We present CineCraft, an interactive mobile application that unifies planning, capture, and post-processing for cinematography on a single device. Our key design insight is to use a storyboard-like shot plan as a persistent representation that connects different stages of the filmmaking process, emulating coordination strategies used by professional film crews. Our shot plans extend common storyboarding conventions to encode time-varying parameters (e.g., camera movement, focus, and zoom) on a shared timeline, enabling previsualization during planning and precise synchronization during capture. CineCraft uses shot plans to generate camera movement instructions, provide augmented-reality (AR) framing guidance during filming, automate focus and zoom, and organize takes for review and rough-cut assembly. By consolidating stages that are often fragmented across separate mobile apps and ad hoc workflows, our system enables rapid on-location iteration with immediate playback. We demonstrate our system through a range of examples and two user studies.

We propose an interactive decision-making tool for discovering and exploring explainable rankings for a given set of choices (e.g., job offers, vacation destinations, award candidates). We define an explainable ranking as an ordering of choices based on some consistent weighting of measured criteria. Our tool is designed to help users explore different orderings, criteria, and criterion weights in search of an explainable ranking that reflects their own personal preferences. To achieve this, we combine visualization, optimization, and (optionally) the integration of AI to help users identify and correct or explain inconsistencies in their evaluation of different choices. Through user experiments, we demonstrate that our tool leads to more consistent explainable rankings with greater user confidence.

Designing 3D scenes is traditionally a challenging and laborious task that demands both artistic expertise and proficiency with complex software. Recent advances in text-to-3D generation have greatly simplified this process by letting users create scenes based on simple text descriptions. However, as these methods generally require extra training or in-context learning, their performance is often hindered by the limited availability of high-quality 3D data. In contrast, modern text-to-image models learned from web-scale images can generate scenes with diverse, reliable spatial layouts and consistent, visually appealing styles. Our key insight is that instead of learning directly from 3D scenes, we can leverage generated 2D images as an intermediary to guide 3D synthesis. In light of this, we introduce ArtiScene, a training-free automated pipeline for scene design that integrates the flexibility of free-form text-to-image generation with the diversity and reliability of 2D intermediary layouts. First, we generate 2D images from a scene description, then extract the shape and appearance of objects to create 3D models. These models are assembled into the final scene using geometry, position, and pose information derived from the same intermediary image. Being generalizable to a wide range of scenes and styles, ArtiScene outperforms state-of-the-art benchmarks by a large margin in layout and aesthetic quality by quantitative metrics. It also averages a 74.89 % winning rate in extensive user studies and 95.07 % in GPT-4o evaluation.

Abstract Recent diffusion‐based methods have achieved impressive results on animating images of human subjects. However, most of that success has built on human‐specific body pose representations and extensive training with labeled real videos. In this work, we extend the ability of such models to animate images of characters with more diverse skeletal topologies. Given a small number (3–5) of example frames showing the character in different poses with corresponding skeletal information, our model quickly infers a rig for that character that can generate images corresponding to new skeleton poses. We propose a procedural data generation pipeline that efficiently samples training data with diverse topologies on the fly. We use it, along with a novel skeleton representation, to train our model on articulated shapes spanning a large space of textures and topologies. Then during fine‐tuning, our model rapidly adapts to unseen target characters and generalizes well to rendering new poses, both for realistic and more stylized cartoon appearances. To better evaluate performance on this novel and challenging task, we create the first 2D video dataset that contains both humanoid and non‐humanoid subjects with per‐frame keypoint annotations. With extensive experiments, we demonstrate the superior quality of our results.

Long-take touring (LTT) shots are characterized by smooth camera motion over a long distance that seamlessly connects different views of the captured scene. These shots offer a compelling way to visualize 3D spaces. However, filming LTT shots directly is very difficult, and rendering them based on a virtual reconstruction of a scene is resource-intensive and prone to many visual artifacts. We propose Hybrid Tours , a hybrid approach to creating LTT shots that combines the capture of short clips representing potential tour segments with a custom interactive application that lets users filter and combine these segments into longer camera trajectories. We show that Hybrid Tours makes capturing LTT shots much easier than the traditional single-take approach, and that clip-based authoring and reconstruction leads to higher-fidelity results at a lower cost than common image-based rendering workflows.

The proliferation of advanced tools for manipulating video has led to an arms race, pitting those who wish to sow disinformation against those who want to detect and expose it. Unfortunately, time favors the ill-intentioned in this race, with fake videos growing increasingly difficult to distinguish from real ones. At the root of this trend is a fundamental advantage held by those manipulating media: equal access to a distribution of what we consider authentic (i.e., “natural”) video. In this paper, we show how coding very subtle, noise-like modulations into the illumination of a scene can help combat this advantage by creating an information asymmetry that favors verification. Our approach effectively adds a temporal watermark to any video recorded under coded illumination. However, rather than encoding a specific message, this watermark encodes an image of the unmanipulated scene as it would appear lit only by the coded illumination. We show that even when an adversary knows that our technique is being used, creating a plausible coded fake video amounts to solving a second, more difficult version of the original adversarial content creation problem at an information disadvantage. This is a promising avenue for protecting high-stakes settings like public events and interviews, where the content on display is a likely target for manipulation, and while the illumination can be controlled, the cameras capturing video cannot.

Our bodies are constantly in motion—from the bending of arms and legs to the less conscious movement of breathing, our precise shape and location change constantly. This can make subtler developments (e.g., the growth of hair, or the healing of a wound) difficult to observe. Our work focuses on helping users record and visualize this type of subtle, longer-term change. We present a mobile tool that combines custom 3D tracking with interactive visual feedback and computational imaging to capture personal time-lapse, which approximates longer-term video of the subject (typically, part of the capturing user’s body) under a fixed viewpoint, body pose, and lighting condition. These personal time-lapses offer a powerful and detailed way to track visual changes of the subject over time. We begin with a formative study that examines what makes personal time-lapse so difficult to capture. Building on our findings, we motivate the design of our capture tool, evaluate this design with users, and demonstrate its effectiveness in a variety of challenging examples.

We present a novel perceptually-motivated interactive tool for using color contrast to enhance details represented in the lightness channel of images and video. Our method lets users adjust the perceived contrast of different details by manipulating local chromaticity while preserving the original lightness of individual pixels. Inspired by the use of similar chromaticity mappings in painting, our tool effectively offers contrast along a user-selected gradient of chromaticities as additional bandwidth for representing and enhancing different details in an image. We provide an interface for our tool that closely resembles the familiar design of tonal contrast curve controls that are available in most professional image editing software. We show that our tool is effective for enhancing the perceived contrast of details without altering lightness in an image and present many examples of effects that can be achieved with our method on both images and video.

There is a rapidly growing group of people learning to sew online. Without hands-on instruction, these learners are often left to discover the challenges and pitfalls of sewing through trial and error, which can be a frustrating and wasteful process. We present InStitches, a software tool that augments existing sewing patterns with targeted practice tasks to guide users through the skills needed to complete their chosen project. InStitches analyzes the difficulty of sewing instructions relative to a user’s reported expertise in order to determine where practice will be helpful and then solves for a new pattern layout that incorporates additional practice steps while optimizing for efficient use of available materials. Our user evaluation indicates that InStitches can successfully identify challenging sewing tasks and augment existing sewing patterns with practice tasks that users find helpful, showing promise as a tool for helping those new to the craft.

Multi-view image generation attracts particular attention these days due to its promising 3D-related applications, e.g., image viewpoint editing. Most existing methods follow a paradigm where a 3D representation is first synthesized, and then rendered into 2D images to ensure photo-consistency across viewpoints. However, such explicit bias for photo-consistency sacrifices photo-realism, causing geometry artifacts and loss of fine-scale details when these methods are applied to edit real images. To address this issue, we propose ray conditioning, a geometry-free alternative that relaxes the photo-consistency constraint. Our method generates multi-view images by conditioning a 2D GAN on a light field prior. With explicit viewpoint control, state-of-the-art photo-realism and identity consistency, our method is particularly suited for the viewpoint editing task.

We propose Factor Matting , an alternative formulation of the video matting problem in terms of counterfactual video synthesis that is better suited for re-composition tasks. The goal of factor matting is to separate the contents of a video into independent components, each representing a counterfactual version of the scene where the contents of other components have been removed. We show that factor matting maps well to a more general Bayesian framing of the matting problem that accounts for complex conditional interactions between layers. Based on this observation, we present a method for solving the factor matting problem that learns augmented patch-based appearance priors to produce useful decompositions even for video with complex cross-layer interactions like splashes, shadows, and reflections. Our method is trained per-video and does not require external training data or any knowledge about the 3D structure of the scene. Through extensive experiments, we show that it is able to produce useful decompositions of scenes with such complex interactions while performing competitively on classical matting tasks as well. We also demonstrate the benefits of our approach on a wide range of downstream video editing tasks. Our project website is at: https://factormatte.github.io/.

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.

We present ReCapture, a system that leverages AR-based guidance to help users capture time-lapse data with hand-held mobile devices. ReCapture works by repeatedly guiding users back to the precise location of previously captured images so they can record time-lapse videos one frame at a time without leaving their camera in the scene. Building on previous work in computational re-photography, we combine three different guidance modes to enable parallel hand-held time-lapse capture in general settings. We demonstrate the versatility of our system on a wide variety of subjects and scenes captured over a year of development and regular use, and explore different visualizations of unstructured hand-held time-lapse data.

Foundation paper piecing is a popular technique for constructing fabric patchwork quilts using printed paper patterns. But, the construction process imposes constraints on the geometry of the pattern and the order in which the fabric pieces are attached to the quilt. Manually designing foundation paper pieceable patterns that meet all of these constraints is challenging. In this work we mathematically formalize the foundation paper piecing process and use this formalization to develop an algorithm that can automatically check if an input pattern geometry is foundation paper pieceable. Our key insight is that we can represent the geometric pattern design using a certain type of dual hypergraph where nodes represent faces and hyperedges represent seams connecting two or more nodes. We show that determining whether the pattern is paper pieceable is equivalent to checking whether this hypergraph is acyclic, and if it is acyclic, we can apply a leaf-plucking algorithm to the hypergraph to generate viable sewing orders for the pattern geometry. We implement this algorithm in a design tool that allows quilt designers to focus on producing the geometric design of their pattern and let the tool handle the tedious task of determining whether the pattern is foundation paper pieceable.

How can we tell whether an image has been mirrored? While we understand the geometry of mirror reflections very well, less has been said about how it affects distributions of imagery at scale, despite widespread use for data augmentation in computer vision. In this paper, we investigate how the statistics of visual data are changed by reflection. We refer to these changes as ``visual chirality,'' after the concept of geometric chirality---the notion of objects that are distinct from their mirror image. Our analysis of visual chirality reveals surprising results, including low-level chiral signals pervading imagery stemming from image processing in cameras, to the ability to discover visual chirality in images of people and faces. Our work has implications for data augmentation, self-supervised learning, and image forensics.

We present a visual analogue for musical rhythm derived from an analysis of motion in video, and show that alignment of visual rhythm with its musical counterpart results in the appearance of dance. Central to our work is the concept of visual beats --- patterns of motion that can be shifted in time to control visual rhythm. By warping visual beats into alignment with musical beats, we can create or manipulate the appearance of dance in video. Using this approach we demonstrate a variety of retargeting applications that control musical synchronization of audio and video: we can change what song performers are dancing to, warp irregular motion into alignment with music so that it appears to be dancing, or search collections of video for moments of accidentally dance-like motion that can be used to synthesize musical performances.

The estimation of material properties is important for scene understanding, with many applications in vision, robotics, and structural engineering. This paper connects fundamentals of vibration mechanics with computer vision techniques in order to infer material properties from small, often imperceptible motions in video. Objects tend to vibrate in a set of preferred modes. The frequencies of these modes depend on the structure and material properties of an object. We show that by extracting these frequencies from video of a vibrating object, we can often make inferences about that object's material properties. We demonstrate our approach by estimating material properties for a variety of objects by observing their motion in high-speed and regular frame rate video.

We present a system for efficiently editing video of dialogue-driven scenes. The input to our system is a standard film script and multiple video takes, each capturing a different camera framing or performance of the complete scene. Our system then automatically selects the most appropriate clip from one of the input takes, for each line of dialogue, based on a user-specified set of film-editing idioms. Our system starts by segmenting the input script into lines of dialogue and then splitting each input take into a sequence of clips time-aligned with each line. Next, it labels the script and the clips with high-level structural information (e.g., emotional sentiment of dialogue, camera framing of clip, etc.). After this pre-process, our interface offers a set of basic idioms that users can combine in a variety of ways to build custom editing styles. Our system encodes each basic idiom as a Hidden Markov Model that relates editing decisions to the labels extracted in the pre-process. For short scenes (< 2 minutes, 8--16 takes, 6--27 lines of dialogue) applying the user-specified combination of idioms to the pre-processed inputs generates an edited sequence in 2--3 seconds. We show that this is significantly faster than the hours of user time skilled editors typically require to produce such edits and that the quick feedback lets users iteratively explore the space of edit designs.

Portraits taken with direct flash look harsh and unflattering because the light source comes from a small set of angles very close to the camera. Advanced photographers address this problem by using bounce flash , a technique where the flash is directed towards other surfaces in the room, creating a larger, virtual light source that can be cast from different directions to provide better shading variation for 3D modeling. However, finding the right direction to point a bounce flash requires skill and careful consideration of the available surfaces and subject configuration. Inspired by the impact of automation for exposure, focus and flash metering, we automate control of the flash direction for bounce illumination. We first identify criteria for evaluating flash directions, based on established photography literature, and relate these criteria to the color and geometry of a scene. We augment a camera with servomotors to rotate the flash head, and additional sensors (a fisheye and 3D sensors) to gather information about potential bounce surfaces. We present a simple numerical optimization criterion that finds directions for the flash that consistently yield compelling illumination and demonstrate the effectiveness of our various criteria in common photographic configurations.

The estimation of material properties is important for scene understanding, with many applications in vision, robotics, and structural engineering. This paper connects fundamentals of vibration mechanics with computer vision techniques in order to infer material properties from small, often imperceptible motion in video. Objects tend to vibrate in a set of preferred modes. The shapes and frequencies of these modes depend on the structure and material properties of an object. Focusing on the case where geometry is known or fixed, we show how information about an object's modes of vibration can be extracted from video and used to make inferences about that object's material properties. We demonstrate our approach by estimating material properties for a variety of rods and fabrics by passively observing their motion in high-speed and regular framerate video.

We present algorithms for extracting an image-space representation of object structure from video and using it to synthesize physically plausible animations of objects responding to new, previously unseen forces. Our representation of structure is derived from an image-space analysis of modal object deformation: projections of an object's resonant modes are recovered from the temporal spectra of optical flow in a video, and used as a basis for the image-space simulation of object dynamics. We describe how to extract this basis from video, and show that it can be used to create physically-plausible animations of objects without any knowledge of scene geometry or material properties.

When sound hits an object, it causes small vibrations of the object's surface. We show how, using only high-speed video of the object, we can extract those minute vibrations and partially recover the sound that produced them, allowing us to turn everyday objects---a glass of water, a potted plant, a box of tissues, or a bag of chips---into visual microphones. We recover sounds from high-speed footage of a variety of objects with different properties, and use both real and simulated data to examine some of the factors that affect our ability to visually recover sound. We evaluate the quality of recovered sounds using intelligibility and SNR metrics and provide input and recovered audio samples for direct comparison. We also explore how to leverage the rolling shutter in regular consumer cameras to recover audio from standard frame-rate videos, and use the spatial resolution of our method to visualize how sound-related vibrations vary over an object's surface, which we can use to recover the vibration modes of an object.

Sparsity in the Fourier domain is an important property that enables the dense reconstruction of signals, such as 4D light fields, from a small set of samples. The sparsity of natural spectra is often derived from continuous arguments, but reconstruction algorithms typically work in the discrete Fourier domain. These algorithms usually assume that sparsity derived from continuous principles will hold under discrete sampling. This article makes the critical observation that sparsity is much greater in the continuous Fourier spectrum than in the discrete spectrum. This difference is caused by a windowing effect. When we sample a signal over a finite window, we convolve its spectrum by an infinite sinc, which destroys much of the sparsity that was in the continuous domain. Based on this observation, we propose an approach to reconstruction that optimizes for sparsity in the continuous Fourier spectrum. We describe the theory behind our approach and discuss how it can be used to reduce sampling requirements and improve reconstruction quality. Finally, we demonstrate the power of our approach by showing how it can be applied to the task of recovering non-Lambertian light fields from a small number of 1D viewpoint trajectories.

It is often desirable to detect whether a surface has been touched, even when the changes made to that surface are too subtle to see in a pair of before and after images. To address this challenge, we introduce a new imaging technique that combines computational photography and laser speckle imaging. Without requiring controlled laboratory conditions, our method is able to detect surface changes that would be indistinguishable in regular photographs. It is also mobile and does not need to be present at the time of contact with the surface, making it well suited for applications where the surface of interest cannot be constantly monitored. Our approach takes advantage of the fact that tiny surface deformations cause phase changes in reflected coherent light which alter the speckle pattern visible under laser illumination. We take before and after images of the surface under laser light and can detect subtle contact by correlating the speckle patterns in these images. A key challenge we address is that speckle imaging is very sensitive to the location of the camera, so removing and reintroducing the camera requires high-accuracy viewpoint alignment. To this end, we use a combination of computational rephotography and correlation analysis of the speckle pattern as a function of camera translation. Our technique provides a reliable way of detecting subtle surface contact at a level that was previously only possible under laboratory conditions. With our system, the detection of these subtle surface changes can now be brought into the wild.

Abstract We present a system for interactively acquiring and rendering light fields using a hand‐held commodity camera. The main challenge we address is assisting a user in achieving good coverage of the 4D domain despite the challenges of hand‐held acquisition. We define coverage by bounding reprojection error between viewpoints, which accounts for all 4 dimensions of the light field. We use this criterion together with a recent Simultaneous Localization and Mapping technique to compute a coverage map on the space of viewpoints. We provide users with real‐time feedback and direct them toward under‐sampled parts of the light field. Our system is lightweight and has allowed us to capture hundreds of light fields. We further present a new rendering algorithm that is tailored to the unstructured yet dense data we capture. Our method can achieve piecewise‐bicubic reconstruction using a triangulation of the captured viewpoints and subdivision rules applied to reconstruction weights.