Chameleon: Style-Content Disentangled Framework for Cross-Domain Object Compositing

The paper introduces Chameleon, a two‑stage training framework for cross‑domain image compositing that separates style and content representations. It first trains a ChameleonEncoder using Joint Hard Contrastive Learning to disentangle style and content, then applies Spatio‑Temporal Attention Gating within a diffusion transformer to stylize the foreground while preserving its identity. The authors also release ChameleonDataset, the first large‑scale training set for cross‑domain compositing, and demonstrate that Chameleon outperforms existing in‑domain, cross‑domain, and commercial models in both plausibility and stylistic fidelity.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

• llms
• diffusion
• benchmarks
• safety