paper-with-me

홈 › Papers

DI-Fusion: Online Implicit 3D Reconstruction with Deep Priors

2020-12-10 · CVPR 2021 1 · Jiahui Huang, Shi-Sheng Huang, Haoxuan Song, Shi-Min Hu

Previous online 3D dense reconstruction methods struggle to achieve the balance between memory storage and surface quality, largely due to the usage of stagnant underlying geometry representation, such as TSDF (truncated signed distance functions) or surfels, without any knowledge of the scene priors. In this paper, we present DI-Fusion (Deep Implicit Fusion), based on a novel 3D representation, i.e. Probabilistic Local Implicit Voxels (PLIVoxs), for online 3D reconstruction with a commodity RGB-D camera. Our PLIVox encodes scene priors considering both the local geometry and uncertainty parameterized by a deep neural network. With such deep priors, we are able to perform online implicit 3D reconstruction achieving state-of-the-art camera trajectory estimation accuracy and mapping quality, while achieving better storage efficiency compared with previous online 3D reconstruction approaches. Our implementation is available at https://www.github.com/huangjh-pub/di-fusion.

📄 PDF Abstract BibTeX arXiv:2012.05551

Code (1)

huangjh-pub/di-fusion 공식 구현 pytorch

Tasks

3D Reconstruction

Similar Papers 제목 키워드 기반

MonoNeuralFusion: Online Monocular Neural 3D Reconstruction with Geometric Priors

2022-09-30 · Zi-Xin Zou, Shi-Sheng Huang, Yan-Pei Cao, Tai-Jiang Mu 외

High-fidelity 3D scene reconstruction from monocular videos continues to be challenging, especially for complete and fine-grained geometry reconstruction. The previous 3D reconstruction approaches with neural implicit re…

3D Reconstruction3D Scene Reconstruction

Online 3D Scene Reconstruction Using Neural Object Priors

2025-03-24 · Thomas Chabal, ShiZhe Chen, Jean Ponce, Cordelia Schmid

This paper addresses the problem of reconstructing a scene online at the level of objects given an RGB-D video sequence. While current object-aware neural implicit representations hold promise, they are limited in online…

3D Scene ReconstructionObject

Learning Deep MRI Reconstruction Models from Scratch in Low-Data Regimes

2023-01-06 · Salman UH Dar, Şaban Öztürk, Muzaffer Özbey, Tolga Çukur

Magnetic resonance imaging (MRI) is an essential diagnostic tool that suffers from prolonged scan times. Reconstruction methods can alleviate this limitation by recovering clinically usable images from accelerated acquis…

DiagnosticMRI ReconstructionRolling Shutter Correction

LCP-Fusion: A Neural Implicit SLAM with Enhanced Local Constraints and Computable Prior

2024-11-06 · Jiahui Wang, Yinan Deng, Yi Yang, Yufeng Yue

Recently the dense Simultaneous Localization and Mapping (SLAM) based on neural implicit representation has shown impressive progress in hole filling and high-fidelity mapping. Nevertheless, existing methods either heavi…

Simultaneous Localization and Mapping

Gaussian Scenes: Pose-Free Sparse-View Scene Reconstruction using Depth-Enhanced Diffusion Priors

2024-11-24 · Soumava Paul, Prakhar Kaushik, Alan Yuille

In this work, we introduce a generative approach for pose-free reconstruction of $360^{\circ}$ scenes from a limited number of uncalibrated 2D images. Pose-free scene reconstruction from incomplete, unposed observations …

Depth EstimationInstruction Following