Yiying Tong

Fizza Rubab, Yiying Tong, Arun Ross

Automated face recognition has made rapid strides over the past decade due to the unprecedented rise of deep neural network (DNN) models that can be trained for domain-specific tasks. At the same time, foundation models that are pretrained on broad vision or vision-language tasks have shown impressive generalization across diverse domains, including biometrics. This raises an important question: Do different DNN models--both domain-specific and foundation models--encode facial identity in similar ways, despite being trained on different datasets, loss functions, and architectures? In this regard, we directly analyze the geometric structure of embedding spaces imputed by different DNN models. Treating embeddings of face images as point clouds, we study whether simple affine transformations can align face representations of one model with another. Our findings reveal surprising cross-model compatibility: low-capacity linear mappings substantially improve cross-model face recognition over unaligned baselines for both face identification and verification tasks. Alignment patterns generalize across datasets and vary systematically across model families, indicating representational convergence in facial identity encoding. These findings have implications for model interoperability, ensemble design, and biometric template security.

Zhe Su, Yiying Tong, Guo-Wei Wei

Recently, topological data analysis has become a trending topic in data science and engineering. However, the key technique of topological data analysis, i.e., persistent homology, is defined on point cloud data, which does not work directly for data on manifolds. Although earlier evolutionary de Rham-Hodge theory deals with data on manifolds, it is inconvenient for machine learning applications because of the numerical inconsistency caused by remeshing the involving manifolds in the Lagrangian representation. In this work, we introduce persistent de Rham-Hodge Laplacian, or persistent Hodge Laplacian (PHL) as an abbreviation, for manifold topological learning. Our PHLs are constructed in the Eulerian representation via structure-persevering Cartesian grids, avoiding the numerical inconsistency over the multiscale manifolds. To facilitate the manifold topological learning, we propose a persistent Hodge Laplacian learning algorithm for data on manifolds or volumetric data. As a proof-of-principle application of the proposed manifold topological learning model, we consider the prediction of protein-ligand binding affinities with two benchmark datasets. Our numerical experiments highlight the power and promise of the proposed method.

Xiang Liu, Zhe Su, Yongyi Shi et al.

Recently, topological deep learning (TDL), which integrates algebraic topology with deep neural networks, has achieved tremendous success in processing point-cloud data, emerging as a promising paradigm in data science. However, TDL has not been developed for data on differentiable manifolds, including images, due to the challenges posed by differential topology. We address this challenge by introducing manifold topological deep learning (MTDL) for the first time. To highlight the power of Hodge theory rooted in differential topology, we consider a simple convolutional neural network (CNN) in MTDL. In this novel framework, original images are represented as smooth manifolds with vector fields that are decomposed into three orthogonal components based on Hodge theory. These components are then concatenated to form an input image for the CNN architecture. The performance of MTDL is evaluated using the MedMNIST v2 benchmark database, which comprises 717,287 biomedical images from eleven 2D and six 3D datasets. MTDL significantly outperforms other competing methods, extending TDL to a wide range of data on smooth manifolds.

Pilseo Park, Ze Zhang, Michel Sarkis et al.

High-fidelity reconstruction of head avatars from monocular videos is highly desirable for virtual human applications, but it remains a challenge in the fields of computer graphics and computer vision. In this paper, we propose a two-phase head avatar reconstruction network that incorporates a refined 3D mesh representation. Our approach, in contrast to existing methods that rely on coarse template-based 3D representations derived from 3DMM, aims to learn a refined mesh representation suitable for a NeRF that captures complex facial nuances. In the first phase, we train 3DMM-stored NeRF with an initial mesh to utilize geometric priors and integrate observations across frames using a consistent set of latent codes. In the second phase, we leverage a novel mesh refinement procedure based on an SDF constructed from the density field of the initial NeRF. To mitigate the typical noise in the NeRF density field without compromising the features of the 3DMM, we employ Laplace smoothing on the displacement field. Subsequently, we apply a second-phase training with these refined meshes, directing the learning process of the network towards capturing intricate facial details. Our experiments demonstrate that our method further enhances the NeRF rendering based on the initial mesh and achieves performance superior to state-of-the-art methods in reconstructing high-fidelity head avatars with such input.

Fizza Rubab, Yiying Tong

Recent advances in implicit neural representations have made them a popular choice for modeling 3D geometry, achieving impressive results in tasks such as shape representation, reconstruction, and learning priors. However, directly editing these representations poses challenges due to the complex relationship between model weights and surface regions they influence. Among such editing tools, sculpting, which allows users to interactively carve or extrude the surface, is a valuable editing operation to the graphics and modeling community. While traditional mesh-based tools like ZBrush facilitate fast and intuitive edits, a comparable toolkit for sculpting neural SDFs is currently lacking. We introduce a framework that enables interactive surface sculpting edits directly on neural implicit representations. Unlike previous works limited to spot edits, our approach allows users to perform stroke-based modifications on the fly, ensuring intuitive shape manipulation without switching representations. By employing tubular neighborhoods to sample strokes and custom brush profiles, we achieve smooth deformations along user-defined curves, providing precise control over the sculpting process. Our method demonstrates that intricate and versatile edits can be made while preserving the smooth nature of implicit representations.

Andrew Hou, Feng Liu, Zhiyuan Ren et al.

We propose INFAMOUS-NeRF, an implicit morphable face model that introduces hypernetworks to NeRF to improve the representation power in the presence of many training subjects. At the same time, INFAMOUS-NeRF resolves the classic hypernetwork tradeoff of representation power and editability by learning semantically-aligned latent spaces despite the subject-specific models, all without requiring a large pretrained model. INFAMOUS-NeRF further introduces a novel constraint to improve NeRF rendering along the face boundary. Our constraint can leverage photometric surface rendering and multi-view supervision to guide surface color prediction and improve rendering near the surface. Finally, we introduce a novel, loss-guided adaptive sampling method for more effective NeRF training by reducing the sampling redundancy. We show quantitatively and qualitatively that our method achieves higher representation power than prior face modeling methods in both controlled and in-the-wild settings. Code and models will be released upon publication.

Andrew Hou, Michel Sarkis, Ning Bi et al.

Most face relighting methods are able to handle diffuse shadows, but struggle to handle hard shadows, such as those cast by the nose. Methods that propose techniques for handling hard shadows often do not produce geometrically consistent shadows since they do not directly leverage the estimated face geometry while synthesizing them. We propose a novel differentiable algorithm for synthesizing hard shadows based on ray tracing, which we incorporate into training our face relighting model. Our proposed algorithm directly utilizes the estimated face geometry to synthesize geometrically consistent hard shadows. We demonstrate through quantitative and qualitative experiments on Multi-PIE and FFHQ that our method produces more geometrically consistent shadows than previous face relighting methods while also achieving state-of-the-art face relighting performance under directional lighting. In addition, we demonstrate that our differentiable hard shadow modeling improves the quality of the estimated face geometry over diffuse shading models.

Andrew Hou, Ze Zhang, Michel Sarkis et al.

Existing face relighting methods often struggle with two problems: maintaining the local facial details of the subject and accurately removing and synthesizing shadows in the relit image, especially hard shadows. We propose a novel deep face relighting method that addresses both problems. Our method learns to predict the ratio (quotient) image between a source image and the target image with the desired lighting, allowing us to relight the image while maintaining the local facial details. During training, our model also learns to accurately modify shadows by using estimated shadow masks to emphasize on the high-contrast shadow borders. Furthermore, we introduce a method to use the shadow mask to estimate the ambient light intensity in an image, and are thus able to leverage multiple datasets during training with different global lighting intensities. With quantitative and qualitative evaluations on the Multi-PIE and FFHQ datasets, we demonstrate that our proposed method faithfully maintains the local facial details of the subject and can accurately handle hard shadows while achieving state-of-the-art face relighting performance.

Max Budninskiy, Glorian Yin, Leman Feng et al.

Manifold learning offers nonlinear dimensionality reduction of high-dimensional datasets. In this paper, we bring geometry processing to bear on manifold learning by introducing a new approach based on metric connection for generating a quasi-isometric, low-dimensional mapping from a sparse and irregular sampling of an arbitrary manifold embedded in a high-dimensional space. Geodesic distances of discrete paths over the input pointset are evaluated through "parallel transport unfolding" (PTU) to offer robustness to poor sampling and arbitrary topology. Our new geometric procedure exhibits the same strong resilience to noise as one of the staples of manifold learning, the Isomap algorithm, as it also exploits all pairwise geodesic distances to compute a low-dimensional embedding. While Isomap is limited to geodesically-convex sampled domains, parallel transport unfolding does not suffer from this crippling limitation, resulting in an improved robustness to irregularity and voids in the sampling. Moreover, it involves only simple linear algebra, significantly improves the accuracy of all pairwise geodesic distance approximations, and has the same computational complexity as Isomap. Finally, we show that our connection-based distance estimation can be used for faster variants of Isomap such as L-Isomap.

P. Mullen, A. McKenzie, D. Pavlov et al.

In this paper, we present a numerical technique for performing Lie advection of arbitrary differential forms. Leveraging advances in high-resolution finite volume methods for scalar hyperbolic conservation laws, we first discretize the interior product (also called contraction) through integrals over Eulerian approximations of extrusions. This, along with Cartan's homotopy formula and a discrete exterior derivative, can then be used to derive a discrete Lie derivative. The usefulness of this operator is demonstrated through the numerical advection of scalar fields and 1-forms on regular grids.