研究人员开发了PhysEdit，一个新颖的图像编辑框架，通过调整其推理过程来提高效率和准确性。该系统集成了复杂度自适应推理深度（CARD），根据编辑复杂度动态调整推理步数和令牌长度。此外，空间推理掩码（SRM）将计算资源集中在图像内的语义相关区域。这种自适应方法在基准数据集上实现了1.18倍的加速，同时保持或略微提高了编辑质量。 AI
影响 通过动态分配计算资源来提高图像编辑任务的效率，可能加快内容创作工作流程。
排序理由 详细介绍一种具有自适应推理的新型图像编辑方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
Large diffusion transformers (DiTs) follow global editing instructions well but consistently leak local edits into unrelated regions, because joint-attention architectures offer no explicit channel telling the network where to apply the edit. We introduce AdaptEdit, a co-trained,…
arXiv:2605.00707v1 Announce Type: new Abstract: Image editing instructions are heterogeneous: a color swap, an object insertion, and a physical-action edit all demand different spatial coverage and different reasoning depth, yet existing reasoning-based editors apply a single fix…
Image editing instructions are heterogeneous: a color swap, an object insertion, and a physical-action edit all demand different spatial coverage and different reasoning depth, yet existing reasoning-based editors apply a single fixed inference recipe to every instruction. We arg…