AI 能把你家街道P回十年前
现在的 AI 修图能把照片里的东西改掉，但改「时间」很难：它不知道十年前这条街长什么样。这篇论文造了一个跨十年的街景数据集，覆盖三大洲 11 个城市、4 万多个地点，然后训练模型用「现在的街景 + 卫星图的变化」当证据，把老照片里拆掉的楼补回来、新盖的楼抹掉，同时保留没变的店面招牌和路灯。效果比现有模型好 17%，而且它不靠猜，靠的是卫星图记录的真实变化。它不是你明天能用上的工具，但它是「AI 复原城市记忆」这条路上第一次有了靠谱的教材。
📄 原文摘要(英文)
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 https://luhanwen67.github.io/CrossTimeEdit-release/.