KGEdit: Ambiguity-Aware Knowledge Graphs for Training-Free Precise Video Generation and Editing
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918529084686336 |
|---|---|
| author | Cai, Mingshu Zhang, Miao Yang, Chenghe Li, Yixuan Yoshie, Osamu Ieiri, Yuya |
| author_facet | Cai, Mingshu Zhang, Miao Yang, Chenghe Li, Yixuan Yoshie, Osamu Ieiri, Yuya |
| contents | In recent years, training-free video generation has progressed remarkably. However, when handling complex textual instructions, existing methods still suffer from semantic ambiguity, incorrect concept binding, and cross-frame inconsistency. To address these issues, we propose KGEdit, a structured semantic control framework for text-to-video (T2V) diffusion models. Specifically, we first construct an ambiguity-aware knowledge graph (AAKG) to disentangle and disambiguate the input prompt, converting it into four types of structured semantics: identity, relation, attribute, and negative constraints. We then design a structured semantic injection module (SSIM) to inject these semantic signals into key layers of the diffusion Transformer, enabling fine-grained semantic control. In addition, we introduce a temporal-aware semantic control (TASC) module that dynamically schedules semantic objectives according to the stage-wise characteristics of the denoising process, further improving semantic alignment and temporal consistency. Experiments show that KGEdit outperforms existing methods in editing precision and temporal stability, while offering higher efficiency and controllability in text-driven interaction scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_29509 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | KGEdit: Ambiguity-Aware Knowledge Graphs for Training-Free Precise Video Generation and Editing Cai, Mingshu Zhang, Miao Yang, Chenghe Li, Yixuan Yoshie, Osamu Ieiri, Yuya Computer Vision and Pattern Recognition In recent years, training-free video generation has progressed remarkably. However, when handling complex textual instructions, existing methods still suffer from semantic ambiguity, incorrect concept binding, and cross-frame inconsistency. To address these issues, we propose KGEdit, a structured semantic control framework for text-to-video (T2V) diffusion models. Specifically, we first construct an ambiguity-aware knowledge graph (AAKG) to disentangle and disambiguate the input prompt, converting it into four types of structured semantics: identity, relation, attribute, and negative constraints. We then design a structured semantic injection module (SSIM) to inject these semantic signals into key layers of the diffusion Transformer, enabling fine-grained semantic control. In addition, we introduce a temporal-aware semantic control (TASC) module that dynamically schedules semantic objectives according to the stage-wise characteristics of the denoising process, further improving semantic alignment and temporal consistency. Experiments show that KGEdit outperforms existing methods in editing precision and temporal stability, while offering higher efficiency and controllability in text-driven interaction scenarios. |
| title | KGEdit: Ambiguity-Aware Knowledge Graphs for Training-Free Precise Video Generation and Editing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.29509 |