We propose a novel ECGAN for the challenging semantic image synthesis task. Although considerable improvement has been achieved, the quality of synthesized images is far from satisfactory due to three largely unresolved challenges. 1) The semantic labels do not provide detailed structural information, making it difficult to synthesize local details and structures. 2) The widely adopted CNN operations such as convolution, down-sampling, and normalization usually cause spatial resolution loss and thus cannot fully preserve the original semantic information, leading to semantically inconsistent results. 3) Existing semantic image synthesis methods focus on modeling local semantic information from a single input semantic layout. However, they ignore global semantic information of multiple input semantic layouts, i.e., semantic cross-relations between pixels across different input layouts. To tackle 1), we propose to use edge as an intermediate representation which is further adopted to guide image generation via a proposed attention guided edge transfer module. Edge information is produced by a convolutional generator and introduces detailed structure information. To tackle 2), we design an effective module to selectively highlight class-dependent feature maps according to the original semantic layout to preserve the semantic information. To tackle 3), inspired by current methods in contrastive learning, we propose a novel contrastive learning method, which aims to enforce pixel embeddings belonging to the same semantic class to generate more similar image content than those from different classes. Doing so can capture more semantic relations by explicitly exploring the structures of labeled pixels from multiple input semantic layouts. Experiments on three challenging datasets show that our ECGAN achieves significantly better results than state-of-the-art methods.

Edge Guided GANs with Contrastive Learning for Semantic Image Synthesis / Tang, Hao; Qi, Xiaojuan; Sun, Guolei; Xu, Dan; Sebe, Nicu; Timofte, Radu; Van Gool, Luc. - 45:12(2023). (Intervento presentato al convegno 11th International Conference on Learning Representations, ICLR 2023 tenutosi a Kigali, Rwanda nel 1-5 May, 2023).

Edge Guided GANs with Contrastive Learning for Semantic Image Synthesis

Tang, Hao;Xu, Dan;Sebe, Nicu;
2023-01-01

Abstract

We propose a novel ECGAN for the challenging semantic image synthesis task. Although considerable improvement has been achieved, the quality of synthesized images is far from satisfactory due to three largely unresolved challenges. 1) The semantic labels do not provide detailed structural information, making it difficult to synthesize local details and structures. 2) The widely adopted CNN operations such as convolution, down-sampling, and normalization usually cause spatial resolution loss and thus cannot fully preserve the original semantic information, leading to semantically inconsistent results. 3) Existing semantic image synthesis methods focus on modeling local semantic information from a single input semantic layout. However, they ignore global semantic information of multiple input semantic layouts, i.e., semantic cross-relations between pixels across different input layouts. To tackle 1), we propose to use edge as an intermediate representation which is further adopted to guide image generation via a proposed attention guided edge transfer module. Edge information is produced by a convolutional generator and introduces detailed structure information. To tackle 2), we design an effective module to selectively highlight class-dependent feature maps according to the original semantic layout to preserve the semantic information. To tackle 3), inspired by current methods in contrastive learning, we propose a novel contrastive learning method, which aims to enforce pixel embeddings belonging to the same semantic class to generate more similar image content than those from different classes. Doing so can capture more semantic relations by explicitly exploring the structures of labeled pixels from multiple input semantic layouts. Experiments on three challenging datasets show that our ECGAN achieves significantly better results than state-of-the-art methods.
2023
International Conference on Learning Representation (ICLR’23)
New York, NY, United States
International Conference on Learning Representations, ICLR
Tang, Hao; Qi, Xiaojuan; Sun, Guolei; Xu, Dan; Sebe, Nicu; Timofte, Radu; Van Gool, Luc
Edge Guided GANs with Contrastive Learning for Semantic Image Synthesis / Tang, Hao; Qi, Xiaojuan; Sun, Guolei; Xu, Dan; Sebe, Nicu; Timofte, Radu; Van Gool, Luc. - 45:12(2023). (Intervento presentato al convegno 11th International Conference on Learning Representations, ICLR 2023 tenutosi a Kigali, Rwanda nel 1-5 May, 2023).
File in questo prodotto:
File Dimensione Formato  
4403_edge_guided_gans_with_contrast (3)-compressed.pdf

accesso aperto

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 566.3 kB
Formato Adobe PDF
566.3 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/400993
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? ND
  • OpenAlex ND
social impact