Evaluating Modern Approaches in 3D Scene Reconstruction: NeRF vs Gaussian-Based Methods

Zhou, Yiming; Zeng, Zixuan; Chen, Andi; Zhou, Xiaofan; Ni, Haowei; Zhang, Shiyao; Li, Panfeng; Liu, Liangxi; Zheng, Mengyao; Chen, Xupeng

doi:10.1109/docs63458.2024.10704527

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2024

Publication Types

Select...

Other2

Article2

Relationship

Self Cite0

Independent4

Authors

Journals

Cited by 4 publications

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Enhancing Skin Lesion Diagnosis with Ensemble Learning

Liu,

Yu,

Tan

et al. 2024

2024 4th International Conference on Computer Science and Blockchain (CCSB)

View full text Add to dashboard Cite

Enhancing Skin Lesion Diagnosis with Ensemble Learning

Liu,

Yu,

Tan

et al. 2024

2024 4th International Conference on Computer Science and Blockchain (CCSB)

View full text Add to dashboard Cite

Style Transfer: From Stitching to Neural Networks

Xu,

Wang,

Zhang

et al. 2024

2024 5th International Conference on Big Data &Amp;amp; Artificial Intelligence &Amp;amp; Software Engineering (ICBASE)

View full text Add to dashboard Cite

Neural Surfel Reconstruction: Addressing Loop Closure Challenges in Large-Scale 3D Neural Scene Mapping

Cui,

Zhang,

Kneip

et al. 2024

Sensors

View full text Add to dashboard Cite

Efficiently reconstructing complex and intricate surfaces at scale remains a significant challenge in 3D surface reconstruction. Recently, implicit neural representations have become a popular topic in 3D surface reconstruction. However, how to handle loop closure and bundle adjustment is a tricky problem for neural methods, because they learn the neural parameters globally. We present an algorithm that leverages the concept of surfels and expands relevant definitions to address such challenges. By integrating neural descriptors with surfels and framing surfel association as a deformation graph optimization problem, our method is able to effectively perform loop closure detection and loop correction in challenging scenarios. Furthermore, the surfel-level representation simplifies the complexity of 3D neural reconstruction. Meanwhile, the binding of neural descriptors to corresponding surfels produces a dense volumetric signed distance function (SDF), enabling the mesh reconstruction. Our approach demonstrates a significant improvement in reconstruction accuracy, reducing the average error by 16.9% compared to previous methods, while also generating modeling files that are up to 90% smaller than those produced by traditional methods.

show abstract

Evaluating Modern Approaches in 3D Scene Reconstruction: NeRF vs Gaussian-Based Methods

Cited by 4 publications

References 28 publications

Enhancing Skin Lesion Diagnosis with Ensemble Learning

Enhancing Skin Lesion Diagnosis with Ensemble Learning

Style Transfer: From Stitching to Neural Networks

Neural Surfel Reconstruction: Addressing Loop Closure Challenges in Large-Scale 3D Neural Scene Mapping

Contact Info

Product

Resources

About