Reference-driven image generation has made rapid progress on identity preservation, but reliable viewpoint control across subjects remains poorly understood. The challenge is to infer the viewpoint...
<p><strong>Tác giả:</strong> Qiwei Yan, Zhiqiang Yuan, Chongyang Li, Jiapei Zhang, Ying Deng, Jinchao Zhang, Jie Zhou</p>
<p>Reference-driven image generation has made rapid progress on identity preservation, but reliable viewpoint control across subjects remains poorly understood. The challenge is to infer the viewpoint of one subject and transfer it to another using only image evidence, without camera poses, depth, or ray-based conditions. In this setting, existing multi-reference generators often rely on spurious semantic correlations, which lead to viewpoint drift, part-level structural mismatches, and missing...</p>
<p>📄 DOI: <a href="https://doi.org/https://doi.org/10.1145/3767308.3836275" target="_blank" rel="noopener">https://doi.org/10.1145/3767308.3836275</a></p>
<p>📖 <a href="https://doi.org/https://doi.org/10.1145/3767308.3836275" target="_blank" rel="noopener">Xem bài báo đầy đủ</a></p>
Bài viết được biên soạn lại bởi LIFVietnam. Nguồn tham khảo: OpenAlex
