Search

Optical motion capture (mocap) requires accurately reconstructing the human body from retroreflective markers, including pose and shape. In a typical mocap setting, marker labeling is an important but tedious and error-prone step. Previous work has shown that marker labeling can be automated by using a structured template defining specific marker placements, but this places additional recording constraints. We propose to relax these constraints and solve for Unstructured Unlabeled Optical (UUO) mocap. Compared to the typical mocap setting that either labels markers or places them w.r.t a structured layout, markers in UUO mocap can be placed anywhere on the body and even on one specific limb (e.g., right leg for biomechanics research), hence it is of more practical significance. It is also more challenging. To solve UUO mocap, we exploit a monocular video captured by a single RGB camera, which does not require camera calibration. On this video, we run an off-the-shelf method to reconstruct and track a human individual, giving strong visual priors of human body pose and shape. With both the video and UUO markers, we propose an optimization pipeline towards marker identification, marker labeling, human pose estimation, and human body reconstruction. Our technical novelties include multiple hypothesis testing to optimize global orientation, and marker localization and marker-part matching to better optimize for body surface. We conduct extensive experiments to quantitatively compare our method against state-of-the-art approaches, including marker-only mocap and video-only human body/shape reconstruction. Experiments demonstrate that our method resoundingly outperforms existing methods on three established benchmark datasets for both full-body and partial-body reconstruction.

We investigate how to use AI-based analytics to support design education. The analytics at hand measure multiscale design, that is, students' use of space and scale to visually and conceptually organize their design work. With the goal of making the analytics intelligible to instructors, we developed a research artifact integrating a design analytics dashboard with design instances, and the design environment that students use to create them. We theorize about how Suchman's notion of mutual intelligibility requires contextualized investigation of AI in order to develop findings about how analytics work for people. We studied the research artifact in 5 situated course contexts, in 3 departments. A total of 236 students used the multiscale design environment. The 9 instructors who taught those students experienced the analytics via the new research artifact. We derive findings from a qualitative analysis of interviews with instructors regarding their experiences. Instructors reflected on how the analytics and their presentation in the dashboard have the potential to affect design education. We develop research implications addressing: (1) how indexing design analytics in the dashboard to actual design work instances helps design instructors reflect on what they mean and, more broadly, is a technique for how AI-based design analytics can support instructors' assessment and feedback experiences in situated course contexts; and (2) how multiscale design analytics, in particular, have the potential to support design education. By indexing, we mean linking which provides context, here connecting the numbers of the analytics with visually annotated design work instances., Comment: 22 pages, 4 figures, Submitted to ACM DIS

Neural implicit fields, such as the neural signed distance field (SDF) of a shape, have emerged as a powerful representation for many applications, e.g., encoding a 3D shape and performing collision detection. Typically, implicit fields are encoded by Multi-layer Perceptrons (MLP) with positional encoding (PE) to capture high-frequency geometric details. However, a notable side effect of such PE-equipped MLPs is the noisy artifacts present in the learned implicit fields. While increasing the sampling rate could in general mitigate these artifacts, in this paper we aim to explain this adverse phenomenon through the lens of Fourier analysis. We devise a tool to determine the appropriate sampling rate for learning an accurate neural implicit field without undesirable side effects. Specifically, we propose a simple yet effective method to estimate the intrinsic frequency of a given network with randomized weights based on the Fourier analysis of the network's responses. It is observed that a PE-equipped MLP has an intrinsic frequency much higher than the highest frequency component in the PE layer. Sampling against this intrinsic frequency following the Nyquist-Sannon sampling theorem allows us to determine an appropriate training sampling rate. We empirically show in the setting of SDF fitting that this recommended sampling rate is sufficient to secure accurate fitting results, while further increasing the sampling rate would not further noticeably reduce the fitting error. Training PE-equipped MLPs simply with our sampling strategy leads to performances superior to the existing methods.

The recent surge of utilizing deep neural networks for geometric processing and shape modeling has opened up exciting avenues. However, there is a conspicuous lack of research efforts on using powerful neural representations to extend the capabilities of parametric surfaces, which are the prevalent surface representations in product design, CAD/CAM, and computer animation. We present Neural Parametric Surfaces, the first piecewise neural surface representation that allows coarse patch layouts of arbitrary $n$-sided surface patches to model complex surface geometries with high precision, offering greater flexibility over traditional parametric surfaces. By construction, this new surface representation guarantees $G^0$ continuity between adjacent patches and empirically achieves $G^1$ continuity, which cannot be attained by existing neural patch-based methods. The key ingredient of our neural parametric surface is a learnable feature complex $\mathcal{C}$ that is embedded in a high-dimensional space $\mathbb{R}^D$ and topologically equivalent to the patch layout of the surface; each face cell of the complex is defined by interpolating feature vectors at its vertices. The learned feature complex is mapped by an MLP-encoded function $f:\mathcal{C} \rightarrow \mathcal{S}$ to produce the neural parametric surface $\mathcal{S}$. We present a surface fitting algorithm that optimizes the feature complex $\mathcal{C}$ and trains the neural mapping $f$ to reconstruct given target shapes with high accuracy. We further show that the proposed representation along with a compact-size neural net can learn a plausible shape space from a shape collection, which can be used for shape interpolation or shape completion from noisy and incomplete input data. Extensive experiments show that neural parametric surfaces offer greater modeling capabilities than traditional parametric surfaces., Comment: 17 pages, 16 figures

We propose a method, named DualMesh-UDF, to extract a surface from unsigned distance functions (UDFs), encoded by neural networks, or neural UDFs. Neural UDFs are becoming increasingly popular for surface representation because of their versatility in presenting surfaces with arbitrary topologies, as opposed to the signed distance function that is limited to representing a closed surface. However, the applications of neural UDFs are hindered by the notorious difficulty in extracting the target surfaces they represent. Recent methods for surface extraction from a neural UDF suffer from significant geometric errors or topological artifacts due to two main difficulties: (1) A UDF does not exhibit sign changes; and (2) A neural UDF typically has substantial approximation errors. DualMesh-UDF addresses these two difficulties. Specifically, given a neural UDF encoding a target surface $\bar{S}$ to be recovered, we first estimate the tangent planes of $\bar{S}$ at a set of sample points close to $\bar{S}$. Next, we organize these sample points into local clusters, and for each local cluster, solve a linear least squares problem to determine a final surface point. These surface points are then connected to create the output mesh surface, which approximates the target surface. The robust estimation of the tangent planes of the target surface and the subsequent minimization problem constitute our core strategy, which contributes to the favorable performance of DualMesh-UDF over other competing methods. To efficiently implement this strategy, we employ an adaptive Octree. Within this framework, we estimate the location of a surface point in each of the octree cells identified as containing part of the target surface. Extensive experiments show that our method outperforms existing methods in terms of surface reconstruction quality while maintaining comparable computational efficiency., Comment: ICCV 2023

Neural implicit representations are known to be more compact for depicting 3D shapes than traditional discrete representations. However, the neural representations tend to round sharp corners or edges and struggle to represent surfaces with open boundaries. Moreover, they are slow to train. We present a unified neural implicit representation, called Patch-Grid, that fits to complex shapes efficiently, preserves sharp features, and effectively models surfaces with open boundaries and thin geometric features. Our superior efficiency comes from embedding each surface patch into a local latent volume and decoding it using a shared MLP decoder, which is pretrained on various local surface geometries. With this pretrained decoder fixed, fitting novel shapes and local shape updates can be done efficiently. The faithful preservation of sharp features is enabled by adopting a novel merge grid to perform local constructive solid geometry (CSG) combinations of surface patches in the cells of an adaptive Octree, yielding better robustness than using a global CSG construction as proposed in the literature. Experiments show that our Patch-Grid method faithfully captures shapes with complex sharp features, open boundaries and thin structures, and outperforms existing learning-based methods in both efficiency and quality for surface fitting and local shape updates.

This colloquium report presents four views on the future of student services in the two-year college. First, "Student Development Philosophy: A Perspective on the Past and Future," by Terry O'Banion, discusses the origins of the student development profession, the emerging "student development model," and the projected impact of the quality reformation, educational technology, finances, and the community college mission. Next, "Student Development and College Services: A Consumer Perspective," by Ernest R. Leach, reviews the "in loco parentis," student services, student development, and consumer models of student development and personnel services. In "Student Developers--Partners in Student Success," Lee Noel and Randi Levitz define the roles of the student services professional as the educational interpreter and the essential learning agent, contending that the key to attracting and retaining students is a focus on identifying and developing competencies for the information age. "A President's Perspective on Effective Leadership in Student Services," by Paul A. Elsner, asserts that integration of student and instructional services will be a necessary ingredient to successful educational programs, suggesting that a human resources management philosophy holds promise for student development professionals. The concluding presentation, "1984 Traverse City Statement: Toward the Future Vitality of Student Development Services," by John S. Keyser, reaffirms the philosophy and purpose of student development services in the two-year college, defines the major issues facing the profession, and puts forth an agenda for local and national action. (EJV)

This collection of papers explores various aspects of strategic planning at Linn-Benton Community College (LBCC). First, an overview is presented, clarifying what strategic planning is not and describing the strategic planning at LBCC and its objectives (i.e., to develop a plan utilizing community and internal assessments that can be developed into an action plan for the campus programs, to develop mechanisms for community involvement in planning, and to establish a financial plan that follows the strategic planning process). In addition, the overview identifies the four internal and external groups involved in the planning process and their roles. Next, a profile of LBCC as an institution in transition is presented, focusing on changes in the United States, in Oregon, and at LBCC. Then, environmental trends and planning assumptions that will affect LBCC are outlined in the areas of governance, finance, curriculum, student services, teaching/learning, staff development, students/enrollments, social and economic trends, job outlook, and outreach/public relations. A report on a survey conducted to prioritize college goals as a means of informing decisions about budget cuts is followed by a series of recommendations concerning the programs, services, and curriculum of the college. Finally, a chart is presented, identifying the programs at LBCC as declining, stable, or experiencing moderate growth. (HB)

This summary report presents a synthesis of discussions at a national colloquium on "Mastery Leadership in Student Development Services," sponsored by the American College Testing Program and the National Council on Student Development. Following introductory material on the colloquium,"Beyond Management to Leadership," by John S. Keyser, this report explores the difference between management and leadership, maintaining that the scientific study of leadership has been a neglected topic in graduate schools, which prepare most students to manage but not to lead. Keyser calls for a concern with "holistic leadership," that is, a synthesis of doing and defining and creating and anticipating. Next, in "Building and Maintaining Trust," Keyser encourages student development professionals to take the lead in managing trust, and suggests five trust-building strategies. "The Deployment of Self," by Richard D. Rowray, stresses the importance of self-leadership and self-management, concluding from interviews with exemplary admissions and guidance services officers that outstanding leadership is accompanied by high levels of positive self-regard. The final sections present position papers resulting from the 1985 colloquium and its predecessor: "1985 Traverse City Statement: Toward Mastery Leadership in Student Development Services" and "1984 Traverse City Statement: Toward the Future Vitality of Student Development Services." (RO)

In July 1986, a colloquium was convened to develop a position paper on access, assessment, and developmental education. This colloquium report contains the keynote speeches presented at the event, along with a statement developed by the participants regarding the issues. First, introductory material describes the purposes, sponsorship, and group processes of the colloquium. Next, the following speeches are presented: (1) "Are We Ready for the Future?" by R. Stephen Nicholson, which places access, assessment, and developmental education within a broad environmental context, and raises questions about the two-year college educators' readiness to deal with contemporary high risk populations; (2) "Access and Excellence: The Articulation Challenge among Urban High Schools, Community Colleges, and Four-Year Institutions," by Nolen M. Ellison and Janet D. Smith, which calls for an equity-based educational model built on the four dimensions of access, process, achievement, and transfer; (3) "Status of Testing Practices at Two-Year Postsecondary Institutions: Trends and Issues Affecting Minority Participation," by Jacqueline E. Woods and Ronald A. Williams, which summarizes the results and implications of a 1986 survey on testing practices in two-year colleges; and (4) "A Silver Anniversary Special: The Anatomy of Excellence in the Community College," by John E. Roueche, Suanne D. Roueche, and George A. Baker, which reviews the accomplishments and failures of the community college movement. Finally, the position paper, "Critical Issues in the Community College: Access, Assessment, and Developmental Education," is presented. (EJV)