Matches in SemOpenAlex for { <https://semopenalex.org/work/W4378506819> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4378506819 abstract "This paper presents a controllable text-to-video (T2V) diffusion model, named Video-ControlNet, that generates videos conditioned on a sequence of control signals, such as edge or depth maps. Video-ControlNet is built on a pre-trained conditional text-to-image (T2I) diffusion model by incorporating a spatial-temporal self-attention mechanism and trainable temporal layers for efficient cross-frame modeling. A first-frame conditioning strategy is proposed to facilitate the model to generate videos transferred from the image domain as well as arbitrary-length videos in an auto-regressive manner. Moreover, Video-ControlNet employs a novel residual-based noise initialization strategy to introduce motion prior from an input video, producing more coherent videos. With the proposed architecture and strategies, Video-ControlNet can achieve resource-efficient convergence and generate superior quality and consistent videos with fine-grained control. Extensive experiments demonstrate its success in various video generative tasks such as video editing and video style transfer, outperforming previous methods in terms of consistency and quality. Project Page: https://controlavideo.github.io/" @default.
- W4378506819 created "2023-05-27" @default.
- W4378506819 creator A5006669765 @default.
- W4378506819 creator A5014851555 @default.
- W4378506819 creator A5016786612 @default.
- W4378506819 creator A5034191292 @default.
- W4378506819 creator A5036983906 @default.
- W4378506819 creator A5061828638 @default.
- W4378506819 creator A5073799726 @default.
- W4378506819 creator A5092031657 @default.
- W4378506819 date "2023-05-23" @default.
- W4378506819 modified "2023-09-29" @default.
- W4378506819 title "Control-A-Video: Controllable Text-to-Video Generation with Diffusion Models" @default.
- W4378506819 doi "https://doi.org/10.48550/arxiv.2305.13840" @default.
- W4378506819 hasPublicationYear "2023" @default.
- W4378506819 type Work @default.
- W4378506819 citedByCount "0" @default.
- W4378506819 crossrefType "posted-content" @default.
- W4378506819 hasAuthorship W4378506819A5006669765 @default.
- W4378506819 hasAuthorship W4378506819A5014851555 @default.
- W4378506819 hasAuthorship W4378506819A5016786612 @default.
- W4378506819 hasAuthorship W4378506819A5034191292 @default.
- W4378506819 hasAuthorship W4378506819A5036983906 @default.
- W4378506819 hasAuthorship W4378506819A5061828638 @default.
- W4378506819 hasAuthorship W4378506819A5073799726 @default.
- W4378506819 hasAuthorship W4378506819A5092031657 @default.
- W4378506819 hasBestOaLocation W43785068191 @default.
- W4378506819 hasConcept C106030495 @default.
- W4378506819 hasConcept C114466953 @default.
- W4378506819 hasConcept C126042441 @default.
- W4378506819 hasConcept C128840427 @default.
- W4378506819 hasConcept C154945302 @default.
- W4378506819 hasConcept C167510206 @default.
- W4378506819 hasConcept C199360897 @default.
- W4378506819 hasConcept C202474056 @default.
- W4378506819 hasConcept C23431618 @default.
- W4378506819 hasConcept C30814859 @default.
- W4378506819 hasConcept C31972630 @default.
- W4378506819 hasConcept C41008148 @default.
- W4378506819 hasConcept C65483669 @default.
- W4378506819 hasConcept C76155785 @default.
- W4378506819 hasConceptScore W4378506819C106030495 @default.
- W4378506819 hasConceptScore W4378506819C114466953 @default.
- W4378506819 hasConceptScore W4378506819C126042441 @default.
- W4378506819 hasConceptScore W4378506819C128840427 @default.
- W4378506819 hasConceptScore W4378506819C154945302 @default.
- W4378506819 hasConceptScore W4378506819C167510206 @default.
- W4378506819 hasConceptScore W4378506819C199360897 @default.
- W4378506819 hasConceptScore W4378506819C202474056 @default.
- W4378506819 hasConceptScore W4378506819C23431618 @default.
- W4378506819 hasConceptScore W4378506819C30814859 @default.
- W4378506819 hasConceptScore W4378506819C31972630 @default.
- W4378506819 hasConceptScore W4378506819C41008148 @default.
- W4378506819 hasConceptScore W4378506819C65483669 @default.
- W4378506819 hasConceptScore W4378506819C76155785 @default.
- W4378506819 hasLocation W43785068191 @default.
- W4378506819 hasOpenAccess W4378506819 @default.
- W4378506819 hasPrimaryLocation W43785068191 @default.
- W4378506819 hasRelatedWork W1491752883 @default.
- W4378506819 hasRelatedWork W1590871397 @default.
- W4378506819 hasRelatedWork W1889918572 @default.
- W4378506819 hasRelatedWork W2035981816 @default.
- W4378506819 hasRelatedWork W2124860813 @default.
- W4378506819 hasRelatedWork W2164320023 @default.
- W4378506819 hasRelatedWork W2426057899 @default.
- W4378506819 hasRelatedWork W2541131230 @default.
- W4378506819 hasRelatedWork W2782365651 @default.
- W4378506819 hasRelatedWork W2946000660 @default.
- W4378506819 isParatext "false" @default.
- W4378506819 isRetracted "false" @default.
- W4378506819 workType "article" @default.