Multi-Scale Geometry Interpolation

by Sean Andrist January 23, 2011 Assignment 1

Assigned paper 1. Sentence: We propose a solution to the vertex interpolation problem that starts from interpolating the local metric (edge lengths) and mean curvature (dihedral angles) and makes consistent choices of local affine transformations using shape matching applied to successively larger parts of the mesh. (Abstract, 5th sentence) 2. Problem: The fundamental problem is […]

Read the full article →

Human Motion Synthesis with Optimization-based Graphs

by Adrian Mayorga January 23, 2011 Assignment 1

Paper 1. Sentence: In this paper we describe a motion synthesis using an optimization-based graph (1st sentence, 3rd paragraph). 2. Problem: Switching between behaviors in a motion graph may require traversal between several nodes. This makes fast changes in behaviors slow or unnatural. 3. Key Idea: Use optimization based ideas to generate links in the […]

Read the full article →

Interactive Generation of Human Animation with Deformable Motion Models

by Adrian Mayorga January 23, 2011 Assignment 1

Paper 1. Sentence: This paper presents a new motion model we term deformable motion models for human motion analysis and synthesis (1st sentence, 3rd paragraph) 2. Problem: To create a motion model that generate natural looking animations and take intuitive inputs. 3. Key Idea: Use annotated motion examples to generate parametrized deformable motion models that […]

Read the full article →

Real-Time Deformation and Fracture in a Game Environment (chosen from list)

by Daniel January 23, 2011 Assignment 1

1. Sentence: “This paper describes a simulation system that has been developed to model the deformation and fracture of solid objects in a real-time gaming context.” (abstract) 2. Problem: Computing the fracturing and deformation of solid objects can take large amounts of processing power, which makes it hard to do in real time in settings […]

Read the full article →

Fast Local and Global Similarity Searches in Large Motion Capture Databases (assigned)

by Daniel January 23, 2011 Assignment 1

1. Sentence: “In this work we demonstrate that identifying locally similar regions in human motion data can be practical even for huge databases, if medium-dimensional (15–90 dimensional) feature sets are used for kd-tree-based nearest-neighbor searches.” (abstract) 2. Problem: Motion capture creates large amounts of data and searching through the data to find similar motions in […]

Read the full article →

Leveraging the talent of hand animators to create three-dimensional animation

by Jim Hill January 23, 2011 Assignment 1

1. Sentence: Our key insight is to use motion capture data as a source of domain knowledge and ‘lift’ the two-dimensional animation to three dimensions, while maintaining the unique style of the input animation . (5th sentence, first paragraph) 2. Problem: There is a large amount of talent in the 2D animation field and it […]

Read the full article →

2.5D Cartoon Models

by Jim Hill January 23, 2011 Assignment 1

1. Sentence: We show how 2D vector art drawings of a cartoon from different views can be used to generate a novel structure, the 2.5D cartoon model, which can be used to simulate 3D rotations and generate plausible renderings of the cartoon from any view. (sentence 2 paragraph 1) 2. Problem: It is easy to […]

Read the full article →

Animating non humanoid characters with human motion data

by Jim Hill January 23, 2011 Assignment 1

1. Sentence: This paper presents a method for generating whole-body skeletal animations of non-humanoid characters from human motion capture data (1st sentence 1st paragraph) 2. Problem: Animating non human characters is difficult to do with motion capture data, find a way to use motion capture data to help build good animations. 3. Key Idea: Take […]

Read the full article →

Fast and Efficient Skinning of Animated Meshes

by Nathan Mitchell January 23, 2011 Assignment 1

Assigned Paper: Found on authors website here Sentence:  We present an algorithm based on iterative coordinate descent optimization which handles arbitrary animations and produces more accurate approximations than previous techniques, while using only standard linear skinning without any modifications or extensions. Problem:  Animating complex meshes per vertex, per frame is time consuming. Instead use a […]

1 comment Read the full article →

Learning behavior styles with inverse reinforcement learning

by Jim Hill January 23, 2011 Assignment 1

1. Sentence: We present a method for inferring the behavior styles of character controllers from a small set of examples (1st sentence, 1st paragraph) 2. Problem: Developing reward functions for the creation of character controllers is difficult and imprecise to do manually. Instead, build a system that will generate the reward function given several examples. […]

Read the full article →

← Previous Entries

Next Entries →