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

TL;DR

The paper presents the Scene Language, a comprehensive scene representation combining programs, words, and embeddings, enabling high-fidelity scene generation and precise control from text or images.

Contribution

It introduces a novel, multi-component scene representation that integrates hierarchical structure, semantic labels, and visual embeddings, inferred without training from pre-trained models.

Findings

Enables high-quality 3D and 4D scene rendering

Outperforms scene graphs in fidelity and control

Supports inference from text and images

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.