Grounding World Simulation Models in a Real-World Metropolis
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917347786227712 |
|---|---|
| author | Seo, Junyoung Choi, Hyunwook Kwon, Minkyung Choi, Jinhyeok Jin, Siyoon Lee, Gayoung Kim, Junho Lee, JoungBin Gu, Geonmo Han, Dongyoon Yun, Sangdoo Kim, Seungryong Kim, Jin-Hwa |
| author_facet | Seo, Junyoung Choi, Hyunwook Kwon, Minkyung Choi, Jinhyeok Jin, Siyoon Lee, Gayoung Kim, Junho Lee, JoungBin Gu, Geonmo Han, Dongyoon Yun, Sangdoo Kim, Seungryong Kim, Jin-Hwa |
| contents | What if a world simulation model could render not an imagined environment but a city that actually exists? Prior generative world models synthesize visually plausible yet artificial environments by imagining all content. We present Seoul World Model (SWM), a city-scale world model grounded in the real city of Seoul. SWM anchors autoregressive video generation through retrieval-augmented conditioning on nearby street-view images. However, this design introduces several challenges, including temporal misalignment between retrieved references and the dynamic target scene, limited trajectory diversity and data sparsity from vehicle-mounted captures at sparse intervals. We address these challenges through cross-temporal pairing, a large-scale synthetic dataset enabling diverse camera trajectories, and a view interpolation pipeline that synthesizes coherent training videos from sparse street-view images. We further introduce a Virtual Lookahead Sink to stabilize long-horizon generation by continuously re-grounding each chunk to a retrieved image at a future location. We evaluate SWM against recent video world models across three cities: Seoul, Busan, and Ann Arbor. SWM outperforms existing methods in generating spatially faithful, temporally consistent, long-horizon videos grounded in actual urban environments over trajectories reaching hundreds of meters, while supporting diverse camera movements and text-prompted scenario variations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_15583 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Grounding World Simulation Models in a Real-World Metropolis Seo, Junyoung Choi, Hyunwook Kwon, Minkyung Choi, Jinhyeok Jin, Siyoon Lee, Gayoung Kim, Junho Lee, JoungBin Gu, Geonmo Han, Dongyoon Yun, Sangdoo Kim, Seungryong Kim, Jin-Hwa Computer Vision and Pattern Recognition What if a world simulation model could render not an imagined environment but a city that actually exists? Prior generative world models synthesize visually plausible yet artificial environments by imagining all content. We present Seoul World Model (SWM), a city-scale world model grounded in the real city of Seoul. SWM anchors autoregressive video generation through retrieval-augmented conditioning on nearby street-view images. However, this design introduces several challenges, including temporal misalignment between retrieved references and the dynamic target scene, limited trajectory diversity and data sparsity from vehicle-mounted captures at sparse intervals. We address these challenges through cross-temporal pairing, a large-scale synthetic dataset enabling diverse camera trajectories, and a view interpolation pipeline that synthesizes coherent training videos from sparse street-view images. We further introduce a Virtual Lookahead Sink to stabilize long-horizon generation by continuously re-grounding each chunk to a retrieved image at a future location. We evaluate SWM against recent video world models across three cities: Seoul, Busan, and Ann Arbor. SWM outperforms existing methods in generating spatially faithful, temporally consistent, long-horizon videos grounded in actual urban environments over trajectories reaching hundreds of meters, while supporting diverse camera movements and text-prompted scenario variations. |
| title | Grounding World Simulation Models in a Real-World Metropolis |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.15583 |