In this work we target a learnableoutputrepresentation that allows continuous, high resolution outputs of arbitrary shape. Recent works represent 3D surfaces implicitly with a Neural Network, thereby breaking previous barriers in resolution, and ability to represent diverse topologies. However, neural implicit representations arelimited to closed surfaces, which divide the space into inside and outside. Many real world objects such as walls of a scene scannedby a sensor,clothing,or a car with innerstructuresare not closed. Thisconstitutesa significant barrier,in termsof datapre-processing (objects need to be artificially closed creating artifacts), and the ability to output open surfaces. In this work, we proposeNeural Distance Fields (NDF), a neural network based model which predicts the unsigned distance field for arbitrary 3D shapes given sparse point clouds. NDF represent surfaces at high resolutions as prior implicit models, but do not require closed surface data, and significantly broaden the class of representable shapes in the output.

In this work we target a learnable output representation that allows continuous, high resolution outputs of arbitrary shape. Recent works represent 3D surfaces implicitly with a Neural Network, thereby breaking previous barriers in resolution, and ability to represent diverse topologies. However, neural implicit representations are limited to closed surfaces, which divide the space into inside and outside. Many real world objects such as walls of a scene scanned by a sensor, clothing, or a car with inner structures are not closed. This constitutes a significant barrier, in terms of data pre-processing (objects need to be artificially closed creating artifacts), and the ability to output open surfaces.

In this work we target a learnable output representation that allows continuous, high resolution outputs of arbitrary shape.

In this work we target a learnable output representation that allows continuous, high resolution outputs of arbitrary shape. Recent works represent 3D surfaces implicitly with a Neural Network, thereby breaking previous barriers in resolution, and ability to represent diverse topologies. However, neural implicit representations are limited to closed surfaces, which divide the space into inside and outside. Many real world objects such as walls of a scene scanned by a sensor, clothing, or a car with inner structures are not closed. This constitutes a significant barrier, in terms of data pre-processing (objects need to be artificially closed creating artifacts), and the ability to output open surfaces.

A growing number of people are living with conditions that could benefit from physical rehabilitation -- but there aren't enough physical therapists (PTs) to go around. The growing need for PTs is racing alongside population growth, and aging, as well as higher rates of severe ailments, are contributing to the problem. An upsurge in sensor-based techniques, such as on-body motion sensors, has provided some autonomy and precision for patients who could benefit from robotic systems to supplement human therapists. Still, the minimalist watches and rings that are currently available largely rely on motion data, which lack more holistic data a physical therapist pieces together, including muscle engagement and tension, in addition to movement. This muscle-motion language barrier recently prompted the creation of an unsupervised physical rehabilitation system, MuscleRehab, by researchers from MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) and Massachusetts General Hospital.

In this paper, we present the texture reformer, a fast and universal neural-based framework for interactive texture transfer with user-specified guidance. The challenges lie in three aspects: 1) the diversity of tasks, 2) the simplicity of guidance maps, and 3) the execution efficiency. To address these challenges, our key idea is to use a novel feed-forward multi-view and multi-stage synthesis procedure consisting of I) a global view structure alignment stage, II) a local view texture refinement stage, and III) a holistic effect enhancement stage to synthesize high-quality results with coherent structures and fine texture details in a coarse-to-fine fashion. In addition, we also introduce a novel learning-free view-specific texture reformation (VSTR) operation with a new semantic map guidance strategy to achieve more accurate semantic-guided and structure-preserved texture transfer. The experimental results on a variety of application scenarios demonstrate the effectiveness and superiority of our framework. And compared with the state-of-the-art interactive texture transfer algorithms, it not only achieves higher quality results but, more remarkably, also is 2-5 orders of magnitude faster. Code is available at https://github.com/EndyWon/Texture-Reformer.

"By using machine learning to process the data, we felt we could revisit the canonical view of a cell," Weigel says.