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
在最新榜 #166 2026-W43 第 9 名 本站收录于 2026-10-24
一句话要点
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。
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.
阅读 arXiv 原文 PDF Hugging Face 讨论
主题与学科
同主题：视觉生成
- StreamEval: Evaluating Interactive Streaming Video Generation Models ▲649
- MaLiang-Harness: A Programmable Path to Image and Video Generation ▲367
- Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation ▲364
- DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models ▲325
- Making MLLM Latents Matter: Factor-Aware Predictive Learning for Cinematic Video Generation ▲200
同主题：多模态
- MJev-Spatial: System One Spatial Intelligence via Native Attention Matching 2026-10-15 · ▲556
- Omni-IO Skills: Harnessing Your Agent Omni-Native 2026-09-25 · ▲485
- LoopVL: Recurrent Visual Intelligence 2026-09-29 · ▲417
- VideoJev: System One Model for Video Understanding and Interaction 2026-10-13 · ▲375
- S-Space: Exploring Spatial Workspace in Multimodal Language Models 2026-10-09 · ▲270
同机构：jingdong
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-26。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。