Text to 3D Scene Generation with Rich Lexical Grounding
원문 초록
The ability to map descriptions of scenes to 3D geometric representations has many applications in areas such as art, education, and robotics. However, prior work on the text to 3D scene generation task has used manually specified object categories and language that identifies them. We introduce a dataset of 3D scenes annotated with natural language descriptions and learn from this data how to ground textual descriptions to physical objects. Our method successfully grounds a variety of lexical terms to concrete referents, and we show quantitatively that our method improves 3D scene generation over previous work using purely rule-based methods. We evaluate the fidelity and plausibility of 3D scenes generated with our grounding approach through human judgments. To ease evaluation on this task, we also introduce an automated metric that strongly correlates with human judgments.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
SceneCraft: Layout-Guided 3D Scene Generation
Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text
Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures
DreamAnywhere: Object-Centric Panoramic 3D Scene Generation
EmbodiedGen: Towards a Generative 3D World Engine for Embodied Intelligence
AI-powered Contextual 3D Environment Generation: A Systematic Review
토론
이 논문과 연결된 포럼 글이 아직 없습니다.