Saved in:
Bibliographic Details
Main Authors: Jo, Hye-Young, Sakashita, Mose, Mishra, Aditi, Suzuki, Ryo, Niinuma, Koichiro, Gupta, Aakar
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.17883
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911328328744960
author Jo, Hye-Young
Sakashita, Mose
Mishra, Aditi
Suzuki, Ryo
Niinuma, Koichiro
Gupta, Aakar
author_facet Jo, Hye-Young
Sakashita, Mose
Mishra, Aditi
Suzuki, Ryo
Niinuma, Koichiro
Gupta, Aakar
contents AI video generation has lowered barriers to video creation, but current tools still struggle with inconsistency. Filmmakers often find that clips fail to match characters and backgrounds, making it difficult to build coherent sequences. A formative study with filmmakers highlighted challenges in shot composition, character motion, and camera control. We present Map2Video, a street view imagery-driven AI video generation tool grounded in real-world geographies. The system integrates Unity and ComfyUI with the VACE video generation model, as well as OpenStreetMap and Mapillary for street view imagery. Drawing on familiar filmmaking practices such as location scouting and rehearsal, Map2Video enables users to choose map locations, position actors and cameras in street view imagery, sketch movement paths, refine camera motion, and generate spatially consistent videos. We evaluated Map2Video with 12 filmmakers. Compared to an image-to-video baseline, it achieved higher spatial accuracy, required less cognitive effort, and offered stronger controllability for both scene replication and open-ended creative exploration.
format Preprint
id arxiv_https___arxiv_org_abs_2512_17883
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Map2Video: Street View Imagery Driven AI Video Generation
Jo, Hye-Young
Sakashita, Mose
Mishra, Aditi
Suzuki, Ryo
Niinuma, Koichiro
Gupta, Aakar
Human-Computer Interaction
AI video generation has lowered barriers to video creation, but current tools still struggle with inconsistency. Filmmakers often find that clips fail to match characters and backgrounds, making it difficult to build coherent sequences. A formative study with filmmakers highlighted challenges in shot composition, character motion, and camera control. We present Map2Video, a street view imagery-driven AI video generation tool grounded in real-world geographies. The system integrates Unity and ComfyUI with the VACE video generation model, as well as OpenStreetMap and Mapillary for street view imagery. Drawing on familiar filmmaking practices such as location scouting and rehearsal, Map2Video enables users to choose map locations, position actors and cameras in street view imagery, sketch movement paths, refine camera motion, and generate spatially consistent videos. We evaluated Map2Video with 12 filmmakers. Compared to an image-to-video baseline, it achieved higher spatial accuracy, required less cognitive effort, and offered stronger controllability for both scene replication and open-ended creative exploration.
title Map2Video: Street View Imagery Driven AI Video Generation
topic Human-Computer Interaction
url https://arxiv.org/abs/2512.17883