We present the first end-to-end solution to create high-quality freeviewpoint video encoded as a compact data stream. Our system records performances using a dense set of RGB and IR video cameras, generates dynamic textured surfaces, and compresses these to a streamable 3D video format. Four technical advances contribute to high fidelity and robustness: multimodal multi-view stereo fusing RGB, IR, and silhouette information; adaptive meshing guided by automatic detection of perceptually salient areas; mesh tracking to create temporally coherent subsequences; and encoding of tracked textured meshes as an MPEG video stream. Quantitative experiments demonstrate geometric accuracy, texture fidelity, and encoding efficiency. We release several datasets with calibrated inputs and processed results to foster future research.

This method provides an effective quality control mechanism for evaluating the DVHs of the OARs. Adoption of such a method will advance the quality of current IMRT planning, providing better treatment plan consistency.

Abstract. In this paper we address the challenge of matching patient geometry to facilitate the design of patient treatment plans in radiotherapy. To this end we propose a novel shape descriptor, the Overlap Volume Histogram, which provides a rotation and translation invariant representation of a patient's organs at risk relative to the tumor volume. Using our descriptor, it is possible to accurately identify database patients with similar constellations of organ and tumor geometries, enabling the transfer of treatment plans between patients with similar geometries. We demonstrate the utility of our method for such tasks by outperforming state of the art shape descriptors in the retrieval of patients with similar treatment plans. We also preliminarily show its potential as a quality control tool by demonstrating how it is used to identify an organ at risk whose dose can be significantly reduced.

Abstract

Input range scans Oriented points and depth hull SPR SPR w/ Dirichlet envelope RMS = 7.8 × 10 −3 RMS = 3.8 × 10 −3 Figure 1: Given a collection of range scans, one can obtain a set of oriented points and a depth hull volume. (Points are colored by normal orientation.) Applying traditional Screened Poisson Reconstruction (SPR) to the oriented points yields a surface with unwanted artifacts in regions with missing data. By incorporating the depth hull as a Dirichlet constraint within the global Poisson formulation, we prevent the emergence of extraneous surfaces, resulting in a more accurate model.