Metraipolis › archive › dc_fd2ad72e2f37
CrossTimeEdit: A Decade-Spanning Cross-View Dataset and Reward-Guided Editing for Historical Street-View Generation — arXiv:2609.36616
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.36616
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T18:38:16.918Z
- SHA-256 of the archived text
c3c0291dd7d5c23e5447053f122687a26a6653f2058670e7e47199ba4a29a6dd- Stable URL of this page
https://metraipolis.com/documento/dc_fd2ad72e2f37
How to cite
CrossTimeEdit: A Decade-Spanning Cross-View Dataset and Reward-Guided Editing for Historical Street-View Generation — arXiv:2609.36616 — arXiv (en), https://arxiv.org/abs/2609.36616 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fd2ad72e2f37 (Metraipolis archive dc_fd2ad72e2f37, sha256 c3c0291dd7d5c23e5447053f122687a26a6653f2058670e7e47199ba4a29a6dd)
BibTeX
@misc{dcfd2ad72e2f37,
title = {CrossTimeEdit: A Decade-Spanning Cross-View Dataset and Reward-Guided Editing for Historical Street-View Generation — arXiv:2609.36616},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.36616},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fd2ad72e2f37; sha256 c3c0291dd7d5c23e5447053f122687a26a6653f2058670e7e47199ba4a29a6dd},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36616. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Historical street-view imagery records urban evolution, but uneven coverage leaves substantial gaps in historical records. Generating plausible past appearances requires restoring changed structures while preserving persistent scene content. We construct VIGOR-his, a decade-spanning cross-view dataset containing 43,653 location-level quadruplets across 11 cities on three continents. Its automated pipeline performs spatial pairing, consistency screening, change classification, and the generation and validation of satellite-based change descriptions and local editing instructions. Based on VIGOR-his, we propose CrossTimeEdit, a model that reformulates historical street-view generation as editing, using recent street views to constrain viewpoint and unchanged appearance and temporal satellite differences as change evidence. Starting from FLUX.2 [Klein] 4B, we train CrossTimeEdit through supervised fine-tuning (SFT) followed by online reinforcement learning (RL). We design three street-view editing criteria, namely Instruction Alignment (IA), Background Preservation (BP), and Quality and Physical Plausibility (QP), as both RL reward dimensions and evaluation metrics. We optimize this multi-reward objective using Within Group Relative Policy Optimization for flow-matching models (Flow-GRPO) with Group reward-Decoupled Normalization Policy Optimization (GDPO), which normalizes each reward dimension before aggregation. CrossTimeEdit improves overall performance across the three editing criteria by 17.12\% over the pretrained baseline and outperforms cross-view generation models in scene consistency, visual realism, and perceptual quality. The implementation code, dataset, and model weights are available at this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-30 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.36616 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T18:04:24.719Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).