The Scene Language: Representing Scenes with Programs, Words, and Embeddings

17citations
arXiv:2410.16770
17
citations
#492
in CVPR 2025
of 2873 papers
5
Top Authors
8
Data Points

Abstract

We introduce the Scene Language, a visual scene representation that concisely and precisely describes the structure, semantics, and identity of visual scenes. It represents a scene with three key components: a program that specifies the hierarchical and relational structure of entities in the scene, words in natural language that summarize the semantic class of each entity, and embeddings that capture the visual identity of each entity. This representation can be inferred from pre-trained language models via a training-free inference technique, given text or image inputs. The resulting scene can be rendered into images using traditional, neural, or hybrid graphics renderers. Together, this forms a robust, automated system for high-quality 3D and 4D scene generation. Compared with existing representations like scene graphs, our proposed Scene Language generates complex scenes with higher fidelity, while explicitly modeling the scene structures to enable precise control and editing.

Citation History

Jan 24, 2026
0
Jan 26, 2026
0
Jan 26, 2026
0
Jan 27, 2026
15+15
Feb 4, 2026
16+1
Feb 13, 2026
17+1
Feb 13, 2026
17
Feb 13, 2026
17