Semanticmapper: Region-Specific Domain Adaptation for 3D Shapes Through Lexical Delineation

• Main Authors: Xie, Tianci, Luo, Siyang, Chen, Zhenghan, Liang, Xiaoxuan
• Format: Conference Proceeding
• Language: English
• Subjects: Array signal processing; Domain adaptation; Location awareness; Multimodal learning; Navigation; Semantics; Shape; Technological innovation; Text Alignment; Three-dimensional displays
• ISSN: 2379-190X
• DOI: 10.1109/ICASSP48485.2024.10446758

In recent advancements within the domain of three-dimensional semantic mapping, a novel framework termed SemanticMapper has emerged, heralding a paradigm shift in the arena of mesh localization through textual inputs. The core innovation of SemanticMapper lies in its adeptness at navigating and accurately projecting semantic regions onto meshes, particularly excelling in "out-of-domain" scenarios. This capability is exemplified in its seamless overlay of attire onto unclad three-dimensional animal forms. The operational backbone of SemanticMapper is a neural field, ingeniously designed to interpret and apply context to textual descriptions. This is synergistically coupled with a sophisticated probability-weighted blending algorithm, which ensures precise coloration of targeted mesh regions. A pivotal advantage of SemanticMapper is its autonomy from the requisites of three-dimensional data sets or manual annotations, a feature made possible by incorporating a pre-trained CLIP2 encoder. A cornerstone of this research is the integration of Combined Adversarial Domain Adaptation (CADA), a mechanism that significantly enhances the domain adaptability of SemanticMapper. This advancement not only extends the system's efficacy but also broadens its applicability across a diverse array of input shapes, marking a substantial leap in the field of semantic mesh localization.