Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313343968> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W4313343968 abstract "Deep learning (DL)-based coding has recently become very popular for multimedia data, notably images and point clouds (PCs). Training a DL coding model using the backpropagation algorithm requires a differentiable loss function. Thus, for PC joint geometry and color coding, both the PC geometry and color distortion metrics must be differentiable. Since the distortion/quality metrics commonly used for the final PC quality assessment do not meet this criterion, new PC distortion metrics have to be designed for DL-based training purposes. Moreover, for PC joint geometry and color coding, it is critical to define the balance between the geometry and color distortions in a meaningful way, ideally driven by the human perception and subjective quality assessment. In this context, this paper proposes a perceptually-driven design for a differentiable PC joint geometry and color distortion metric to be used for training purposes in DL-based coding, notably to define the relative weights for the geometry and color distortions. The obtained perceptually-driven weights achieve a rate reduction of around 3 % regarding the default balanced weights at no complexity cost. This is the first proposal in the literature with this purpose and this perceptual approach." @default.
- W4313343968 created "2023-01-06" @default.
- W4313343968 creator A5025109904 @default.
- W4313343968 creator A5060502961 @default.
- W4313343968 creator A5069749824 @default.
- W4313343968 date "2022-12-01" @default.
- W4313343968 modified "2023-09-29" @default.
- W4313343968 title "Deep Learning-based Point Cloud Joint Geometry and Color Coding: Designing a Perceptually-Driven Differentiable Training Distortion Metric" @default.
- W4313343968 cites W1994513297 @default.
- W4313343968 cites W2146395539 @default.
- W4313343968 cites W2963351448 @default.
- W4313343968 cites W2964350391 @default.
- W4313343968 cites W2985655328 @default.
- W4313343968 cites W2996188831 @default.
- W4313343968 cites W2996973935 @default.
- W4313343968 cites W3014200484 @default.
- W4313343968 cites W3015751022 @default.
- W4313343968 cites W3035130434 @default.
- W4313343968 cites W3081203363 @default.
- W4313343968 cites W3089343273 @default.
- W4313343968 cites W3098518823 @default.
- W4313343968 cites W3113844551 @default.
- W4313343968 cites W3159975835 @default.
- W4313343968 cites W3202918664 @default.
- W4313343968 doi "https://doi.org/10.1109/bigmm55396.2022.00011" @default.
- W4313343968 hasPublicationYear "2022" @default.
- W4313343968 type Work @default.
- W4313343968 citedByCount "0" @default.
- W4313343968 crossrefType "proceedings-article" @default.
- W4313343968 hasAuthorship W4313343968A5025109904 @default.
- W4313343968 hasAuthorship W4313343968A5060502961 @default.
- W4313343968 hasAuthorship W4313343968A5069749824 @default.
- W4313343968 hasConcept C105795698 @default.
- W4313343968 hasConcept C11413529 @default.
- W4313343968 hasConcept C126780896 @default.
- W4313343968 hasConcept C127413603 @default.
- W4313343968 hasConcept C131979681 @default.
- W4313343968 hasConcept C134306372 @default.
- W4313343968 hasConcept C154945302 @default.
- W4313343968 hasConcept C176217482 @default.
- W4313343968 hasConcept C179518139 @default.
- W4313343968 hasConcept C194257627 @default.
- W4313343968 hasConcept C202615002 @default.
- W4313343968 hasConcept C21547014 @default.
- W4313343968 hasConcept C2524010 @default.
- W4313343968 hasConcept C2776257435 @default.
- W4313343968 hasConcept C31258907 @default.
- W4313343968 hasConcept C31972630 @default.
- W4313343968 hasConcept C33923547 @default.
- W4313343968 hasConcept C41008148 @default.
- W4313343968 hasConceptScore W4313343968C105795698 @default.
- W4313343968 hasConceptScore W4313343968C11413529 @default.
- W4313343968 hasConceptScore W4313343968C126780896 @default.
- W4313343968 hasConceptScore W4313343968C127413603 @default.
- W4313343968 hasConceptScore W4313343968C131979681 @default.
- W4313343968 hasConceptScore W4313343968C134306372 @default.
- W4313343968 hasConceptScore W4313343968C154945302 @default.
- W4313343968 hasConceptScore W4313343968C176217482 @default.
- W4313343968 hasConceptScore W4313343968C179518139 @default.
- W4313343968 hasConceptScore W4313343968C194257627 @default.
- W4313343968 hasConceptScore W4313343968C202615002 @default.
- W4313343968 hasConceptScore W4313343968C21547014 @default.
- W4313343968 hasConceptScore W4313343968C2524010 @default.
- W4313343968 hasConceptScore W4313343968C2776257435 @default.
- W4313343968 hasConceptScore W4313343968C31258907 @default.
- W4313343968 hasConceptScore W4313343968C31972630 @default.
- W4313343968 hasConceptScore W4313343968C33923547 @default.
- W4313343968 hasConceptScore W4313343968C41008148 @default.
- W4313343968 hasLocation W43133439681 @default.
- W4313343968 hasOpenAccess W4313343968 @default.
- W4313343968 hasPrimaryLocation W43133439681 @default.
- W4313343968 hasRelatedWork W2033574012 @default.
- W4313343968 hasRelatedWork W2111347602 @default.
- W4313343968 hasRelatedWork W2979718872 @default.
- W4313343968 hasRelatedWork W3006763290 @default.
- W4313343968 hasRelatedWork W3090896893 @default.
- W4313343968 hasRelatedWork W3151946617 @default.
- W4313343968 hasRelatedWork W3202424074 @default.
- W4313343968 hasRelatedWork W3204162010 @default.
- W4313343968 hasRelatedWork W3206828132 @default.
- W4313343968 hasRelatedWork W4310007291 @default.
- W4313343968 isParatext "false" @default.
- W4313343968 isRetracted "false" @default.
- W4313343968 workType "article" @default.