DI-Fusion: Online Implicit 3D Reconstruction with Deep Priors
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.
Code (1)
Tasks
3D ReconstructionSimilar Papers 제목 키워드 기반
MonoNeuralFusion: Online Monocular Neural 3D Reconstruction with Geometric Priors
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 ReconstructionOnline 3D Scene Reconstruction Using Neural Object Priors
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 ReconstructionObjectLearning Deep MRI Reconstruction Models from Scratch in Low-Data Regimes
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 CorrectionLCP-Fusion: A Neural Implicit SLAM with Enhanced Local Constraints and Computable Prior
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 MappingGaussian Scenes: Pose-Free Sparse-View Scene Reconstruction using Depth-Enhanced Diffusion Priors
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