5 research outputs found
CGS: Continual Gaussian Splatting for Evolving 3D Scene Reconstruction
No full text3D Gaussian Splatting (3DGS) has gained significant attention for its fast optimization and high-quality rendering capabilities. However, in the context of continual scene reconstruction, optimizing newly observed regions often leads to degradation in previously reconstructed areas due to changes in camera viewpoints. To address this issue, we propose Continual Gaussian Splatting (CGS)-an efficient incremental reconstruction method that updates dynamic scenes using only a limited amount of new data while minimizing computational overhead. CGS is composed of three core components. First, we introduce a similarity-based registration algorithm that leverages the strong semantic understanding and translation invariance of pretrained Transformers to identify and align similar regions between new and existing scenes. These regions are then modeled as Gaussian Mixture Models (GMMs) to handle sparsity and outliers in point clouds, ensuring geometric consistency across scenes. Second, we propose Continual Gaussian Optimization (CGO), an importance-aware optimization strategy. By computing the Fisher Information Matrix, we evaluate the significance of each Gaussian point in the old scene and automatically restrict updates to those deemed critical, allowing only non-sensitive components to be adjusted. This ensures the preservation of the original scene while efficiently integrating new content. Finally, to address remaining issues such as geometric inconsistencies, blurring, and ghosting artifacts during optimization, we introduce a series of geometric regularization techniques. These terms guide the optimization toward geometrically coherent 3D structures, ultimately enhancing rendering quality. Extensive experiments demonstrate that CGS effectively mitigates forgetting and significantly improves overall reconstruction fidelity.Pacific Graphics Conference Papers, Posters, and DemosPoint Clouds & Gaussian Splattin
Generating animatable 3D cartoon faces from single portraits
No full textBackground
With the development of virtual reality (VR) technology, there is a growing need for customized 3D avatars. However, traditional methods for 3D avatar modeling are either time-consuming or fail to retain the similarity to the person being modeled. This study presents a novel framework for generating animatable 3D cartoon faces from a single portrait image.
Methods
First, we transferred an input real-world portrait to a stylized cartoon image using StyleGAN. We then proposed a two-stage reconstruction method to recover a 3D cartoon face with detailed texture. Our two-stage strategy initially performs coarse estimation based on template models and subsequently refines the model by nonrigid deformation under landmark supervision. Finally, we proposed a semantic-preserving face-rigging method based on manually created templates and deformation transfer.
Conclusions
Compared with prior arts, the qualitative and quantitative results show that our method achieves better accuracy, aesthetics, and similarity criteria. Furthermore, we demonstrated the capability of the proposed 3D model for real-time facial animation
Knowledge graph construction with structure and parameter learning for indoor scene design
No full textAbstract We consider the problem of learning a representation of both spatial relations and dependencies between objects for indoor scene design. We propose a novel knowledge graph framework based on the entity-relation model for representation of facts in indoor scene design, and further develop a weaklysupervised algorithm for extracting the knowledge graph representation from a small dataset using both structure and parameter learning. The proposed framework is flexible, transferable, and readable. We present a variety of computer-aided indoor scene design applications using this representation, to show the usefulness and robustness of the proposed framework
Reconstruction of the lost colonial architecture in the context of heritage tourism: Dutch Trading Post in Taiwan
No full textAbstract To strengthen brand identity, enrich tourist experiences, and promote heritage education, Taijiang National Park proposed to reconstruct Taiwan’s Dutch Trading Post in a different location from where it was initially erected in the 17th century. This paper is a case study of the reconstruction proposal for a lost colonial architectural complex in the context of heritage tourism. It discusses the practical and academic issues of rebuilding long-lost colonial heritage sites. The author provided a first-hand account of the technical and practical reasoning for reconstructing a bygone complex erected by Dutch settlers. Historical development phases of the Dutch Trading Post of Taiwan were first introduced, and then a reconstruction strategy was proposed to resolve conflicts with legal constraints. Additionally, a site selection process using GIS, a conceptually driven plan for reconstruction, and a 3D simulation were provided. Three specific issues in heritage rebuilding were further discussed, including the decision to reconstruct a heritage building (complex), the authenticity of the reconstructed building if done in a different location from where it was initially situated, and the need to discover more archaeological facts
