CVMay 31

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

arXiv:2606.0107965.3
AI Analysis

For researchers and practitioners in image compositing, this work addresses the underexplored cross-domain scenario with a training-based solution, achieving SOTA results.

The paper tackles cross-domain object compositing, where foreground and background come from different domains. It introduces ChameleonDataset, the first large-scale training dataset for this task, and proposes a two-stage framework (JHCL for style-content disentanglement and STAG for stylization) that outperforms existing methods in compositional plausibility and stylistic fidelity.

Image compositing aims to seamlessly insert a foreground object into a background image, and recent advances in diffusion models have significantly enhanced the quality, especially when the foreground and background images come from the same domain (e.g., natural images). However, cross-domain compositing, where the foreground and background come from different domains, is relatively underexplored and remains challenging because the model must preserve the foreground object's identity while stylizing it to match the background domain. Existing cross-domain compositing approaches largely rely on training-free blending and refinement strategies. This is partly due to the lack of large-scale paired datasets for cross-domain compositing, limiting the development of training-based solutions. As a result, they are limited to tone-level alignment and often produce style-inconsistent or overstylized results. To overcome such limitations, we construct ChameleonDataset, the first large-scale training dataset for cross-domain compositing, with a comprehensive evaluation benchmark, built through a scalable data construction pipeline. Building on this, we propose Chameleon, a novel two-stage training-based cross-domain compositing framework. In the first stage, we propose Joint Hard Contrastive Learning (JHCL) to train ChameleonEncoder, which effectively disentangles style and content representations. In the second stage, we introduce Spatio-Temporal Attention Gating (STAG) into a diffusion transformer for effective stylization, adaptively regulating how style tokens from the first-stage encoder are injected across spatial and temporal dimensions. Our method outperforms state-of-the-art in-domain and cross-domain compositing models, sequential pipelines and commercial models, achieving improvements in both compositional plausibility and stylistic fidelity.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes