Metraipolis › archive › dc_18ecce5b9fea

EmoWorld: A Decoupled Affective Field for Controllable Emotional Video Generation — arXiv:2608.06231

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.06231
License (as archived)
CC0-1.0
Archived
2026-10-31T10:37:45.514Z
SHA-256 of the archived text
3f6ee5c4db92d59b178f56aa65c2c807d4955d6c6da68cfee378293706b3951a
Stable URL of this page
https://metraipolis.com/documento/dc_18ecce5b9fea

How to cite

EmoWorld: A Decoupled Affective Field for Controllable Emotional Video Generation — arXiv:2608.06231 — arXiv (en), https://arxiv.org/abs/2608.06231 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_18ecce5b9fea (Metraipolis archive dc_18ecce5b9fea, sha256 3f6ee5c4db92d59b178f56aa65c2c807d4955d6c6da68cfee378293706b3951a)
BibTeX
@misc{dc18ecce5b9fea,
  title = {EmoWorld: A Decoupled Affective Field for Controllable Emotional Video Generation — arXiv:2608.06231},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.06231},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_18ecce5b9fea; sha256 3f6ee5c4db92d59b178f56aa65c2c807d4955d6c6da68cfee378293706b3951a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.06231. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Emotion shapes how viewers interpret a scene, yet existing video generators entangle global atmosphere, affect-bearing semantic cues, and temporal progression within a single text condition. We present EmoWorld, a framework that decouples these factors within a frozen flow-matching video diffusion transformer (Video DiT). A one-time preparation stage extracts layer-specific affect directions and a reusable cue library from geometry-preserving neutral and emotion-edited panoramas. At inference, Visual Atmosphere Steering (VAS) injects atmosphere directions into hidden states, Semantic Affective Steering (SAS) isolates a separately scalable prompt residual for semantic cues, and Temporal Affective Steering (TAS) interpolates endpoint residual fields across denoising and video time. On Wan2.2, VAS improves target-emotion alignment by 19% while reducing a temporal-fluctuation proxy by 48%; SAS improves target-emotion alignment by 37% and increases detected affect-bearing cues by 36%; and TAS improves transition monotonicity by 15% over the strongest baseline. EmoWorld is evaluated across 27 emotion categories in text-to-video and image-to-video settings, demonstrates portability across multiple Video-DiT backbones, and supports camera-conditioned composition without updating generator parameters.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.06231 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-31T10:23:31.061Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).