Avatar Concept Slider：3D 人体 Avatar 中概念的可控编辑
Avatar Concept Slider: Controllable Editing of Concepts in 3D Human Avatars
AI总结：
提出 Avatar Concept Slider，通过概念轴定位、身份保持和敏感 3D Gaussian Splatting 基元选择，实现 3D 人体 avatar 语义概念的连续可控编辑。
摘要：
由于自然语言固有的模糊性和有限的表达能力，通过基于文本的编辑使 3D 人体 avatar 精确符合用户要求具有挑战性。为克服这一问题，我们提出 Avatar Concept Slider（ACS），这是一种 3D avatar 编辑方法，能够将人体 avatar 中的语义概念精确编辑到两个概念极端之间指定的中间点，就像沿滑块轨道移动旋钮一样。为实现这一点，我们的 ACS 包含三项设计：首先，提出基于线性判别分析的 Concept Sliding Loss，用于定位特定概念轴以实现精确编辑；其次，提出基于主成分分析的 Attribute Preserving Loss，用于在编辑过程中更好地保持 avatar 身份。我们还提出一种基于概念敏感性的 3D Gaussian Splatting 基元选择机制，仅更新对目标概念最敏感的基元，从而提高效率。结果表明，我们的 ACS 能够实现可控的 3D avatar 编辑，同时不会损害 avatar 质量或其身份属性。
英文摘要：
Text-based editing of 3D human avatars to precisely match user requirements is challenging due to the inherent ambiguity and limited expressiveness of natural language. To overcome this, we propose the Avatar Concept Slider (ACS), a 3D avatar editing method that allows precise editing of semantic concepts in human avatars towards a specified intermediate point between two extremes of concepts, akin to moving a knob along a slider track. To achieve this, our ACS has three designs: Firstly, a Concept Sliding Loss based on linear discriminant analysis to pinpoint the concept-specific axes for precise editing. Secondly, an Attribute Preserving Loss based on principal component analysis for improved preservation of avatar identity during editing. We further propose a 3D Gaussian Splatting primitive selection mechanism based on concept-sensitivity, which updates only the primitives that are the most sensitive to our target concept, to improve efficiency. Results demonstrate that our ACS enables controllable 3D avatar editing, without compromising the avatar quality or its identifying attributes.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
