Browse research papers in Computer Graphics and Computer-Aided Design - Computer Science Discover 8 academic papers with AI-powered analysis

PAPERZILLA

Crunching Academic Papers into Bite-sized Insights.

About

Sign Out

← Back

Fields

Computer Science

Computer Graphics and Computer-Aided Design

The creation and manipulation of visual content using computers, including 3D modeling, rendering, animation, visualization, virtual reality, CAD/CAM systems, and computational geometry

8 papers in this specialization

Paperzilla Papers in Computer Graphics and Computer-Aided Design

WAN-ANIMATE: UNIFIED CHARACTER ANIMATION AND REPLACEMENT WITH HOLISTIC REPLICATION

This paper introduces Wan-Animate, a new open-source framework for animating and replacing characters in videos, built upon the Wan-I2V model. It uses a modified input paradigm and control signals for body motion and facial expressions to create more realistic and expressive character animations, even outperforming some closed-source commercial products.

Avat3r: Large Animatable Gaussian Reconstruction Model for High-fidelity 3D Head Avatars

Avat3r creates animatable 3D head avatars from a few images using large reconstruction models and priors from other models like DUSt3R and Sapiens. It simplifies avatar creation by animating heads without needing videos of expressions and handles inconsistencies in input images.

SketchGraphs: A Large-Scale Dataset for Modeling Relational Geometry in Computer-Aided Design

This paper introduces SketchGraphs, a massive dataset of 15 million 2D sketches from CAD models, along with a toolkit for processing and using the data. The dataset aims to help train machine learning models for tasks like auto-completion and constraint inference in CAD software.

LEARNING TO GENERATE 3D SHAPES WITH GENERATIVE CELLULAR AUTOMATA

This paper proposes Generative Cellular Automata (GCA), a new method for generating 3D shapes in a computer. GCA mimics cell growth by iteratively adding voxels to a shape, focusing computation on a small, local area around the existing shape. Experiments show it can complete missing parts of shapes and generate entirely new shapes.

★

☆

151_learning_to_generate_3d_shapes.pdf

Aug 17, 02:34 PM

LEARNING TO GENERATE 3D SHAPES WITH GENERATIVE CELLULAR AUTOΜΑΤΑ

This paper introduces a new method called Generative Cellular Automata (GCA) to create 3D shapes with a computer. GCA is like building with digital LEGOs, starting with a single block and adding more based on learned rules. It performs well at completing missing parts of shapes and generating entirely new ones, but mainly tests on computer-generated, not real-world, shapes.

★

☆

151_learning_to_generate_3d_shapes.pdf

Aug 17, 02:31 PM

A Large-Scale Comparison of Tetrahedral and Hexahedral Elements for Solving Elliptic PDEs with the Finite Element Method

In a surprising upset, quadratic tetrahedral elements performed similarly or better than hexahedral elements for a range of elliptic PDEs, particularly when considering the entire FEM pipeline from meshing to solving. This suggests that robust, automatic tetrahedral meshing, coupled with quadratic elements, can be a strong choice for many common simulation scenarios without sacrificing performance.

Design and Simulation of Computer Aided Chinese Vocabulary Evaluation System

A computer-aided system for assessing Chinese vocabulary was developed and tested with a small group of students and teachers. Preliminary results suggest that the system is user-friendly and provides helpful feedback, but further research is needed to validate its effectiveness and address limitations in content and assessment scope.

★

☆

CAD_18(S3)_2021_1-11.pdf

Jul 14, 11:17 AM

Application of Artificial Intelligence in Modern Art Teaching

This paper explores the application of artificial intelligence (AI) in modern art teaching, identifying current limitations and proposing strategies to enhance AI's role. It suggests expanding AI's adaptability, improving intelligent teaching modes, and enriching the artistic experience through personalized learning and virtual reality integration. A performance analysis model based on AHP and grey clustering is introduced to evaluate AI's application effect.