This paper introduces a novel grid structure that extends tall cell methods for efficient deep water simulation. Unlike previous tall cell methods, which are designed to capture all the fine details around liquid surfaces, our approach subdivides tall cells horizontally, allowing for more aggressive … Continue reading “Quadtree Tall Cells for Eulerian Liquid Simulation”
Author: Takashi Kanai
Presented at EG 2025.
From May 12 to 16, 2025, PhD student Tomoyo Kikuchi gave an oral presentation at Eurographics 2025, held at BFI Southbank in London, UK. The presentation covered research on collision handling in elastic body simulation. For more details, please see this page.
A Unified Discrete Collision Framework for Triangle Primitives
We present a unified, primitive-first framework with DCD for collision response in physics-based simulations. Previous methods do not provide sufficient solutions on a framework that resolves edge-triangle and edge-edge collisions when handling self-collisions and inter-object collisions in a unifie … Continue reading “A Unified Discrete Collision Framework for Triangle Primitives”
DeepFracture: A Generative Approach for Predicting Brittle Fractures with Neural Discrete Representation Learning
In the field of brittle fracture animation, generating realistic destruction animations using physics-based simulation methods is computationally expensive. While techniques based on Voronoi diagrams or pre-fractured patterns are effective for real-time applications, they fail to incorporate collisi … Continue reading “DeepFracture: A Generative Approach for Predicting Brittle Fractures with Neural Discrete Representation Learning”
Presented at I3D 2024.
From May 8 to 10, 2024, the ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games 2024 was held at the office of Cesium GS Inc. in Philadelphia, USA. PhD students Hirasawa and Kikuchi presented posters, and faculty member Kanai gave an oral presentation. The oral presentation featured a joint … Continue reading “Presented at I3D 2024.”
Presented at MIG 2023.
At the international conference 16th ACM SIGGRAPH Conference on Motion, Interaction and Games (MIG 2023) held in Rennes, France, our lab member Xin Huang gave a presentation. Although on-site attendance was not possible, the presentation was delivered online via Zoom. Presentation videos, the paper, … Continue reading “Presented at MIG 2023.”
Video-Based Motion Retargeting Framework between Characters with Various Skeleton Structure
We introduce a motion retargeting framework capable of animating characters with distinct skeletal structures using video data. While prior studies have successfully performed motion retargeting be- tween skeletons with different structures, retargeting noisy and unnatural motion data extracted from … Continue reading “Video-Based Motion Retargeting Framework between Characters with Various Skeleton Structure”
Presented at EG 2023.
At the international conference Eurographics 2023, held in Saarbrücken, Germany from May 8 to 12, 2023, Tianxing Li, who graduated from our lab in 2021, gave a presentation. The paper was accepted to Computer Graphics Forum in the fall of last year, leading to its presentation at EG2023. It focuses … Continue reading “Presented at EG 2023.”
Detail-Aware Deep Clothing Animations Infused with Multi-Source Attributes
This paper presents a novel learning-based clothing deformation method to generate rich and reasonable detailed deformations for garments worn by bodies of various shapes in various animations. In contrast to existing learning-based methods, which require numerous trained models for different garmen … Continue reading “Detail-Aware Deep Clothing Animations Infused with Multi-Source Attributes”
Presented at MIG 2021.
Sorry, this entry is only available in 日本語.