Supplemental Materials for Activity-centric Scene Synthesis for Functional 3D Scene Modeling
نویسندگان
چکیده
This document provides additional details about the implementation of the scene synthesis algorithm of Fisher et al. [2015], the associated activity detection and plane extraction methods, as well as the types of data provided in our scene, model, and scan databases. Section 2 lists and discusses the parameters used in our synthesis pipeline. The methodology and parameters used in activity detection and plane extraction are discussed in Sections 3 and 4. The details of our database are given in Section 5.
منابع مشابه
Supplementary Material for Human-centric Indoor Scene Synthesis Using Stochastic Grammar
Depth estimation Single-image depth estimation is a fundamental problem in computer vision, which has found broad applications in scene understanding, 3D modeling, and robotics. The problem is challenging since no reliable depth cues are available. In this task, the algorithms output a depth image based on a single RGB input image. To demonstrate the efficacy of our synthetic data, we compare t...
متن کاملA 2D + 3D Rich Data Approach to Scene Understanding
On your one-minute walk from the coffee machine to your desk each morning, you pass by dozens of scenes – a kitchen, an elevator, your office – and you effortlessly recognize them and perceive their 3D structure. But this one-minute scene-understanding problem has been an open challenge in computer vision since the field was first established 50 years ago. In this dissertation, we aim to rethin...
متن کامل3D Scene and Object Classification Based on Information Complexity of Depth Data
In this paper the problem of 3D scene and object classification from depth data is addressed. In contrast to high-dimensional feature-based representation, the depth data is described in a low dimensional space. In order to remedy the curse of dimensionality problem, the depth data is described by a sparse model over a learned dictionary. Exploiting the algorithmic information theory, a new def...
متن کاملSupplemental Document for ”Sketch2Scene: Sketch-based Co-retrieval and Co-placement of 3D Models”
This supplemental document contains two parts. User Study Materials. We provide all the 7 sketched scenes, for each of which we include an artist-created 3D scene, three automatically generated 3D scenes by our technique, and user study statistics (i.e., the percentage in favor of our technique), as shown in Figures 1-7. 24 Sketched Scenes for Parameter Analysis. Each of them consists of 2 to 2...
متن کاملDepicting shape, materials and lighting: observation, formulation and implementation of artistic principles
The appearance of a scene results from complex interactions between the geometry, materials and lights that compose that scene. While Computer Graphics algorithms are now capable of simulating these interactions, it comes at the cost of tedious 3D modeling of a virtual scene, which only well-trained artists can do. In contrast, photographs allow the instantaneous capture of a scene, but shape, ...
متن کامل