paper-with-me

홈 › Papers

Vox-Surf: Voxel-based Implicit Surface Representation

2022-08-21 · Hai Li, Xingrui Yang, Hongjia Zhai, Yuqian Liu, Hujun Bao, Guofeng Zhang

Virtual content creation and interaction play an important role in modern 3D applications such as AR and VR. Recovering detailed 3D models from real scenes can significantly expand the scope of its applications and has been studied for decades in the computer vision and computer graphics community. We propose Vox-Surf, a voxel-based implicit surface representation. Our Vox-Surf divides the space into finite bounded voxels. Each voxel stores geometry and appearance information in its corner vertices. Vox-Surf is suitable for almost any scenario thanks to sparsity inherited from voxel representation and can be easily trained from multiple view images. We leverage the progressive training procedure to extract important voxels gradually for further optimization so that only valid voxels are preserved, which greatly reduces the number of sampling points and increases rendering speed.The fine voxels can also be considered as the bounding volume for collision detection.The experiments show that Vox-Surf representation can learn delicate surface details and accurate color with less memory and faster rendering speed than other methods.We also show that Vox-Surf can be more practical in scene editing and AR applications.

📄 PDF Abstract BibTeX arXiv:2208.10925

Code (1)

zju3dv/vox-surf 공식 구현 pytorch

Tasks

valid

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

IPVNet: Learning Implicit Point-Voxel Features for Open-Surface 3D Reconstruction

2023-11-05 · Mohammad Samiul Arshad, William J. Beksi

Reconstruction of 3D open surfaces (e.g., non-watertight meshes) is an underexplored area of computer vision. Recent learning-based implicit techniques have removed previous barriers by enabling reconstruction in arbitra…

3D Reconstruction

Neural Volumetric Mesh Generator

2022-10-06 · Yan Zheng, Lemeng Wu, Xingchao Liu, Zhen Chen 외

Deep generative models have shown success in generating 3D shapes with different representations. In this work, we propose Neural Volumetric Mesh Generator(NVMG) which can generate novel and high-quality volumetric meshe…

HVOFusion: Incremental Mesh Reconstruction Using Hybrid Voxel Octree

2024-04-27 · Shaofan Liu, Junbo Chen, Jianke Zhu

Incremental scene reconstruction is essential to the navigation in robotics. Most of the conventional methods typically make use of either TSDF (truncated signed distance functions) volume or neural networks to implicitl…

GVKF: Gaussian Voxel Kernel Functions for Highly Efficient Surface Reconstruction in Open Scenes

2024-11-04 · Gaochao Song, Chong Cheng, Hao Wang

In this paper we present a novel method for efficient and effective 3D surface reconstruction in open scenes. Existing Neural Radiance Fields (NeRF) based works typically require extensive training and rendering time due…

3DGSNeRFSurface Reconstruction

Implicit Surface Representations As Layers in Neural Networks

2019-10-01 · ICCV 2019 10 · Mateusz Michalkiewicz, Jhony K. Pontes, Dominic Jack, Mahsa Baktashmotlagh 외

Implicit shape representations, such as Level Sets, provide a very elegant formulation for performing computations involving curves and surfaces. However, including implicit representations into canonical Neural Network …