Matches in SemOpenAlex for { <https://semopenalex.org/work/W2223551652> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W2223551652 abstract "This dissertation addresses the problem of inferring scene depth information from a collection of calibrated images taken from different viewpoints via stereo matching. Although it has been heavily investigated for decades, depth from stereo remains a long-standing challenge and popular research topic for several reasons. First of all, in order to be of practical use for many real-time applications such as autonomous driving, accurate depth estimation in real-time is of great importance and one of the core challenges in stereo. Second, for applications such as 3D reconstruction and view synthesis, high-quality depth estimation is crucial to achieve photo realistic results. However, due to the matching ambiguities, accurate dense depth estimates are difficult to achieve. Last but not least, most stereo algorithms rely on identification of corresponding points among images and only work effectively when scenes are Lambertian. For non-Lambertian surfaces, the brightness constancy assumption is no longer valid. This dissertation contributes three novel stereo algorithms that are motivated by the specific requirements and limitations imposed by different applications.In addressing high speed depth estimation from images, we present a stereo algorithm that achieves high quality results while maintaining real-time performance. We introduce an adaptive aggregation step in a dynamic-programming framework. Matching costs are aggregated in the vertical direction using a computationally expensive weighting scheme based on color and distance proximity. We utilize the vector processing capability and parallelism in commodity graphics hardware to speed up this process over two orders of magnitude.In addressing high accuracy depth estimation, we present a stereo model that makes use of constraints from points with known depths - the Ground Control Points (GCPs) as referred to in stereo literature. Our formulation explicitly models the influences of GCPs in a Markov Random Field. A novel regularization prior is naturally integrated into a global inference framework in a principled way using the Bayes rule. Our probabilistic framework allows GCPs to be obtained from various modalities and provides a natural way to integrate information from various sensors.In addressing non-Lambertian reflectance, we introduce a new invariant for stereo correspondence which allows completely arbitrary scene reflectance (bidirectional reflectance distribution functions - BRDFs). This invariant can be used to formulate a rank constraint on stereo matching when the scene is observed by several lighting configurations in which only the lighting intensity varies.KEYWORDS: Stereo Matching, Bilateral Filtering, Dynamic Programming, Global Optimization, Light Transport Constancy Author's." @default.
- W2223551652 created "2016-06-24" @default.
- W2223551652 creator A5015051749 @default.
- W2223551652 creator A5086664647 @default.
- W2223551652 date "2012-01-01" @default.
- W2223551652 modified "2023-09-27" @default.
- W2223551652 title "Novel dense stereo algorithms for high-quality depth estimation from images" @default.
- W2223551652 hasPublicationYear "2012" @default.
- W2223551652 type Work @default.
- W2223551652 sameAs 2223551652 @default.
- W2223551652 citedByCount "0" @default.
- W2223551652 crossrefType "journal-article" @default.
- W2223551652 hasAuthorship W2223551652A5015051749 @default.
- W2223551652 hasAuthorship W2223551652A5086664647 @default.
- W2223551652 hasConcept C105795698 @default.
- W2223551652 hasConcept C111919701 @default.
- W2223551652 hasConcept C11413529 @default.
- W2223551652 hasConcept C116834253 @default.
- W2223551652 hasConcept C126838900 @default.
- W2223551652 hasConcept C154945302 @default.
- W2223551652 hasConcept C165064840 @default.
- W2223551652 hasConcept C183115368 @default.
- W2223551652 hasConcept C205711294 @default.
- W2223551652 hasConcept C2776449333 @default.
- W2223551652 hasConcept C31451488 @default.
- W2223551652 hasConcept C31972630 @default.
- W2223551652 hasConcept C33923547 @default.
- W2223551652 hasConcept C35861506 @default.
- W2223551652 hasConcept C41008148 @default.
- W2223551652 hasConcept C59822182 @default.
- W2223551652 hasConcept C68537008 @default.
- W2223551652 hasConcept C71924100 @default.
- W2223551652 hasConcept C86803240 @default.
- W2223551652 hasConcept C98045186 @default.
- W2223551652 hasConceptScore W2223551652C105795698 @default.
- W2223551652 hasConceptScore W2223551652C111919701 @default.
- W2223551652 hasConceptScore W2223551652C11413529 @default.
- W2223551652 hasConceptScore W2223551652C116834253 @default.
- W2223551652 hasConceptScore W2223551652C126838900 @default.
- W2223551652 hasConceptScore W2223551652C154945302 @default.
- W2223551652 hasConceptScore W2223551652C165064840 @default.
- W2223551652 hasConceptScore W2223551652C183115368 @default.
- W2223551652 hasConceptScore W2223551652C205711294 @default.
- W2223551652 hasConceptScore W2223551652C2776449333 @default.
- W2223551652 hasConceptScore W2223551652C31451488 @default.
- W2223551652 hasConceptScore W2223551652C31972630 @default.
- W2223551652 hasConceptScore W2223551652C33923547 @default.
- W2223551652 hasConceptScore W2223551652C35861506 @default.
- W2223551652 hasConceptScore W2223551652C41008148 @default.
- W2223551652 hasConceptScore W2223551652C59822182 @default.
- W2223551652 hasConceptScore W2223551652C68537008 @default.
- W2223551652 hasConceptScore W2223551652C71924100 @default.
- W2223551652 hasConceptScore W2223551652C86803240 @default.
- W2223551652 hasConceptScore W2223551652C98045186 @default.
- W2223551652 hasLocation W22235516521 @default.
- W2223551652 hasOpenAccess W2223551652 @default.
- W2223551652 hasPrimaryLocation W22235516521 @default.
- W2223551652 hasRelatedWork W175726419 @default.
- W2223551652 hasRelatedWork W1832355761 @default.
- W2223551652 hasRelatedWork W1980343256 @default.
- W2223551652 hasRelatedWork W1980775837 @default.
- W2223551652 hasRelatedWork W2101386384 @default.
- W2223551652 hasRelatedWork W2112529397 @default.
- W2223551652 hasRelatedWork W2159881884 @default.
- W2223551652 hasRelatedWork W2179264821 @default.
- W2223551652 hasRelatedWork W2380157022 @default.
- W2223551652 hasRelatedWork W2896576772 @default.
- W2223551652 hasRelatedWork W2898031042 @default.
- W2223551652 hasRelatedWork W2905493506 @default.
- W2223551652 hasRelatedWork W3005560105 @default.
- W2223551652 hasRelatedWork W3035606294 @default.
- W2223551652 hasRelatedWork W3049583210 @default.
- W2223551652 hasRelatedWork W3123618337 @default.
- W2223551652 hasRelatedWork W3135153428 @default.
- W2223551652 hasRelatedWork W3208409104 @default.
- W2223551652 hasRelatedWork W3086221119 @default.
- W2223551652 hasRelatedWork W912342929 @default.
- W2223551652 isParatext "false" @default.
- W2223551652 isRetracted "false" @default.
- W2223551652 magId "2223551652" @default.
- W2223551652 workType "article" @default.