Skip to content
English

Switch theme

arXiv 2610.24738 · cs.CV · 2026-10-17

Editing Images into Reusable Layers via Compositional Edit-Prior Distillation

Wen Xue, Yong Liu, Xueheng Li, Si Wu, Yong Xu, Yipeng Sun, Yan Li, Simiu Gu

jingdong

In latest · #166 2026-W43 #9 Added on 2026-10-24

One-line takeaway

JD's LayerEditor unifies instruction-guided image editing with controllable generation of reusable RGBA layers: one token sequence jointly represents the edited canvas and an ordered stack of RGB-Alpha layers, so edits stay layer-separable and reusable instead of flattened.

京东的 LayerEditor 把指令式图像编辑和可复用 RGBA 图层生成合在一个框架里:在同一个 token 序列里同时表示编辑后的画面和有序的 RGB-Alpha 图层,编辑结果可以按图层单独调整和复用,而不是一张拍平的图。

191HF upvotes
–GitHub stars
0Citations (Semantic Scholar)
54.2Buzz score

Read on arXiv PDF Hugging Face discussion

About this data

Metadata from the arXiv API (verified); upvotes from Hugging Face Daily Papers; citations from Semantic Scholar. Last refreshed 2026-10-26.

The takeaway is written by AIMap from the abstract; the abstract itself is not reproduced — read the original.

Data updated: Latest AI papers(UTC+8)