Paper page - PermaVid: Consistent Video Generation Across Edits via Disentangled Context Memory

Source: https://huggingface.co/papers/2606.16449

Abstract

PermaVid addresses long-term video consistency after edits by using multi-modal memory banks that separate appearance and geometric structure, enabling coherent video generation across time and viewpoints.

Consistent video generation under editing operations requires persistence: when edits modify scene appearance or layout, subsequent generations should remain coherent across time and viewpoints. However, existing memory designs struggle to maintain long-term consistency after such modifications, as stored contexts may become outdated or invalid. To address this, we propose PermaVid, a novel framework built upon amulti-modal context memorythat disentanglesspatial contextintosemantic appearanceandgeometric structure, together with anedit-aware memory updateand retrieval strategy that keeps memory evolution aligned with subsequent observations. Specifically, we develop two complementary memory banks: anRGB context memorythat captures appearance-aware observations while implicitly encoding geometry, and adepth context memorythat preserves geometry-only structure disentangled from semantics. Building on this design, we introduce amemory-guided video generationmodel that performsmulti-modal feature fusionunder reference conditions drawn from mixed-modality memory contexts. Experiments demonstrate that our method maintains strong long-term semantic and structural consistency after edits, significantly outperforming state-of-the-art methods.

View arXiv pageView PDFProject pageGitHub3Add to collection

Get this paper in your agent:

hf papers read 2606\.16449

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2606.16449 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2606.16449 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.16449 in a Space README.md to link it from this page.

Collections including this paper1