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

NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priors

About

Reconstructing 3D indoor scenes from 2D images is an important task in many computer vision and graphics applications. A main challenge in this task is that large texture-less areas in typical indoor scenes make existing methods struggle to produce satisfactory reconstruction results. We propose a new method, named NeuRIS, for high quality reconstruction of indoor scenes. The key idea of NeuRIS is to integrate estimated normal of indoor scenes as a prior in a neural rendering framework for reconstructing large texture-less shapes and, importantly, to do this in an adaptive manner to also enable the reconstruction of irregular shapes with fine details. Specifically, we evaluate the faithfulness of the normal priors on-the-fly by checking the multi-view consistency of reconstruction during the optimization process. Only the normal priors accepted as faithful will be utilized for 3D reconstruction, which typically happens in the regions of smooth shapes possibly with weak texture. However, for those regions with small objects or thin structures, for which the normal priors are usually unreliable, we will only rely on visual features of the input images, since such regions typically contain relatively rich visual features (e.g., shade changes and boundary contours). Extensive experiments show that NeuRIS significantly outperforms the state-of-the-art methods in terms of reconstruction quality.

Jiepeng Wang, Peng Wang, Xiaoxiao Long, Christian Theobalt, Taku Komura, Lingjie Liu, Wenping Wang• 2022

Related benchmarks

TaskDatasetResultRank
3D Geometry ReconstructionScanNet
Accuracy5
54
3D Scene ReconstructionScanNet v2 (test)
Accuracy0.054
26
Scene-level 3D ReconstructionScanNet (test)
F-score69.1
20
3D Scene ReconstructionScanNet
Accuracy5.1
9
Scene-level reconstructionScanNet
Chamfer Distance (L1)0.05
8
Scene-level 3D ReconstructionScanNet
Accuracy5
8
3D Scene ReconstructionICL-NUIM
Accuracy4.3
3
Showing 7 of 7 rows

Other info

Follow for update