Avatar Concept Slider: Controllable Editing of Concepts in 3D Human Avatars
This addresses the problem of ambiguous and limited text-based editing for 3D human avatars, offering a more precise and efficient solution for users in digital content creation, though it is incremental as it builds on existing 3D editing methods.
The paper tackles the challenge of precise text-based editing of 3D human avatars by proposing the Avatar Concept Slider, which enables controllable editing of semantic concepts along a slider-like interface, resulting in improved preservation of avatar identity and efficiency without compromising quality.
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.