Search Results

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 ...

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 ...

Style-guided texture generation aims to generate a texture that is harmonious with both the style of the reference image and the geometry of the input mesh, given a reference style image and a 3D mesh with its text description. Although diffusion-based ...

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 ...

Existing neural rendering-based text-to-3D-portrait generation methods typically make use of human geometry prior and diffusion models to obtain guidance. However, relying solely on geometry information introduces issues such as the Janus problem, over-...

Recent advances in supersampling for frame generation and super-resolution improve real-time rendering performance significantly. However, because these methods rely heavily on the most recent features of high-end GPUs, they are impractical for mobile ...

3D mesh denoising is a crucial pre-processing step in many graphics applications. However, existing data-driven mesh denoising models, primarily trained on synthetic white noise, are less effective when applied to real-world meshes with the noise ...

• Introduced an EMD method using rotation-equivariant features for SOTA mesh denoising.
• Developed an RMNG model to create realistic noisy-clean pairs, enhancing real-world denoising.
• Proposed a method to add smoothing degradation in ...

Signed Distance Fields (SDFs) have found widespread utility in collision detection applications due to their superior query efficiency and ability to represent continuous geometries. However, little attention has been paid to calculating the ...

• The first real-time and accurate general SDF-SDF collision detection method.
• A novel method for testing the intersection of analytic distance functions.
• An accurate method for estimating contact information for SDF-SDF collision ...

Mesh deformation has a wide range of applications, including character creation, geometry modelling, deforming animation, and morphing. Recently, mesh deformation methods based on CLIP models demonstrated the ability to perform automatic text-...

When introducing physics-constrained deep learning solutions to the volumetric super-resolution of scientific data, the training is challenging to converge and always time-consuming. We propose a new hierarchical sampling method based on octree ...

• We propose a novel octree-based approach for modeling volumetric scientific data by leveraging its importance distribution.
• We present a hierarchical sampling method to optimize the distribution of sample points in each training data ...

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 ...

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 ...

Styled online in-between motion generation has important application scenarios in computer animation and games. Its core challenge lies in the need to satisfy four critical requirements simultaneously: generation speed, motion quality, style diversity, ...

We present Multi-feature Radiance-Predicting Neural Networks (MRPNN), a practical framework with a lightweight feature fusion neural network for rendering high-order scattered radiance of participating media in real time. By reformulating the Radiative ...

Although neural supersampling has achieved great success in various applications for improving image quality, it is still difficult to apply it to a wide range of real-time rendering applications due to the high computational power demand. Most existing ...

We present <italic>MobileSky</italic>, the first automatic method for real-time high-quality sky replacement for mobile AR applications. The primary challenge of this task is how to extract sky regions in camera feed both quickly and accurately. While the ...

Current video semantic segmentation tasks involve two main challenges: how to take full advantage of multi-frame context information, and how to improve computational efficiency. To tackle the two challenges simultaneously, we present a novel Multi-...

Self-supervised monocular depth estimation has achieved encouraging performance recently. A consensus is that high-resolution inputs often yield better results. However, we find that the performance gap between high and low resolutions in this ...

Crowd simulation methods generally focus on high fidelity 2D trajectories but ignore detailed 3D body animation which is normally added in a post-processing step. We argue that this is an intrinsic flaw as detailed body motions affect the 2D ...