The Scene Language: Representing Scenes with Programs, Words, and Embeddings
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
$I^{2}$-World: Intra-Inter Tokenization for Efficient Dynamic 4D Scene Forecasting
XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation
Long-term Traffic Simulation with Interleaved Autoregressive Motion and Scenario Generation
3D Scene Generation: A Survey
Steerable Scene Generation with Post Training and Inference-Time Search
HoloTime: Taming Video Diffusion Models for Panoramic 4D Scene Generation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.