Projects per year
The Generative Adversarial Network (GAN) and its variations have enabled high quality image generation. However, generating reasonable persons in complex scenes (such as MS-COCO images) remains challenging. We propose a novel structure-based and context-aware approach to enhance the person synthesis in complex scenes. The method can success fully predict the person pose and face structures while respecting the weak layout-based context, then leverage the structures to refine the person appearance. Our method involves three parts. First, a memory-based model is used to encode person intrinsic structures including pose and face key points. Second, a context-aware model infers the conditional person structures from the layout context. Third, the structure-guided personappearancerefinersfurtherenhancethefinalimagegeneration.Ourexperiments present convincing person generation results in layout-to-image tasks on a challenging dataset. Person-related evaluations demonstrate our method achieves state-of-the-art performance, especially on person accuracy and face detection metrics.
|Publication status||Acceptance date - 1 Oct 2022|
|Event||British Machine Vision Conference 2022 - |
Duration: 21 Nov 2022 → 24 Nov 2022
|Conference||British Machine Vision Conference 2022|
|Period||21/11/22 → 24/11/22|
FingerprintDive into the research topics of 'Enhancing Person Synthesis in Complex Scenes via Intrinsic and Contextual Structure Modeling'. Together they form a unique fingerprint.
Centre for the Analysis of Motion, Entertainment Research and Applications (CAMERA) - 2.0
Cosker, D., Bilzon, J., Campbell, N., Cazzola, D., Colyer, S., Lutteroth, C., McGuigan, P., O'Neill, E., Petrini, K., Proulx, M. & Yang, Y.
Engineering and Physical Sciences Research Council
1/11/20 → 31/10/25
Project: Research council
CAMERA MC2 Award
Cosker, D., Cosker, D., Campbell, N., Fincham Haines, T., Hall, P., Li, W., Lutteroth, C., O'Neill, E., Richardt, C., Yang, Y. & Parsons, M.
2/12/19 → 31/03/23
Project: EU Commission