跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-09-29AI 評分41

CrossTimeEdit:跨越十年的跨視角數據集與獎勵引導編輯,用於歷史街景生成

CrossTimeEdit: A Decade-Spanning Cross-View Dataset and Reward-Guided Editing for Historical Street-View Generation

AI 導讀

研究團隊構建 VIGOR-his 數據集,並提出 CrossTimeEdit,以獎勵引導編輯生成歷史街景。數據集涵蓋三大洲 11 個城市的 43,653 個位置級四元組;CrossTimeEdit 在三項編輯準則上的整體表現較預訓練基線提升 17.12%。程式碼、數據集及模型權重均已提供。

正文

Published on Sep 29

Authors:

,

,

,

,

,

Abstract

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/.

View arXiv page View PDF Project page GitHub 2 Add to collection

Get this paper in your agent:

hf papers read 2609.36616

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2609.36616 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2609.36616 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2609.36616 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co