Optical motion capture (MoCap) is the "gold standard" for accurately capturing full-body motions. To make use of raw MoCap point data, the system labels the points with corresponding body part locations and solves the full-body motions. However, MoCap data often contains mislabeling, occlusion and positional errors, requiring extensive manual correction. To alleviate this burden, we introduce RoMo, a learning-based framework for robustly labeling and solving raw optical motion capture data. In the labeling stage, RoMo employs a divide-and-conquer strategy to break down the complex full-body labeling challenge into manageable subtasks: alignment, full-body segmentation and part-specific labeling. To utilize the temporal continuity of markers, RoMo generates marker tracklets using a K-partite graph-based clustering algorithm, where markers serve as nodes, and edges are formed based on positional and feature similarities. For motion solving, to prevent error accumulation along the kinematic chain, we introduce a hybrid inverse kinematic solver that utilizes joint positions as intermediate representations and adjusts the template skeleton to match estimated joint positions. We demonstrate that RoMo achieves high labeling and solving accuracy across multiple metrics and various datasets. Extensive comparisons show that our method outperforms state-of-the-art research methods. On a real dataset, RoMo improves the F1 score of hand labeling from 0.94 to 0.98, and reduces joint position error of body motion solving by 25%. Furthermore, RoMo can be applied in scenarios where commercial systems are inadequate. The code and data for RoMo are available at https://github.com/non-void/RoMo.

Motion style transfer changes the style of a motion while retaining its content and is useful in computer animations and games. Contact is an essential component of motion style transfer that should be controlled explicitly in order to express the style vividly while enhancing motion naturalness and quality. However, it is unknown how to decouple and control contact to achieve fine-grained control in motion style transfer. In this paper, we present a novel style transfer method for fine-grained control over contacts while achieving both motion naturalness and spatial-temporal variations of style. Based on our empirical evidence, we propose controlling contact indirectly through the hip velocity, which can be further decomposed into the trajectory and contact timing, respectively. To this end, we propose a new model that explicitly models the correlations between motions and trajectory/contact timing/style, allowing us to decouple and control each separately. Our approach is built around a motion manifold, where hip controls can be easily integrated into a Transformer-based decoder. It is versatile in that it can generate motions directly as well as be used as post-processing for existing methods to improve quality and contact controllability. In addition, we propose a new metric that measures a correlation pattern of motions based on our empirical evidence, aligning well with human perception in terms of motion naturalness. Based on extensive evaluation, our method outperforms existing methods in terms of style expressivity and motion quality.

Abstract We propose a novel ray reordering technique designed to accelerate the ray tracing process by encoding and sorting rays prior to traversal. Our method, called “hierarchy cut code”, involves encoding rays based on the cuts of the hierarchical acceleration structure, rather than relying solely on spatial coordinates. This approach allows for a more effective adaptation to the acceleration structure, resulting in a more reliable and efficient encoding outcome. Furthermore, our research identifies “bounding drift” as a major obstacle in achieving better acceleration effects using longer sorting keys in existing reordering methods. Fortunately, our hierarchy cut code successfully overcomes this issue, providing improved performance in ray tracing. Experimental results demonstrate the effectiveness of our approach, showing up to a 1.81 times faster secondary ray tracing compared to existing methods. These promising results highlight the potential for further enhancement in the acceleration effect of reordering techniques, warranting further exploration and research in this exciting field.

We present a novel learning method using a two-stream network to predict cloth deformation for skeleton-based characters. The characters processed in our approach are not limited to humans, and can be other targets with skeleton-based representations such as fish or pets. We use a novel network architecture which consists of skeleton-based and mesh-based residual networks to learn the coarse features and wrinkle features forming the overall residual from the template cloth mesh. Our network may be used to predict the deformation for loose or tight-fitting clothing. The memory footprint of our network is low, thereby resulting in reduced computational requirements. In practice, a prediction for a single cloth mesh for a skeleton-based character takes about 7 ms on an nVidia GeForce RTX 3090 GPU. Compared to prior methods, our network can generate finer deformation results with details and wrinkles.

Recent advancements in 2D diffusion models allow appearance generation on untextured raw meshes. These methods create RGB textures by distilling a 2D diffusion model, which often contains unwanted baked-in shading effects and results in unrealistic rendering effects in the downstream applications. Generating Physically Based Rendering (PBR) materials instead of just RGB textures would be a promising solution. However, directly distilling the PBR material parameters from 2D diffusion models still suffers from incorrect material decomposition, such as baked-in shading effects in albedo. We introduce DreamMat , an innovative approach to resolve the aforementioned problem, to generate high-quality PBR materials from text descriptions. We find out that the main reason for the incorrect material distillation is that large-scale 2D diffusion models are only trained to generate final shading colors, resulting in insufficient constraints on material decomposition during distillation. To tackle this problem, we first finetune a new light-aware 2D diffusion model to condition on a given lighting environment and generate the shading results on this specific lighting condition. Then, by applying the same environment lights in the material distillation, DreamMat can generate high-quality PBR materials that are not only consistent with the given geometry but also free from any baked-in shading effects in albedo. Extensive experiments demonstrate that the materials produced through our methods exhibit greater visual appeal to users and achieve significantly superior rendering quality compared to baseline methods, which are preferable for downstream tasks such as game and film production.

Optimizing the memory footprint of 3D models can have a major impact on the user experiences during real-time rendering and streaming visualization, where the major memory overhead lies in the high-resolution texture data. In this work, we propose a robust and automatic pipeline to content-aware, lossy compression for texture atlas. The design of our solution lies in two observations: 1) mapping multiple surface patches to the same texture region is seamlessly compatible with the standard rendering pipeline, requiring no decompression before any usage; 2) a texture image has background regions and salient structural features, which can be handled separately to achieve a high compression rate. Accordingly, our method contains joint operations of image segmentation, re-meshing, UV unwrapping, and texture baking. To evaluate the efficacy of our approach, we batch-processed a dataset containing 100 models collected online. On average, our method achieves a texture atlas compression ratio of 81.41% with an averaged PSNR and MS-SSIM scores of 40.90 and 0.98, a marginal error in visual appearance.

We present a novel locality-based learning method for cleaning and solving optical motion capture data. Given noisy marker data, we propose a new heterogeneous graph neural network which treats markers and joints as different types of nodes, and uses graph convolution operations to extract the local features of markers and joints and transform them to clean motions. To deal with anomaly markers (e.g. occluded or with big tracking errors), the key insight is that a marker’s motion shows strong correlations with the motions of its immediate neighboring markers but less so with other markers, a.k.a. locality, which enables us to efficiently fill missing markers (e.g. due to occlusion). Additionally, we also identify marker outliers due to tracking errors by investigating their acceleration profiles. Finally, we propose a training regime based on representation learning and data augmentation, by training the model on data with masking. The masking schemes aim to mimic the occluded and noisy markers often observed in the real data. Finally, we show that our method achieves high accuracy on multiple metrics across various datasets. Extensive comparison shows our method outperforms state-of-the-art methods in terms of prediction accuracy of occluded marker position error by approximately 20%, which leads to a further error reduction on the reconstructed joint rotations and positions by 30%. The code and data for this paper are available at https://github.com/non-void/LocalMoCap.

Abstract We propose a three‐stage network that utilizes a skinning‐based model to accurately predict dynamic cloth deformation. Our approach decomposes cloth deformation into three distinct components: static, coarse dynamic, and wrinkle dynamic components. To capture these components, we train our three‐stage network accordingly. In the first stage, the static component is predicted by constructing a static skinning model that incorporates learned joint increments and skinning weight increments. Then, in the second stage, the coarse dynamic component is added to the static skinning model by incorporating serialized skeleton information. Finally, in the third stage, the mesh sequence stage refines the prediction by incorporating the wrinkle dynamic component using serialized mesh information. We have implemented our network and used it in a Unity game scene, enabling real‐time prediction of cloth dynamics. Our implementation achieves impressive prediction speeds of approximately 3.65ms using an NVIDIA GeForce RTX 3090 GPU and 9.66ms on an Intel i7‐7700 CPU. Compared to SOTA methods, our network excels in accurately capturing fine dynamic cloth deformations.

Abstract Character hit reaction is an inherent component in game development. Natural hit reactions in games are typically achieved through the use of artist‐created hit animations and motion capture. To improve the realism of impact reactions, game developers combine physics simulation with distinct hit animations based on character statuses. However, there is currently no method that can automatically produce hit reactions based on hit information in game development. To this end, we propose a physics‐driven inverse kinematic method for generating character reaction animations. We postulate that a character's hit reactions are the result of an assault impulse spreading throughout the body and forcing the body to move. Five IK (inverse kinematics) solvers are used to control character poses. Each IK solver is used to control the movement of a different part of the body. The IK solvers, which are used to determine the positions of various bodily parts, are driven by unconstrained physics simulation. Furthermore, physics simulation with constraints is used to fine‐tune the character's movements. Experiment results show that our method outperforms Unreal Engine‐based hit animation and physics simulation.

Real-time in-between motion generation is universally required in games and highly desirable in existing animation pipelines. Its core challenge lies in the need to satisfy three critical conditions simultaneously: quality, controllability and speed , which renders any methods that need offline computation (or post-processing) or cannot incorporate (often unpredictable) user control undesirable. To this end, we propose a new real-time transition method to address the aforementioned challenges. Our approach consists of two key components: motion manifold and conditional transitioning. The former learns the important low-level motion features and their dynamics; while the latter synthesizes transitions conditioned on a target frame and the desired transition duration. We first learn a motion manifold that explicitly models the intrinsic transition stochasticity in human motions via a multi-modal mapping mechanism. Then, during generation, we design a transition model which is essentially a sampling strategy to sample from the learned manifold, based on the target frame and the aimed transition duration. We validate our method on different datasets in tasks where no post-processing or offline computation is allowed. Through exhaustive evaluation and comparison, we show that our method is able to generate high-quality motions measured under multiple metrics. Our method is also robust under various target frames (with extreme cases).