Papers › SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing Objects
SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing Objects
Evangelos Ntavelis, Andrés Romero, Iason Kastanis, Luc van Gool, Radu Timofte
Recent advances in image generation gave rise to powerful tools for semantic image editing. However, existing approaches can either operate on a single image or require an abundance of additional information. They are not capable of handling the complete set of editing operations, that is addition, manipulation or removal of semantic concepts. To address these limitations, we propose SESAME, a novel generator-discriminator pair for Semantic Editing of Scenes by Adding, Manipulating or Erasing objects. In our setup, the user provides the semantic labels of the areas to be edited and the generator synthesizes the corresponding pixels. In contrast to previous methods that employ a discriminator that trivially concatenates semantics and image as an input, the SESAME discriminator is composed of two input streams that independently process the image and its semantics, using the latter to manipulate the results of the former. We evaluate our model on a diverse set of datasets and report state-of-the-art performance on two tasks: (a) image manipulation and (b) image generation conditioned on semantic labels.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Image-to-Image Translation | ADE20K Labels-to-Photos | SPADE + SESAME | Accuracy | 85.5% | #4 of 16 | Archive leaderboard | report |
| Image-to-Image Translation | ADE20K Labels-to-Photos | SPADE + SESAME | FID | 31.9 | #4 of 16 | Archive leaderboard | report |
| Image-to-Image Translation | ADE20K Labels-to-Photos | SPADE + SESAME | mIoU | 49 | #4 of 16 | Archive leaderboard | report |
| Image-to-Image Translation | Cityscapes Labels-to-Photo | SPADE + SESAME | FID | 54.2 | #4 of 21 | Archive leaderboard | report |
| Image-to-Image Translation | Cityscapes Labels-to-Photo | SPADE + SESAME | Per-pixel Accuracy | 82.5% | #4 of 21 | Archive leaderboard | report |
| Image-to-Image Translation | Cityscapes Labels-to-Photo | SPADE + SESAME | mIoU | 66 | #4 of 21 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections