Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382466831> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4382466831 endingPage "2356" @default.
- W4382466831 startingPage "2348" @default.
- W4382466831 abstract "Over the years, learning-based multi-view stereo methods have achieved great success based on their coarse-to-fine depth estimation frameworks. However, 3D CNN-based cost volume regularization inevitably leads to over-smoothing problems at object boundaries due to its smooth properties. Moreover, discrete and sparse depth hypothesis sampling exacerbates the difficulty in recovering the depth of thin structures and object boundaries. To this end, we present an Efficient edge-Preserving multi-view stereo Network (EPNet) for practical depth estimation. To keep delicate estimation at details, a Hierarchical Edge-Preserving Residual learning (HEPR) module is proposed to progressively rectify the upsampling errors and help refine multi-scale depth estimation. After that, a Cross-view Photometric Consistency (CPC) is proposed to enhance the gradient flow for detailed structures, which further boosts the estimation accuracy. Last, we design a lightweight cascade framework and inject the above two strategies into it to achieve better efficiency and performance trade-offs. Extensive experiments show that our method achieves state-of-the-art performance with fast inference speed and low memory usage. Notably, our method tops the first place on challenging Tanks and Temples advanced dataset and ETH3D high-res benchmark among all published learning-based methods. Code will be available at https://github.com/susuwj/EPNet." @default.
- W4382466831 created "2023-06-29" @default.
- W4382466831 creator A5008451144 @default.
- W4382466831 creator A5087239641 @default.
- W4382466831 date "2023-06-26" @default.
- W4382466831 modified "2023-09-23" @default.
- W4382466831 title "Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation" @default.
- W4382466831 doi "https://doi.org/10.1609/aaai.v37i2.25330" @default.
- W4382466831 hasPublicationYear "2023" @default.
- W4382466831 type Work @default.
- W4382466831 citedByCount "0" @default.
- W4382466831 crossrefType "journal-article" @default.
- W4382466831 hasAuthorship W4382466831A5008451144 @default.
- W4382466831 hasAuthorship W4382466831A5087239641 @default.
- W4382466831 hasBestOaLocation W43824668311 @default.
- W4382466831 hasConcept C108583219 @default.
- W4382466831 hasConcept C110384440 @default.
- W4382466831 hasConcept C11413529 @default.
- W4382466831 hasConcept C115961682 @default.
- W4382466831 hasConcept C13280743 @default.
- W4382466831 hasConcept C141268832 @default.
- W4382466831 hasConcept C154945302 @default.
- W4382466831 hasConcept C155512373 @default.
- W4382466831 hasConcept C162307627 @default.
- W4382466831 hasConcept C185798385 @default.
- W4382466831 hasConcept C205649164 @default.
- W4382466831 hasConcept C2776214188 @default.
- W4382466831 hasConcept C2776436953 @default.
- W4382466831 hasConcept C31972630 @default.
- W4382466831 hasConcept C3770464 @default.
- W4382466831 hasConcept C41008148 @default.
- W4382466831 hasConceptScore W4382466831C108583219 @default.
- W4382466831 hasConceptScore W4382466831C110384440 @default.
- W4382466831 hasConceptScore W4382466831C11413529 @default.
- W4382466831 hasConceptScore W4382466831C115961682 @default.
- W4382466831 hasConceptScore W4382466831C13280743 @default.
- W4382466831 hasConceptScore W4382466831C141268832 @default.
- W4382466831 hasConceptScore W4382466831C154945302 @default.
- W4382466831 hasConceptScore W4382466831C155512373 @default.
- W4382466831 hasConceptScore W4382466831C162307627 @default.
- W4382466831 hasConceptScore W4382466831C185798385 @default.
- W4382466831 hasConceptScore W4382466831C205649164 @default.
- W4382466831 hasConceptScore W4382466831C2776214188 @default.
- W4382466831 hasConceptScore W4382466831C2776436953 @default.
- W4382466831 hasConceptScore W4382466831C31972630 @default.
- W4382466831 hasConceptScore W4382466831C3770464 @default.
- W4382466831 hasConceptScore W4382466831C41008148 @default.
- W4382466831 hasIssue "2" @default.
- W4382466831 hasLocation W43824668311 @default.
- W4382466831 hasOpenAccess W4382466831 @default.
- W4382466831 hasPrimaryLocation W43824668311 @default.
- W4382466831 hasRelatedWork W1998618079 @default.
- W4382466831 hasRelatedWork W2003340466 @default.
- W4382466831 hasRelatedWork W2090346739 @default.
- W4382466831 hasRelatedWork W2787555990 @default.
- W4382466831 hasRelatedWork W2921666650 @default.
- W4382466831 hasRelatedWork W3005941135 @default.
- W4382466831 hasRelatedWork W3091976719 @default.
- W4382466831 hasRelatedWork W3147384217 @default.
- W4382466831 hasRelatedWork W3207322857 @default.
- W4382466831 hasRelatedWork W3208409104 @default.
- W4382466831 hasVolume "37" @default.
- W4382466831 isParatext "false" @default.
- W4382466831 isRetracted "false" @default.
- W4382466831 workType "article" @default.