Learning Preposition Priors to Generate Scene from Text Using Contact Constraints

S Yashaswini,S S Shylaja

doi:10.24018/ejece.2021.5.4.342

Abstract

In this paper, we propose the method of generating a 3D scene from text with respect to interior designing by considering the orientation of every object present in the scene. Thousands of interiors designing related sentences are generated using RNN to preserve context between sentences. The BiLSTM-RNN-WE method is used for POS Tagging, blender is used to generate 3D scene based on query. This paper focuses on interior designing and has considered objects placement with respect to the preposition in the Sentence. Our approach uses Natural Language processing to extract useful information from the user text, which will aid the rendering engine generate better scene.

Highlights

People communicate their feelings, thoughts, and ideas through language, so this is an attempt to mimic imagination of their dream home through visualization
The scale of the objects was considered when generating the 3D scene before placement as discussed in algorithm Fig. 5 discusses various steps involved in scene generation
A good metric could be used to measure accuracy of generated scene

Summary

INTRODUCTION

Thoughts, and ideas through language, so this is an attempt to mimic imagination of their dream home through visualization. WordsEye has used natural language as a medium for describing visual ideas and images to acquire artistic skills on window-based interface, it automatically converts text into 3D-scenes by depicting entities and objects involved, their poses, grips, shapes and spatial tags and relations, color, kinematics, attributes like twisting, bending and tries to avoid conflicting constraints by specifying path, orientation, and position as specified by Bob Coyne, Richard Sprout [5] These approaches when scaled down to interior designing fails to give good results for objects whose reference is a wall or the ceiling, neither does it consider the orientation aspect of objects

IMPLEMENTATION

Preprocessing

Parts of Speech Tagging

RESULTS AND DISCUSSIONS

CONCLUSION

FUTURE ENHANCEMENTS