图形学
This work investigates how weight and pressure can function as haptic metaphors to support user interface notifications in Virtual Reality (VR). While prior research has explored ungrounded weight simulation and pneumatic feedback, their…
Joint rendering and deformation of mesh and 3D Gaussian Splatting (3DGS) have significant value as both representa tions offer complementary advantages for graphics applica tions. However, due to differences in representation and ren dering…
High-quality motion data underpins games, film, XR, and robotics. Vision-based motion capture tools have made significant progress, offering accessible and visually convincing results, yet often fall short in the final stretch -- the last…
Model reduction is essential for real-time simulation of deformable objects. Linear techniques such as PCA provide structured and predictable behavior, but their limited expressiveness restricts accuracy under large or nonlinear…
In order to be widely applicable, speech-driven 3D head avatars must articulate their lips in accordance with speech, while also conveying the appropriate emotions with dynamically changing facial expressions. The key problem is that…
Free-Viewpoint Video (FVV) reconstruction enables photorealistic and interactive 3D scene visualization; however, real-time streaming is often bottlenecked by sparse-view inputs, prohibitive training costs, and bandwidth constraints. While…
Stylized motion generation is actively studied in computer graphics, especially benefiting from the rapid advances in diffusion models. The goal of this task is to produce a novel motion respecting both the motion content and the desired…
Materials used in real clothing exhibit remarkable complexity and spatial variation due to common processes such as stitching, hemming, dyeing, printing, padding, and bonding. Simulating these materials, for instance using finite element…
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…
Radiance field-based rendering methods have attracted significant interest from the computer vision and computer graphics communities. They enable high-fidelity rendering with complex real-world lighting effects, but at the cost of high…
We live in a world filled with anisotropy, a ubiquitous characteristic of both natural and engineered systems. In this study, we concentrate on space deformation and introduce \textit{anisotropic Green coordinates}, which provide versatile…
Creating high-fidelity, real-time drivable 3D head avatars is a core challenge in digital animation. While 3D Gaussian Splashing (3D-GS) offers unprecedented rendering speed and quality, current animation techniques often rely on a…
Holographic displays offer significant potential for augmented and virtual reality applications by reconstructing wavefronts that enable continuous depth cues and natural parallax without vergence-accommodation conflict. However, despite…
Generating 3D models has traditionally been a complex task requiring specialized expertise. While recent advances in generative AI have sought to automate this process, existing methods produce non-editable representation, such as meshes or…
3D Gaussian Splatting (3DGS) is a technique to create high-quality, real-time 3D scenes from images. This method often produces visual artifacts known as floaters--nearly transparent, disconnected elements that drift in space away from the…
MimicKit is an open-source framework for training motion controllers using motion imitation and reinforcement learning. The codebase provides implementations of commonly-used motion-imitation techniques and RL algorithms. This framework is…
Diffusion-based talking head models generate high-quality, photorealistic videos but suffer from slow inference, limiting practical applications. Existing acceleration methods for general diffusion models fail to exploit the temporal and…
Transfer learning of diffusion models to smaller target domains is challenging, as naively fine-tuning the model often results in poor generalization. Test-time guidance methods help mitigate this by offering controllable improvements in…
With the rapid development of AI-generated content (AIGC), video generation has emerged as one of its most dynamic and impactful subfields. In particular, the advancement of video generation foundation models has led to growing demand for…
We introduce Reflectance Diffusion, a new neural text-to-texture model capable of generating high-fidelity SVBRDF maps from textual descriptions. Our method leverages a tandem neural approach, consisting of two modules, to accurately model…