Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

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

About

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.

Jiahui Huang, Shi-Sheng Huang, Haoxuan Song, Shi-Min Hu• 2020

Related benchmarks

TaskDatasetResultRank
Camera pose estimationScanNet
ATE RMSE (Avg.)78.89
61
ReconstructionReplica average over 8 scenes
Accuracy (Dist)19.4
21
Camera TrackingTUM RGB-D fr1 desk
ATE RMSE0.044
16
Camera TrackingTUM RGB-D fr2 xyz
ATE RMSE0.02
16
Camera TrackingTUM RGB-D fr3 office
ATE RMSE0.058
16
Camera TrackingTUM RGB-D
ATE RMSE (cm)4.07
13
TrackingTUM-RGBD fr1_desk, fr2_xyz, fr3_off
fr1_desk Tracking Error4.4
12
DenoisingMRI sigma=0.05
PSNR37.21
7
DenoisingMRI sigma=0.10
PSNR35.82
7
DenoisingMRI sigma=0.15
PSNR35.1
7
Showing 10 of 12 rows

Other info

Follow for update