arXiv subjects

Jun Saito

Publications and source records attributed to Jun Saito.

At least 19 recordsLinked to original sources

arXiv2026

SOMA: Unifying Parametric Human Body Models

Parametric human body models are foundational to human reconstruction, animation, and simulation, yet they remain mutually incompatible: SMPL, SMPL-X, MHR, Anny, and related models each diverge in mesh topology, skeletal structure, shape parameterization, and unit convention, making it impractical to exploit their complementary strengths within a single pipeline. We present SOMA, a unified body layer that bridges these heterogeneous representations through three abstraction layers. Mesh topology abstraction maps any source model's identity to a shared canonical mesh in constant time per vertex. Skeletal abstraction recovers a full set of identity-adapted joint transforms from any body shape, whether in rest pose or an arbitrary posed configuration, in a single closed-form pass, with no iterative optimization or per-model training. Pose abstraction inverts the skinning pipeline to recover unified skeleton rotations directly from posed vertices of any supported model, enabling heterogeneous motion datasets to be consumed without custom retargeting. Together, these layers reduce the $O(M^2)$ per-pair adapter problem to $O(M)$ single-backend connectors, letting practitioners freely mix identity sources and pose data at inference time. The entire pipeline is fully differentiable end-to-end and GPU-accelerated via NVIDIA-Warp.

cs.CV↗

arXiv2024

Gauge Covariant Link Formulation of Twisted N=D=4 and N=4 D=5 Super Yang-Mills on a Lattice

We propose a lattice formulation of four dimensional super Yang-Mills model with a twisted N=4 supersymmetry in a manifestly gauge covariant manner. The formulation we employ here is a four dimensional extension of the manifestly gauge covariant method which was developed in our proposals of Dirac-Kahler twisted N=D=2 and N=4 D=3 super Yang-Mills on a lattice. Twisted N=4 supersymmetry algebra is geometrically realized on a four dimensional lattice with link supercharges and the use of link (anti-)commutators. Employing Grassmann parameters with link nature, we explicitly show that the resulting super Yang-Mills action is invariant under all the supercharges on a lattice without chiral fermion problems. As a group and algebraic interpretation of the link approach, we show that promoting bosonic supercovariant derivatives to their exponentials consistently with the lattice Leibniz rule naturally gives rise to the notion of gauge covariant link (anti-)commutators. This can be regarded as a fermionic decomposition of a Lie group element, which may provide a new methodology in super Lie group and super Lie algebra. We also provide a five dimensional lift-up of the formulation with exact N=4 SUSY invariance on a five dimensional lattice.

hep-lat↗

arXiv2024

Instant Facial Gaussians Translator for Relightable and Interactable Facial Rendering

We propose GauFace, a novel Gaussian Splatting representation, tailored for efficient animation and rendering of physically-based facial assets. Leveraging strong geometric priors and constrained optimization, GauFace ensures a neat and structured Gaussian representation, delivering high fidelity and real-time facial interaction of 30fps@1440p on a Snapdragon 8 Gen 2 mobile platform. Then, we introduce TransGS, a diffusion transformer that instantly translates physically-based facial assets into the corresponding GauFace representations. Specifically, we adopt a patch-based pipeline to handle the vast number of Gaussians effectively. We also introduce a novel pixel-aligned sampling scheme with UV positional encoding to ensure the throughput and rendering quality of GauFace assets generated by our TransGS. Once trained, TransGS can instantly translate facial assets with lighting conditions to GauFace representation, With the rich conditioning modalities, it also enables editing and animation capabilities reminiscent of traditional CG pipelines. We conduct extensive evaluations and user studies, compared to traditional offline and online renderers, as well as recent neural rendering methods, which demonstrate the superior performance of our approach for facial asset rendering. We also showcase diverse immersive applications of facial assets using our TransGS approach and GauFace representation, across various platforms like PCs, phones and even VR headsets.

cs.GR↗

arXiv2024

Motion-Driven Neural Optimizer for Prophylactic Braces Made by Distributed Microstructures

Joint injuries, and their long-term consequences, present a substantial global health burden. Wearable prophylactic braces are an attractive potential solution to reduce the incidence of joint injuries by limiting joint movements that are related to injury risk. Given human motion and ground reaction forces, we present a computational framework that enables the design of personalized braces by optimizing the distribution of microstructures and elasticity. As varied brace designs yield different reaction forces that influence kinematics and kinetics analysis outcomes, the optimization process is formulated as a differentiable end-to-end pipeline in which the design domain of microstructure distribution is parameterized onto a neural network. The optimized distribution of microstructures is obtained via a self-learning process to determine the network coefficients according to a carefully designed set of losses and the integrated biomechanical and physical analyses. Since knees and ankles are the most commonly injured joints, we demonstrate the effectiveness of our pipeline by designing, fabricating, and testing prophylactic braces for the knee and ankle to prevent potentially harmful joint movements.

physics.med-ph↗

arXiv2023

GroundLink: A Dataset Unifying Human Body Movement and Ground Reaction Dynamics

The physical plausibility of human motions is vital to various applications in fields including but not limited to graphics, animation, robotics, vision, biomechanics, and sports science. While fully simulating human motions with physics is an extreme challenge, we hypothesize that we can treat this complexity as a black box in a data-driven manner if we focus on the ground contact, and have sufficient observations of physics and human activities in the real world. To prove our hypothesis, we present GroundLink, a unified dataset comprised of captured ground reaction force (GRF) and center of pressure (CoP) synchronized to standard kinematic motion captures. GRF and CoP of GroundLink are not simulated but captured at high temporal resolution using force platforms embedded in the ground for uncompromising measurement accuracy. This dataset contains 368 processed motion trials (~1.59M recorded frames) with 19 different movements including locomotion and weight-shifting actions such as tennis swings to signify the importance of capturing physics paired with kinematics. GroundLinkNet, our benchmark neural network model trained with GroundLink, supports our hypothesis by predicting GRFs and CoPs accurately and plausibly on unseen motions from various sources. The dataset, code, and benchmark models are made public for further research on various downstream tasks leveraging the rich physics information at https://csr.bu.edu/groundlink/.

cs.GR↗

arXiv2023

Neural Face Rigging for Animating and Retargeting Facial Meshes in the Wild

We propose an end-to-end deep-learning approach for automatic rigging and retargeting of 3D models of human faces in the wild. Our approach, called Neural Face Rigging (NFR), holds three key properties: (i) NFR's expression space maintains human-interpretable editing parameters for artistic controls; (ii) NFR is readily applicable to arbitrary facial meshes with different connectivity and expressions; (iii) NFR can encode and produce fine-grained details of complex expressions performed by arbitrary subjects. To the best of our knowledge, NFR is the first approach to provide realistic and controllable deformations of in-the-wild facial meshes, without the manual creation of blendshapes or correspondence. We design a deformation autoencoder and train it through a multi-dataset training scheme, which benefits from the unique advantages of two data sources: a linear 3DMM with interpretable control parameters as in FACS, and 4D captures of real faces with fine-grained details. Through various experiments, we show NFR's ability to automatically produce realistic and accurate facial deformations across a wide range of existing datasets as well as noisy facial scans in-the-wild, while providing artist-controlled, editable parameters.

cs.GR↗

arXiv2022

NeMF: Neural Motion Fields for Kinematic Animation

We present an implicit neural representation to learn the spatio-temporal space of kinematic motions. Unlike previous work that represents motion as discrete sequential samples, we propose to express the vast motion space as a continuous function over time, hence the name Neural Motion Fields (NeMF). Specifically, we use a neural network to learn this function for miscellaneous sets of motions, which is designed to be a generative model conditioned on a temporal coordinate $t$ and a random vector $z$ for controlling the style. The model is then trained as a Variational Autoencoder (VAE) with motion encoders to sample the latent space. We train our model with a diverse human motion dataset and quadruped dataset to prove its versatility, and finally deploy it as a generic motion prior to solve task-agnostic problems and show its superiority in different motion generation and editing applications, such as motion interpolation, in-betweening, and re-navigating. More details can be found on our project page: https://cs.yale.edu/homes/che/projects/nemf/.

cs.CV↗

arXiv2022

Skeleton-free Pose Transfer for Stylized 3D Characters

We present the first method that automatically transfers poses between stylized 3D characters without skeletal rigging. In contrast to previous attempts to learn pose transformations on fixed or topology-equivalent skeleton templates, our method focuses on a novel scenario to handle skeleton-free characters with diverse shapes, topologies, and mesh connectivities. The key idea of our method is to represent the characters in a unified articulation model so that the pose can be transferred through the correspondent parts. To achieve this, we propose a novel pose transfer network that predicts the character skinning weights and deformation transformations jointly to articulate the target character to match the desired pose. Our method is trained in a semi-supervised manner absorbing all existing character data with paired/unpaired poses and stylized shapes. It generalizes well to unseen stylized characters and inanimate objects. We conduct extensive experiments and demonstrate the effectiveness of our method on this novel task.

cs.CV↗

arXiv2022

Audio-driven Neural Gesture Reenactment with Video Motion Graphs

Human speech is often accompanied by body gestures including arm and hand gestures. We present a method that reenacts a high-quality video with gestures matching a target speech audio. The key idea of our method is to split and re-assemble clips from a reference video through a novel video motion graph encoding valid transitions between clips. To seamlessly connect different clips in the reenactment, we propose a pose-aware video blending network which synthesizes video frames around the stitched frames between two clips. Moreover, we developed an audio-based gesture searching algorithm to find the optimal order of the reenacted frames. Our system generates reenactments that are consistent with both the audio rhythms and the speech content. We evaluate our synthesized video quality quantitatively, qualitatively, and with user studies, demonstrating that our method produces videos of much higher quality and consistency with the target audio compared to previous work and baselines.

cs.CV↗

arXiv2022

Neural Jacobian Fields: Learning Intrinsic Mappings of Arbitrary Meshes

This paper introduces a framework designed to accurately predict piecewise linear mappings of arbitrary meshes via a neural network, enabling training and evaluating over heterogeneous collections of meshes that do not share a triangulation, as well as producing highly detail-preserving maps whose accuracy exceeds current state of the art. The framework is based on reducing the neural aspect to a prediction of a matrix for a single given point, conditioned on a global shape descriptor. The field of matrices is then projected onto the tangent bundle of the given mesh, and used as candidate jacobians for the predicted map. The map is computed by a standard Poisson solve, implemented as a differentiable layer with cached pre-factorization for efficient training. This construction is agnostic to the triangulation of the input, thereby enabling applications on datasets with varying triangulations. At the same time, by operating in the intrinsic gradient domain of each individual mesh, it allows the framework to predict highly-accurate mappings. We validate these properties by conducting experiments over a broad range of scenarios, from semantic ones such as morphing, registration, and deformation transfer, to optimization-based ones, such as emulating elastic deformations and contact correction, as well as being the first work, to our knowledge, to tackle the task of learning to compute UV parameterizations of arbitrary meshes. The results exhibit the high accuracy of the method as well as its versatility, as it is readily applied to the above scenarios without any changes to the framework.

cs.GR↗

arXiv2022

FaceFormer: Speech-Driven 3D Facial Animation with Transformers

Speech-driven 3D facial animation is challenging due to the complex geometry of human faces and the limited availability of 3D audio-visual data. Prior works typically focus on learning phoneme-level features of short audio windows with limited context, occasionally resulting in inaccurate lip movements. To tackle this limitation, we propose a Transformer-based autoregressive model, FaceFormer, which encodes the long-term audio context and autoregressively predicts a sequence of animated 3D face meshes. To cope with the data scarcity issue, we integrate the self-supervised pre-trained speech representations. Also, we devise two biased attention mechanisms well suited to this specific task, including the biased cross-modal multi-head (MH) attention and the biased causal MH self-attention with a periodic positional encoding strategy. The former effectively aligns the audio-motion modalities, whereas the latter offers abilities to generalize to longer audio sequences. Extensive experiments and a perceptual user study show that our approach outperforms the existing state-of-the-arts. The code will be made available.

cs.CV↗

arXiv2021

Joint Audio-Text Model for Expressive Speech-Driven 3D Facial Animation

Speech-driven 3D facial animation with accurate lip synchronization has been widely studied. However, synthesizing realistic motions for the entire face during speech has rarely been explored. In this work, we present a joint audio-text model to capture the contextual information for expressive speech-driven 3D facial animation. The existing datasets are collected to cover as many different phonemes as possible instead of sentences, thus limiting the capability of the audio-based model to learn more diverse contexts. To address this, we propose to leverage the contextual text embeddings extracted from the powerful pre-trained language model that has learned rich contextual representations from large-scale text data. Our hypothesis is that the text features can disambiguate the variations in upper face expressions, which are not strongly correlated with the audio. In contrast to prior approaches which learn phoneme-level features from the text, we investigate the high-level contextual text features for speech-driven 3D facial animation. We show that the combined acoustic and textual modalities can synthesize realistic facial expressions while maintaining audio-lip synchronization. We conduct the quantitative and qualitative evaluations as well as the perceptual user study. The results demonstrate the superior performance of our model against existing state-of-the-art approaches.

cs.CV↗

arXiv2021

Contact-Aware Retargeting of Skinned Motion

This paper introduces a motion retargeting method that preserves self-contacts and prevents interpenetration. Self-contacts, such as when hands touch each other or the torso or the head, are important attributes of human body language and dynamics, yet existing methods do not model or preserve these contacts. Likewise, interpenetration, such as a hand passing into the torso, are a typical artifact of motion estimation methods. The input to our method is a human motion sequence and a target skeleton and character geometry. The method identifies self-contacts and ground contacts in the input motion, and optimizes the motion to apply to the output skeleton, while preserving these contacts and reducing interpenetration. We introduce a novel geometry-conditioned recurrent network with an encoder-space optimization strategy that achieves efficient retargeting while satisfying contact constraints. In experiments, our results quantitatively outperform previous methods and we conduct a user study where our retargeted motions are rated as higher-quality than those produced by recent works. We also show our method generalizes to motion estimated from human videos where we improve over previous works that produce noticeable interpenetration.

cs.CV↗

arXiv2021

Stochastic Scene-Aware Motion Prediction

A long-standing goal in computer vision is to capture, model, and realistically synthesize human behavior. Specifically, by learning from data, our goal is to enable virtual humans to navigate within cluttered indoor scenes and naturally interact with objects. Such embodied behavior has applications in virtual reality, computer games, and robotics, while synthesized behavior can be used as a source of training data. This is challenging because real human motion is diverse and adapts to the scene. For example, a person can sit or lie on a sofa in many places and with varying styles. It is necessary to model this diversity when synthesizing virtual humans that realistically perform human-scene interactions. We present a novel data-driven, stochastic motion synthesis method that models different styles of performing a given action with a target object. Our method, called SAMP, for Scene-Aware Motion Prediction, generalizes to target objects of various geometries while enabling the character to navigate in cluttered scenes. To train our method, we collected MoCap data covering various sitting, lying down, walking, and running styles. We demonstrate our method on complex indoor scenes and achieve superior performance compared to existing solutions. Our code and data are available for research at https://samp.is.tue.mpg.de.

cs.CV↗

arXiv2020

Neural Puppet: Generative Layered Cartoon Characters

We propose a learning based method for generating new animations of a cartoon character given a few example images. Our method is designed to learn from a traditionally animated sequence, where each frame is drawn by an artist, and thus the input images lack any common structure, correspondences, or labels. We express pose changes as a deformation of a layered 2.5D template mesh, and devise a novel architecture that learns to predict mesh deformations matching the template to a target image. This enables us to extract a common low-dimensional structure from a diverse set of character poses. We combine recent advances in differentiable rendering as well as mesh-aware models to successfully align common template even if only a few character images are available during training. In addition to coarse poses, character appearance also varies due to shading, out-of-plane motions, and artistic effects. We capture these subtle changes by applying an image translation network to refine the mesh rendering, providing an end-to-end model to generate new animations of a character with high visual quality. We demonstrate that our generative model can be used to synthesize in-between frames and to create data-driven deformation. Our template fitting procedure outperforms state-of-the-art generic techniques for detecting image correspondences.

cs.CV↗

arXiv2019

Minimally Supervised Learning of Affective Events Using Discourse Relations

Recognizing affective events that trigger positive or negative sentiment has a wide range of natural language processing applications but remains a challenging problem mainly because the polarity of an event is not necessarily predictable from its constituent words. In this paper, we propose to propagate affective polarity using discourse relations. Our method is simple and only requires a very small seed lexicon and a large raw corpus. Our experiments using Japanese data show that our method learns affective events effectively without manually labeled data. It also improves supervised learning results when labeled data are small.

cs.CL↗

arXiv2017

An Alternative Lattice Field Theory Formulation Inspired by Lattice Supersymmetry -Summary of the Formulation-

We propose a lattice field theory formulation which overcomes some fundamental difficulties in realizing exact supersymmetry on the lattice. The Leibniz rule for the difference operator can be recovered by defining a new product on the lattice, the star product, and the chiral fermion species doublers degrees of freedom can be avoided consistently. This framework is general enough to formulate non-supersymmetric lattice field theory without chiral fermion problem. This lattice formulation has a nonlocal nature and is essentially equivalent to the corresponding continuum theory. We can show that the locality of the star product is recovered exponentially in the continuum limit. Possible regularization procedures are proposed.The associativity of the product and the lattice translational invariance of the formulation will be discussed.

hep-lat↗

arXiv2017

An Alternative Lattice Field Theory Formulation Inspired by Lattice Supersymmetry

We propose an unconventional formulation of lattice field theories which is quite general, although originally motivated by the quest of exact lattice supersymmetry. Two long standing problems have a solution in this context: 1) Each degree of freedom on the lattice corresponds to $2^d$ degrees of freedom in the continuum, but all these doublers have (in the case of fermions) the same chirality and can be either identified, thus removing the degeneracy, or, in some theories with extended supersymmetry, identified with different members of the same supermultiplet. 2) The derivative operator, defined on the lattice as a suitable periodic function of the lattice momentum, is an addittive and conserved quantity, thus assuring that the Leibnitz rule is satisfied. This implies that the product of two fields on the lattice is replaced by a non-local "star product" which is however in general non-associative. Associativity of the "star product" poses strong restrictions on the form of the lattice derivative operator (which becomes the inverse gudermannian function of the lattice momentum) and has the consequence that the degrees of freedom of the lattice theory and of the continuum theory are in one-to-one correspondence, so that the two theories are eventually equivalent. Regularization of the ultraviolet divergences on the lattice is not associated to the lattice spacing, which does not act as a regulator, but may be obtained by a one parameter deformation of the lattice derivative, thus preserving the lattice structure even in the limit of infinite momentum cutoff. However this regularization breaks gauge invariance and a gauge invariant regularization within the lattice formulation is still lacking.

hep-lat↗