Search for: All records

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. 

Mobile Augmented Reality (AR) offers a powerful way to provide spatially-aware guidance for real-world applications. In many cases, these applications involve the configuration of a camera or articulated subject, asking users to navigate several spatial degrees of freedom (DOF) at once. Most guidance for such tasks relies on decomposing available DOF into subspaces that can be more easily mapped to simple 1D or 2D visualizations. Unfortunately, different factorizations of the same motion often map to very different visual feedback, and finding the factorization that best matches a user’s intuition can be difficult. We propose an interactive approach that infers rotational degrees of freedom from short user demonstrations. Users select one or two DOFs at a time by demonstrating a small range of motion, which we use to learn a rotational frame that best aligns with user control of the object. We show that deriving visual feedback from this inferred learned rotational frame leads to improved task completion times on 6DOF guidance tasks compared to standard default reference frames used in most mixed reality applications. 

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. 

Abstract Anomaly, or out-of-distribution, detection is a promising tool for aiding discoveries of new particles or processes in particle physics. In this work, we identify and address two overlooked opportunities to improve anomaly detection (AD) for high-energy physics. First, rather than train a generative model on the single most dominant background process, we build detection algorithms using representation learning from multiple background types, thus taking advantage of more information to improve estimation of what is relevant for detection. Second, we generalize decorrelation to the multi-background setting, thus directly enforcing a more complete definition of robustness for AD. We demonstrate the benefit of the proposed robust multi-background AD algorithms on a high-dimensional dataset of particle decays at the Large Hadron Collider. 

Abstract We study the performance of a cloud-based GPU-accelerated inference server to speed up event reconstruction in neutrino data batch jobs. Using detector data from the ProtoDUNE experiment and employing the standard DUNE grid job submission tools, we attempt to reprocess the data by running several thousand concurrent grid jobs, a rate we expect to be typical of current and future neutrino physics experiments. We process most of the dataset with the GPU version of our processing algorithm and the remainder with the CPU version for timing comparisons. We find that a 100-GPU cloud-based server is able to easily meet the processing demand, and that using the GPU version of the event processing algorithm is two times faster than processing these data with the CPU version when comparing to the newest CPUs in our sample. The amount of data transferred to the inference server during the GPU runs can overwhelm even the highest-bandwidth network switches, however, unless care is taken to observe network facility limits or otherwise distribute the jobs to multiple sites. We discuss the lessons learned from this processing campaign and several avenues for future improvements.