Toward Intelligent Scene Augmentation for Context-Aware Object Placement and Sponsor-Logo Integration
Unnati Saraswat, Tarun Rao, Namah Gupta, Shweta Swami, Shikhar Sharma, Prateek Narang, Dhruv Kumar
TL;DR
This work introduces two practical tasks for advertising-oriented image editing: context-aware object insertion and sponsor-product logo augmentation. It presents a modular pipeline that fuses vision-language reasoning, category-conditioned localization, diffusion-based generation, and compositing, along with two annotated datasets to support evaluation. Across six targeted experiments, the approach shows that two-stage prompting boosts object diversity, placement accuracy via YOLOv8 surpasses grounding baselines, and sponsor-logo augmentation achieves strong detection, segmentation, and realism metrics. The results demonstrate a viable, interpretable framework for intelligent, brand-aware scene editing, with clear pathways for improvement in end-to-end integration, 3D reasoning, and temporal consistency for video applications.
Abstract
Intelligent image editing increasingly relies on advances in computer vision, multimodal reasoning, and generative modeling. While vision-language models (VLMs) and diffusion models enable guided visual manipulation, existing work rarely ensures that inserted objects are \emph{contextually appropriate}. We introduce two new tasks for advertising and digital media: (1) \emph{context-aware object insertion}, which requires predicting suitable object categories, generating them, and placing them plausibly within the scene; and (2) \emph{sponsor-product logo augmentation}, which involves detecting products and inserting correct brand logos, even when items are unbranded or incorrectly branded. To support these tasks, we build two new datasets with category annotations, placement regions, and sponsor-product labels.