arXiv Open Access 2025

WorldScore: A Unified Evaluation Benchmark for World Generation

Haoyi Duan Hong-Xing Yu Sirui Chen Li Fei-Fei Jiajun Wu

Lihat Sumber

Abstrak

We introduce the WorldScore benchmark, the first unified benchmark for world generation. We decompose world generation into a sequence of next-scene generation tasks with explicit camera trajectory-based layout specifications, enabling unified evaluation of diverse approaches from 3D and 4D scene generation to video generation models. The WorldScore benchmark encompasses a curated dataset of 3,000 test examples that span diverse worlds: static and dynamic, indoor and outdoor, photorealistic and stylized. The WorldScore metrics evaluate generated worlds through three key aspects: controllability, quality, and dynamics. Through extensive evaluation of 19 representative models, including both open-source and closed-source ones, we reveal key insights and challenges for each category of models. Our dataset, evaluation code, and leaderboard can be found at https://haoyi-duan.github.io/WorldScore/

Topik & Kata Kunci

cs.GR cs.AI cs.CV

Penulis (5)

Haoyi Duan

Hong-Xing Yu

Sirui Chen

Li Fei-Fei

Jiajun Wu

Format Sitasi

APA MLA BibTeX

Duan, H., Yu, H., Chen, S., Fei-Fei, L., Wu, J. (2025). WorldScore: A Unified Evaluation Benchmark for World Generation. https://arxiv.org/abs/2504.00983

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2025
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓