图形学
Incompressibility is a fundamental condition in most fluid models. Accumulation of simulation errors violates it and causes volume loss. Past work suggested correction methods to battle it. These methods, however, are imperfect and in some…
We propose a novel discretization of tangent vector fields for triangle meshes. Starting with a Phong map continuously assigning normals to all points on the mesh, we define an extrinsic bases for continuous tangent vector fields by using…
Real-time visualization of large-scale volumetric data remains challenging, as direct volume rendering and voxel-based methods suffer from prohibitively high computational cost. We propose Variable Basis Mapping (VBM), a framework that…
OpenPBR is a physically based, standardized uber-shader developed for interoperable material authoring and rendering across VFX, animation, and design visualization workflows. This document serves as a companion to the official…
With the development of virtualization and AI, real-time facial avatar animation is widely used in entertainment, office, business and other fields. Against this background, blendshapes have become a common industry animation solution…
Dynamic 4D Gaussian Splatting (4DGS) effectively extends the high-speed rendering capabilities of 3D Gaussian Splatting (3DGS) to represent volumetric videos. However, the large number of Gaussians, substantial temporal redundancies, and…
Recent advancements in text-to-image (T2I) generation have led to the emergence of highly expressive models such as diffusion transformers (DiTs), exemplified by FLUX. However, their massive parameter sizes lead to slow inference, high…
Visualizing the large-scale datasets output by HPC resources presents a difficult challenge, as the memory and compute power required become prohibitively expensive for end user systems. Novel view synthesis techniques can address this by…
The use of floating bipolar electrodes in copper electro-winning cells represents an emerging technology that promises economic and operational impacts. This thesis presents EWCellCAD, a computational tool designed for the simulation and…
In active reconstruction, an embodied agent must decide where to look next to efficiently acquire views that support high-quality novel-view rendering. Recent work on active view planning for neural rendering largely derives next-best-view…
We introduce VennFan, a method for generating $n$-set Venn diagrams based on the polar coordinate projection of trigonometric boundaries, resulting in Venn diagrams that resemble a set of fan blades. Unlike most classical constructions, our…
Despite significant progress in 4D generation, rig and motion, the core structural and dynamic components of animation are typically modeled as separate problems. Existing pipelines rely on ground-truth skeletons and skinning weights for…
Many emerging many-core accelerators replace a single large device memory with hundreds to thousands of lightweight cores, each owning only a small local SRAM and exchanging data via explicit on-chip communication. This organization offers…
We present Paris, the first publicly released diffusion model pre-trained entirely through decentralized computation. Paris demonstrates that high-quality text-to-image generation can be achieved without centrally coordinated…
Grids are a general representation for capturing regularly-spaced information, but since they are uniform in space, they cannot dynamically allocate resolution to regions with varying levels of detail. There has been some exploration of…
We present interactive data-driven compute overlays for native and web-based 3D geographic map applications based on WebGPU. Our data-driven overlays are generated in a multi-step compute workflow from multiple data sources on the GPU. We…
Computer-aided design (CAD) is the digital construction of 2D and 3D objects, and is central to a wide range of engineering and manufacturing applications like automobile and aviation. Despite its importance, CAD modeling remains largely a…
A photorealistic and controllable 3D caricaturization framework for faces is introduced. We start with an intrinsic Gaussian curvature-based surface exaggeration technique, which, when coupled with texture, tends to produce over-smoothed…
Natural head rotation is critical for believable embodied virtual agents, yet this micro-level behavior remains largely underexplored. While head-rotation prediction algorithms could, in principle, reproduce this behavior, they typically…
The use of floating bipolar electrodes in copper electro-winning cells represents an emerging technology that promises economic and operational impacts. This article presents a computational tool designed for the simulation and analysis of…