Improve neural surface reconstruction by using surface normals in smooth regions with NeuRIS

Improve neural surface reconstruction by using surface normals in smooth regions with NeuRIS

NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priors

arXiv paper abstract https://arxiv.org/abs/2206.13597

arXiv PDF paper https://arxiv.org/pdf/2206.13597.pdf

Project page https://jiepengwang.github.io/NeuRIS

Reconstructing 3D indoor scenes from 2D images ... main challenge ... is that large texture-less areas in typical indoor scenes make existing methods struggle to produce satisfactory reconstruction results.

... propose ... NeuRIS, for high quality reconstruction of indoor scenes.

... 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.

... for ... small objects or thin structures, for which ... normal ... are ... unreliable ... rely on visual features of the input images, since such regions typically contain relatively rich visual features (e.g., shade changes and boundary contours).

... NeuRIS significantly outperforms the state-of-the-art methods in terms of reconstruction quality.

Please like and share this post if you enjoyed it using the buttons at the bottom! Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact Web site with my other posts by category https://morrislee1234.wixsite.com/website LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b #ComputerVision #3D #AINewsClips #AI #ML #ArtificialIntelligence #MachineLearning