Pith. sign in

REVIEW 2 cited by

SurfaceNet: An End-to-end 3D Neural Network for Multiview Stereopsis

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1708.01749 v1 pith:MJAMBL5D submitted 2017-08-05 cs.CV

classification cs.CV
keywords surfacenetend-to-endmultiviewnetworkstereopsiscameradirectlyframework
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This paper proposes an end-to-end learning framework for multiview stereopsis. We term the network SurfaceNet. It takes a set of images and their corresponding camera parameters as input and directly infers the 3D model. The key advantage of the framework is that both photo-consistency as well geometric relations of the surface structure can be directly learned for the purpose of multiview stereopsis in an end-to-end fashion. SurfaceNet is a fully 3D convolutional network which is achieved by encoding the camera parameters together with the images in a 3D voxel representation. We evaluate SurfaceNet on the large-scale DTU benchmark.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Point-Based Multi-View Stereo Network

    cs.CV 2019-08 conditional novelty 7.0 of 10

    A point-based network that iteratively refines an initial coarse depth map to yield more accurate and complete multi-view 3D reconstructions.

  2. 3D Point Cloud Super-Resolution via Graph Total Variation on Surface Normals

    eess.SP 2019-08 conditional novelty 5.0 of 10

    A graph total variation regularizer on surface normals, optimized with ADMM on a bipartite graph, upsamples 3D point clouds with lower point-to-point and point-to-plane errors than APSS and RIMLS.

Pith tools