Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Yifan, He, Tong
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2605.15182
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911685937201152
author Wang, Yifan
He, Tong
author_facet Wang, Yifan
He, Tong
contents Camera-controlled video generation has made substantial progress, enabling generated videos to follow prescribed viewpoint trajectories. However, existing methods usually learn camera-specific conditioning through camera encoders, control branches, or attention and positional-encoding modifications, which often require post-training on large-scale camera-annotated videos. Training-free alternatives avoid such post-training, but often shift the cost to test-time optimization or extra denoising-time guidance. We propose Warp-as-History, a simple interface that turns camera-induced warps into camera-warped pseudo-history with target-frame positional alignment and visible-token selection. Given a target camera trajectory, we construct camera-warped pseudo-history from past observations and feed it through the model's visual-history pathway. Crucially, we align its positional encoding with the target frames being denoised and remove warped-history tokens without valid source observations. Without any training, architectural modification, or test-time optimization, this interface reveals a non-trivial zero-shot capability of a frozen video generation model to follow camera trajectories. Moreover, lightweight offline LoRA finetuning on only one camera-annotated video further improves this capability and generalizes to unseen videos, improving camera adherence, visual quality, and motion dynamics without test-time optimization or target-video adaptation. Extensive experiments on diverse datasets confirm the effectiveness of our method.
format Preprint
id arxiv_https___arxiv_org_abs_2605_15182
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Warp-as-History: Generalizable Camera-Controlled Video Generation from One Training Video
Wang, Yifan
He, Tong
Computer Vision and Pattern Recognition
Camera-controlled video generation has made substantial progress, enabling generated videos to follow prescribed viewpoint trajectories. However, existing methods usually learn camera-specific conditioning through camera encoders, control branches, or attention and positional-encoding modifications, which often require post-training on large-scale camera-annotated videos. Training-free alternatives avoid such post-training, but often shift the cost to test-time optimization or extra denoising-time guidance. We propose Warp-as-History, a simple interface that turns camera-induced warps into camera-warped pseudo-history with target-frame positional alignment and visible-token selection. Given a target camera trajectory, we construct camera-warped pseudo-history from past observations and feed it through the model's visual-history pathway. Crucially, we align its positional encoding with the target frames being denoised and remove warped-history tokens without valid source observations. Without any training, architectural modification, or test-time optimization, this interface reveals a non-trivial zero-shot capability of a frozen video generation model to follow camera trajectories. Moreover, lightweight offline LoRA finetuning on only one camera-annotated video further improves this capability and generalizes to unseen videos, improving camera adherence, visual quality, and motion dynamics without test-time optimization or target-video adaptation. Extensive experiments on diverse datasets confirm the effectiveness of our method.
title Warp-as-History: Generalizable Camera-Controlled Video Generation from One Training Video
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.15182