UniTouch/.

Diffusion models are capable of generating impressive images conditioned on text descriptions, and extensions of these models allow users to edit images at a relatively coarse scale. However, the ability to precisely edit the layout, position, pose, and shape of objects in images with diffusion models is still difficult. To this end, we propose _motion guidance_, a zero-shot technique that allows a user to specify dense, complex motion fields that indicate where each pixel in an image should move. Motion guidance works by steering the diffusion sampling process with the gradients through an off-the-shelf optical flow network. Specifically, we design a guidance loss that encourages the sample to have the desired motion, as estimated by a flow network, while also being visually similar to the source image. By simultaneously sampling from a diffusion model and guiding the sample to have low guidance loss, we can obtain a motion-edited image. We demonstrate that our technique works on complex motions and produces high quality edits of real and generated images.

Spectrograms are 2D representations of sound that look very different from the images found in our visual world. And natural images, when played as spectrograms, make unnatural sounds. In this paper, we show that it is possible to synthesize spectrograms that simultaneously look like natural images and sound like natural audio. We call these visual spectrograms *images that sound*. Our approach is simple and zero-shot, and it leverages pre-trained text-to-image and text-to-spectrogram diffusion models that operate in a shared latent space. During the reverse process, we denoise noisy latents with both the audio and image diffusion models in parallel, resulting in a sample that is likely under both models. Through quantitative evaluations and perceptual studies, we find that our method successfully generates spectrograms that align with a desired audio prompt while also taking the visual appearance of a desired image prompt.

The sound effects that designers add to videos are designed to convey a particular artistic effect and, thus, may be quite different from a scene's true sound. Inspired by the challenges of creating a soundtrack for a video that differs from its true sound, but that nonetheless matches the actions occurring on screen, we propose the problem of conditional Foley. We present the following contributions to address this problem. First, we propose a pretext task for training our model to predict sound for an input video clip using a conditional audio-visual clip sampled from another time within the same source video. Second, we propose a model for generating a soundtrack for a silent input video, given a user-supplied example that specifies what the video should “sound like”. We show through human studies and automated evaluation metrics that our model successfully generates sound from videos, while varying its output according to the content of a supplied example. Project site: https://xypb.github.io/CondFoleyGen.

Manipulated videos often contain subtle inconsistencies between their visual and audio signals. We propose a video forensics method, based on anomaly detection, that can identify these inconsistencies, and that can be trained solely using real, unlabeled data. We train an autoregressive model to generate sequences of audio-visual features, using feature sets that capture the temporal synchronization between video frames and sound. At test time, we then flag videos that the model assigns low probability. Despite being trained entirely on real videos, our model obtains strong performance on the task of detecting manipulated speech videos. Project site: https://cfeng16.github.io/audio-visual-forensics.

We propose a method that learns to camouflage 3D objects within scenes. Given an object's shape and a distribution of viewpoints from which it will be seen, we estimate a texture that will make it difficult to detect. Successfully solving this task requires a model that can accurately reproduce textures from the scene, while simultaneously dealing with the highly conflicting constraints imposed by each viewpoint. We address these challenges with a model based on texture fields and adversarial learning. Our model learns to camouflage a variety of object shapes from randomly sampled locations and viewpoints within the input scene, and is the first to address the problem of hiding complex object shapes. Using a human visual search study, we find that our estimated textures conceal objects significantly better than previous methods.

How does audio describe the world around us? In this paper, we propose a method for generating an image of a scene from sound. Our method addresses the challenges of dealing with the large gaps that often exist between sight and sound. We design a model that works by scheduling the learning procedure of each model component to associate audio-visual modalities despite their information gaps. The key idea is to enrich the audio features with visual information by learning to align audio to visual latent space. We translate the input audio to visual features, then use a pre-trained generator to produce an image. To further improve the quality of our generated images, we use sound source localization to select the audio-visual pairs that have strong cross-modal correlations. We obtain substantially better results on the VEGAS and VGGSound datasets than prior approaches. We also show that we can control our model's predictions by applying simple manipulations to the input waveform, or to the latent space.

We learn a visual representation that captures information about the camera that recorded a given photo. To do this, we train a multimodal embedding between image patches and the EXIF metadata that cameras automatically insert into image files. Our model represents this meta-data by simply converting it to text and then processing it with a transformer. The features that we learn significantly outperform other self-supervised and supervised features on downstream image forensics and calibration tasks. In particular, we successfully localize spliced image regions “zero shot” by clustering the visual embeddings for all of the patches within an image.

The images and sounds that we perceive undergo subtle but geometrically consistent changes as we rotate our heads. In this paper, we use these cues to solve a problem we call Sound Localization from Motion (SLfM): jointly estimating camera rotation and localizing sound sources. We learn to solve these tasks solely through self-supervision. A visual model predicts camera rotation from a pair of images, while an audio model predicts the direction of sound sources from binaural sounds. We train these models to generate predictions that agree with one another. At test time, the models can be deployed independently. To obtain a feature representation that is well-suited to solving this challenging problem, we also propose a method for learning an audio-visual representation through cross-view binauralization: estimating binaural sound from one view, given images and sound from another. Our model can successfully estimate accurate rotations on both real and synthetic scenes, and localize sound sources with accuracy competitive with state-of-the-art self-supervised approaches. Project site: https://ificl.github.io/SLfM.

We present Text2Room1, a method for generating room-scale textured 3D meshes from a given text prompt as input. To this end, we leverage pre-trained 2D text-to-image models to synthesize a sequence of images from different poses. In order to lift these outputs into a consistent 3D scene representation, we combine monocular depth estimation with a text-conditioned inpainting model. The core idea of our approach is a tailored viewpoint selection such that the content of each image can be fused into a seamless, textured 3D mesh. More specifically, we propose a continuous alignment strategy that iteratively fuses scene frames with the existing geometry to create a seamless mesh. Unlike existing works that focus on generating single objects [56], [41] or zoom-out trajectories [18] from text, our method generates complete 3D scenes with multiple objects and explicit 3D geometry. We evaluate our approach using qualitative and quantitative metrics, demonstrating it as the first method to generate room-scale 3D geometry with compelling textures from only text as input.

An emerging line of work has sought to generate plausible imagery from touch. Existing approaches, however, tackle only narrow aspects of the visuo-tactile synthesis problem, and lag significantly behind the quality of cross-modal synthesis methods in other domains. We draw on recent advances in latent diffusion to create a model for synthesizing images from tactile signals (and vice versa) and apply it to a number of visuo-tactile synthesis tasks. Using this model, we significantly outperform prior work on the tactile-driven stylization problem, i.e., manipulating an image to match a touch signal, and we are the first to successfully generate images from touch without additional sources of information about the scene. We also successfully use our model to address two novel synthesis problems: generating images that do not contain the touch sensor or the hand holding it, and estimating an image’s shading from its reflectance and touch. Project Page: https://fredfyyang.github.io/vision-from-touch/

This paper presents a simple, self-supervised method for magnifying subtle motions in video: given an input video and a magnification factor, we manipulate the video such that its new optical flow is scaled by the desired amount. To train our model, we propose a loss function that estimates the optical flow of the generated video and penalizes how far if deviates from the given magnification factor. Thus, training involves differentiating through a pretrained optical flow network. Since our model is self-supervised, we can further improve its performance through test-time adaptation, by finetuning it on the input video. It can also be easily extended to magnify the motions of only user-selected objects. Our approach avoids the need for synthetic magnification datasets that have been used to train prior learning-based approaches. Instead, it leverages the existing capabilities of off-the-shelf motion estimators. We demonstrate the effectiveness of our method through evaluations of both visual quality and quantitative metrics on a range of real-world and synthetic videos, and we show our method works for both supervised and unsupervised optical flow methods.

Humans are remarkably sensitive to the alignment of visual events with other stimuli, which makes synchronization one of the hardest tasks in video editing. A key observation of our work is that most of the alignment we do involves salient localizable events that occur sparsely in time. By learning how to recognize these events, we can greatly reduce the space of possible synchronizations that an editor or algorithm has to consider. Furthermore, by learning descriptors of these events that capture additional properties of visible motion, we can build active tools that adapt their notion of eventfulness to a given task as they are being used. Rather than learning an automatic solution to one specific problem, our goal is to make a much broader class of interactive alignment tasks significantly easier and less time-consuming. We show that a suitable visual event descriptor can be learned entirely from stochastically-generated synthetic video. We then demonstrate the usefulness of learned and adaptive eventfulness by integrating it in novel interactive tools for applications including audio-driven time warping of video and the extraction and application of sound effects across different videos.

In this paper, we explore the relation between gestures and language. Using a multimodal dataset, consisting of Ted talks where the language is aligned with the gestures made by the speakers, we adapt a semi-supervised multimodal model to learn gesture embeddings. We show that gestures are predictive of the native language of the speaker, and that gesture embeddings further improve language prediction result. In addition, gesture embeddings might contain some linguistic information, as we show by probing embeddings for psycholinguistic categories. Finally, we analyze the words that lead to the most expressive gestures and find that function words drive the expressiveness of gestures.

A range of video modeling tasks, from optical flow to multiple object tracking, share the same fundamental challenge: establishing space-time correspondence. Yet, approaches that dominate each space differ. We take a step to-wards bridging this gap by extending the recent contrastive random walk formulation to much denser, pixel-level spacetime graphs. The main contribution is introducing hierarchy into the search problem by computing the transition matrix between two frames in a coarse-to-fine manner, forming a multiscale contrastive random walk when ex-tended in time. This establishes a unified technique for self-supervised learning of optical flow, keypoint tracking, and video object segmentation. Experiments demonstrate that, for each of these tasks, the unified model achieves performance competitive with strong self-supervised approaches specific to that task.11Project page at https://jasonbian97.github.io/flowwalk

Image prediction methods often struggle on tasks that require changing the positions of objects, such as video prediction, producing blurry images that average over the many positions that objects might occupy. In this paper, we propose a simple change to existing image similarity metrics that makes them more robust to positional errors: we match the images using optical flow, then measure the visual similarity of corresponding pixels. This change leads to crisper and more perceptually accurate predictions, and does not require modifications to the image prediction network. We apply our method to a variety of video prediction tasks, where it obtains strong performance with simple network architectures, and to the closely related task of video interpolation. Code and results are available at our webpage: https://dangeng.github.io/CorrWiseLosses

We present a method for simultaneously localizing multiple sound sources within a visual scene. This task requires a model to both group a sound mixture into individual sources, and to associate them with a visual signal. Our method jointly solves both tasks at once, using a formulation inspired by the contrastive random walk of Jabri et al. We create a graph in which images and separated sounds correspond to nodes, and train a random walker to transition between nodes from different modalities with high return probability. The transition probabilities for this walk are determined by an audio-visual similarity metric that is learned by our model. We show through experiments with musical instruments and human speech that our model can successfully localize multiple sounds, outperforming other self-supervised methods.

The ability to associate touch with sight is essential for tasks that require physically interacting with objects in the world. We propose a dataset with paired visual and tactile data called Touch and Go, in which human data collectors probe objects in natural environments using tactile sensors, while simultaneously recording egocentric video. In contrast to previous efforts, which have largely been confined to lab settings or simulated environments, our dataset spans a large number of “in the wild” objects and scenes. We successfully apply our dataset to a variety of multimodal learning tasks: 1) self-supervised visuo-tactile feature learning, 2) tactile-driven image stylization, i.e., making the visual appearance of an object more consistent with a given tactile signal, and 3) predicting future frames of a tactile signal from visuo-tactile inputs.

We introduce a non-parametric approach for infinite video texture synthesis using a representation learned via contrastive learning. We take inspiration from Video Textures [43], which showed that plausible new videos could be generated from a single one by stitching its frames together in a novel yet consistent order. This classic work, however, was constrained by its use of hand-designed distance metrics, limiting its use to simple, repetitive videos. We draw on recent techniques from self-supervised learning to learn this distance metric, allowing us to compare frames in a manner that scales to more challenging dynamics, and to condition on other data, such as audio. We learn representations for video frames and frame-to-frame transition probabilities by fitting a video-specific model trained using contrastive learning. To synthesize a texture, we randomly sample frames with high transition probabilities to generate diverse temporally smooth videos with novel sequences and transitions. The model naturally extends to an audio-conditioned setting without requiring any finetuning. Our model outperforms baselines on human perceptual scores, can handle a diverse range of input videos, and can combine semantic and audiovisual cues in order to synthesize videos that synchronize well with an audio signal.

The paper studies planar surface reconstruction of indoor scenes from two views with unknown camera poses. While prior approaches have successfully created object-centric reconstructions of many scenes, they fail to exploit other structures, such as planes, which are typically the dominant components of indoor scenes. In this paper, we re-construct planar surfaces from multiple views, while jointly estimating camera pose. Our experiments demonstrate that our method is able to advance the state of the art of re-construction from sparse views, on challenging scenes from Matterport3D.

Although many simulation models of natural phenomena have been developed to date, little attention was given to a major contributor to the beauty of nature: the colorful patterns of flowers. We survey typical patterns and propose methods for simulating them inspired by the current understanding of the biology of floral patterning. The patterns are generated directly on geometric models of flowers, using different combinations of key mathematical models of morphogenesis: vascular patterning, positional information, reaction-diffusion, and random pattern generation. The integration of these models makes it possible to capture a wide range of the flower pigmentation patterns observed in nature.

In this work we ask whether it is possible to create a "universal" detector for telling apart real images from these generated by a CNN, regardless of architecture or dataset used. To test this, we collect a dataset consisting of fake images generated by 11 different CNN-based image generator models, chosen to span the space of commonly used architectures today (ProGAN, StyleGAN, BigGAN, CycleGAN, StarGAN, GauGAN, DeepFakes, cascaded refinement networks, implicit maximum likelihood estimation, second-order attention super-resolution, seeing-in-the-dark). We demonstrate that, with careful pre- and post-processing and data augmentation, a standard image classifier trained on only one specific CNN generator (ProGAN) is able to generalize surprisingly well to unseen architectures, datasets, and training methods (including the just released StyleGAN2). Our findings suggest the intriguing possibility that today's CNN-generated images share some common systematic flaws, preventing them from achieving realistic image synthesis.

This paper proposes a simple self-supervised approach for learning a representation for visual correspondence from raw video. We cast correspondence as prediction of links in a space-time graph constructed from video. In this graph, the nodes are patches sampled from each frame, and nodes adjacent in time can share a directed edge. We learn a representation in which pairwise similarity defines transition probability of a random walk, such that prediction of long-range correspondence is computed as a walk along the graph. We optimize the representation to place high probability along paths of similarity. Targets for learning are formed without supervision, by cycle-consistency: the objective is to maximize the likelihood of returning to the initial node when walking along a graph constructed from a palindrome of frames. Thus, a single path-level constraint implicitly supervises chains of intermediate comparisons. When used as a similarity metric without adaptation, the learned representation outperforms the self-supervised state-of-the-art on label propagation tasks involving objects, semantic parts, and pose. Moreover, we demonstrate that a technique we call edge dropout, as well as self-supervised adaptation at test-time, further improve transfer for object-centric correspondence.

Human speech is often accompanied by hand and arm gestures. We present a method for cross-modal translation from "in-the-wild" monologue speech of a single speaker to their conversational gesture motion. We train on unlabeled videos for which we only have noisy pseudo ground truth from an automatic pose detection system. Our proposed model significantly outperforms baseline methods in a quantitative comparison. To support research toward obtaining a computational understanding of the relationship between gesture and speech, we release a large video dataset of person-specific gestures.

Most malicious photo manipulations are created using standard image editing tools, such as Adobe Photoshop. We present a method for detecting one very popular Photoshop manipulation -- image warping applied to human faces -- using a model trained entirely using fake images that were automatically generated by scripting Photoshop itself. We show that our model outperforms humans at the task of recognizing manipulated images, can predict the specific location of edits, and in some cases can be used to "undo" a manipulation to reconstruct the original, unedited image. We demonstrate that the system can be successfully applied to artist-created image manipulations.

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.

Hardness is among the most important attributes of an object that humans learn about through touch. However, approaches for robots to estimate hardness are limited, due to the lack of information provided by current tactile sensors. In this work, we address these limitations by introducing a novel method for hardness estimation, based on the GelSight tactile sensor, and the method does not require accurate control of contact conditions or the shape of objects. A GelSight has a soft contact interface, and provides high resolution tactile images of contact geometry, as well as contact force and slip conditions. In this paper, we try to use the sensor to measure hardness of objects with multiple shapes, under a loosely controlled contact condition. The contact is made manually or by a robot hand, while the force and trajectory are unknown and uneven. We analyze the data using a deep constitutional (and recurrent) neural network. Experiments show that the neural net model can estimate the hardness of objects with different shapes and hardness ranging from 8 to 87 in Shore 00 scale.

Objects make distinctive sounds when they are hit or scratched. These sounds reveal aspects of an object's material properties, as well as the actions that produced them. In this paper, we propose the task of predicting what sound an object makes when struck as a way of studying physical interactions within a visual scene. We present an algorithm that synthesizes sound from silent videos of people hitting and scratching objects with a drumstick. This algorithm uses a recurrent neural network to predict sound features from videos and then produces a waveform from these features with an example-based synthesis procedure. We show that the sounds predicted by our model are realistic enough to fool participants in a "real or fake" psychophysical experiment, and that they convey significant information about material properties and physical interactions.

Showy inflorescences - clusters of flowers - are a common feature of many plants, greatly contributing to their beauty. The large numbers of individual flowers (florets), arranged in space in a systematic manner, make inflorescences a natural target for procedural modeling. We present a suite of biologically motivated algorithms for modeling and animating the development of inflorescences with closely packed florets. These inflorescences share the following characteristics: (i) in their ensemble, the florets form a relatively smooth, often approximately planar surface; (ii) there are numerous collisions between petals of the same or adjacent florets; and (iii) the developmental stage and type of a floret may depend on its position within the inflorescence, with drastic or gradual differences. To model flat-topped branched inflorescences (corymbs and umbels), we propose a florets-first algorithm, in which the branching structure self-organizes to support florets in predetermined positions. This is an alternative to previous branching-first models, in which floret positions were determined by branch arrangement. To obtain realistic visualizations, we complement the algorithms that generate the inflorescence structure with an interactive method for modeling floret corollas (petal sets). The method supports corollas with both separate and fused petals. We illustrate our techniques with models from several plant families.

We address the problem of camouflaging a 3D object from the many viewpoints that one might see it from. Given photographs of an object's surroundings, we produce a surface texture that will make the object difficult for a human to detect. To do this, we introduce several background matching algorithms that attempt to make the object look like whatever is behind it. Of course, it is impossible to exactly match the background from every possible viewpoint. Thus our models are forced to make trade-offs between different perceptual factors, such as the conspicuousness of the occlusion boundaries and the amount of texture distortion. We use experiments with human subjects to evaluate the effectiveness of these models for the task of camouflaging a cube, finding that they significantly outperform naïve strategies.

We present a data-driven method for building dense 3D reconstructions using a combination of recognition and multi-view cues. Our approach is based on the idea that there are image patches that are so distinctive that we can accurately estimate their latent 3D shapes solely using recognition. We call these patches shape anchors, and we use them as the basis of a multi-view reconstruction system that transfers dense, complex geometry between scenes. We "anchor" our 3D interpretation from these patches, using them to predict geometry for parts of the scene that are relatively ambiguous. The resulting algorithm produces dense reconstructions from stereo point clouds that are sparse and noisy, and we demonstrate it on a challenging dataset of real-world, indoor scenes.

Existing scene understanding datasets contain only a limited set of views of a place, and they lack representations of complete 3D spaces. In this paper, we introduce SUN3D, a large-scale RGB-D video database with camera pose and object labels, capturing the full 3D extent of many places. The tasks that go into constructing such a dataset are difficult in isolation -- hand-labeling videos is painstaking, and structure from motion (SfM) is unreliable for large spaces. But if we combine them together, we make the dataset construction task much easier. First, we introduce an intuitive labeling tool that uses a partial reconstruction to propagate labels from one frame to another. Then we use the object labels to fix errors in the reconstruction. For this, we introduce a generalization of bundle adjustment that incorporates object-to-object correspondences. This algorithm works by constraining points for the same object from different frames to lie inside a fixed-size bounding box, parameterized by its rotation and translation. The SUN3D database, the source code for the generalized bundle adjustment, and the web-based 3D annotation tool are all available at http://sun3d.cs.princeton.edu.

Recent work in structure from motion (SfM) has built 3D models from large collections of images downloaded from the Internet. Many approaches to this problem use incremental algorithms that solve progressively larger bundle adjustment problems. These incremental techniques scale poorly as the image collection grows, and can suffer from drift or local minima. We present an alternative framework for SfM based on finding a coarse initial solution using hybrid discrete-continuous optimization and then improving that solution using bundle adjustment. The initial optimization step uses a discrete Markov random field (MRF) formulation, coupled with a continuous Levenberg-Marquardt refinement. The formulation naturally incorporates various sources of information about both the cameras and points, including noisy geotags and vanishing point (VP) estimates. We test our method on several large-scale photo collections, including one with measured camera positions, and show that it produces models that are similar to or better than those produced by incremental bundle adjustment, but more robustly and in a fraction of the time.

Recent work in structure from motion (SfM) has successfully built 3D models from large unstructured collections of images downloaded from the Internet. Most approaches use incremental algorithms that solve progressively larger bundle adjustment problems. These incremental techniques scale poorly as the number of images grows, and can drift or fall into bad local minima. We present an alternative formulation for SfM based on finding a coarse initial solution using a hybrid discrete-continuous optimization, and then improving that solution using bundle adjustment. The initial optimization step uses a discrete Markov random field (MRF) formulation, coupled with a continuous Levenberg-Marquardt refinement. The formulation naturally incorporates various sources of information about both the cameras and the points, including noisy geotags and vanishing point estimates. We test our method on several large-scale photo collections, including one with measured camera positions, and show that it can produce models that are similar to or better than those produced with incremental bundle adjustment, but more robustly and in a fraction of the time.

Reading has traditionally been seen as an essential component in learning, especially at the university level. However, many instructors in higher education, especially in technical courses, do not emphasize reading or try to evaluate it. In this abstract we present an automated system designed to measure and improve reading comprehension and describe preliminary results using the system.