Aug 28, 2022 · We propose a novel Multi-Expansion (MEx) loss. It is implemented by the adversarial loss on MEx areas. Each MEx area has the inpainted area as dominance.

Semantic Inpainting on Segmentation Map (SISM) aims to manipulate segmentation maps by semantics. Recent works show SISM provides semantic-aware auxiliary ...

Semantic Inpainting on Segmentation Map (SISM) aims to manipulate segmentation maps by semantics. Recent works show SISM provides semantic-aware auxiliary ...

Oct 16, 2020 · We propose MExGAN for semantic editing on segmentation map, which uses a novel Multi-Expansion (MEx) loss implemented by adversarial losses on MEx areas.

Semantic Inpainting on Segmentation Map (SISM) aims to manipulate segmentation maps by semantics. Recent works show SISM provides semantic-aware auxiliary ...

Oct 26, 2020 · Semantic editing on segmentation map has been proposed as an intermediate interface for image generation, because it provides flexible and ...

Semantic inpainting on segmentation map via multi-expansion loss. record by Shuo Lei • Semantic inpainting on segmentation map via multi-expansion loss.

This paper proposes MExGAN for semantic editing on segmentation map, which uses a novel Multi-Expansion (MEx) loss implemented by adversarial losses on MEx ...

README. Code Introduction. This is the code for Neurocomputing 2022 paper Semantic Inpainting on Segmentation Map via Multi-Expansion Loss.

This paper aims to improve quality of edited segmentation map conditioned on semantic inputs. Even though recent studies apply global and local adversarial ...