Submitted by Fangjinhua Wang.

Submission data

Full namePatchmatchNet
DescriptionWe present PatchmatchNet, a novel and learnable cascade formulation of Patchmatch for high-resolution multi-view stereo. With high computation speed and low memory requirement, PatchmatchNet can process higher resolution imagery and is more suited to run on resource limited devices than competitors that employ 3D cost volume regularization. For the first time we introduce an iterative multi-scale Patchmatch in an end-to-end trainable architecture and improve the Patchmatch core algorithm with a novel and learned adaptive propagation and evaluation scheme for each iteration. Extensive experiments show a very competitive performance and generalization for our method on DTU, Tanks & Temples and ETH3D, but at a significantly higher efficiency than all existing top-performing models: at least two and a half times faster than state-of-the-art methods with twice less memory usage.
Parametersimage size: 2688*1792
Publication titlePatchmatchNet: Learned Multi-View Patchmatch Stereo
Publication authorsFangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys
Publication URLhttps://arxiv.org/abs/2012.01411
Programming language(s)python
HardwareIntel(R) Core(TM) i7-9700K CPU @ 3.60GHz, GeForce RTX 2080, RAM: 32GB
Source code or download URLhttps://github.com/FangjinhuaWang/PatchmatchNet
Submission creation date8 Aug, 2020
Last edited18 Mar, 2021

High-res multi-view results



Infoallhigh-res
multi-view
indooroutdoorbotani.boulde.bridgedoorexhibi.lectur.living.loungeobserv.old co.statueterrac.
permissive91.9191.3593.5995.3884.1193.1595.3989.5492.1093.6882.8298.1384.8195.3298.52

Low-res many-view results



Infoalllow-res
many-view
indooroutdoordelivery areaelectroforestplaygroundterrains
No results yet.

Low-res two-view results



Infoalllakes. 1llakes. 1ssand box 1lsand box 1sstora. room 1lstora. room 1sstora. room 2lstora. room 2sstora. room 2 1lstora. room 2 1sstora. room 2 2lstora. room 2 2sstora. room 3lstora. room 3stunnel 1ltunnel 1stunnel 2ltunnel 2stunnel 3ltunnel 3s
No results yet.

SLAM results



allboxesboxes darkbuddhacables 4cables 5desk 1desk 2desk changing 2desk dark 1desk dark 2desk global light changesdesk ir lightdinodroneforeground occlusionhelmetkidnap 2lamplarge loop 2large loop 3large non loopmotion 2motion 3motion 4planar 1reflective 2scale changetable 1table 2table 5table 6table global light changestable local light changestable scenetrashbin
MethodInfo
No results yet.