Higher order priors for joint intrinsic image, objects, and attributes estimation
Many methods have been proposed to recover the intrinsic scene properties such as shape, reflectance and illumination from a single image. However, most of these models have been applied on laboratory datasets. In this work we explore the synergy effects between intrinsic scene properties recovered...
| Main Authors: | , , |
|---|---|
| Format: | Conference item |
| Language: | English |
| Published: |
Curran Associates
2014
|
| _version_ | 1826314434204663808 |
|---|---|
| author | Vineet, V Rother, C Torr, PHS |
| author_facet | Vineet, V Rother, C Torr, PHS |
| author_sort | Vineet, V |
| collection | OXFORD |
| description | Many methods have been proposed to recover the intrinsic scene properties such as shape, reflectance and illumination from a single image. However, most of these models have been applied on laboratory datasets. In this work we explore the synergy effects between intrinsic scene properties recovered from an image, and the objects and attributes present in the scene. We cast the problem in a joint energy minimization framework; thus our model is able to encode the strong correlations between intrinsic properties (reflectance, shape, illumination), objects (table, tv-monitor), and materials (wooden, plastic) in a given scene. We tested our approach on the NYU and Pascal datasets, and observe both qualitative and quantitative improvements in the overall accuracy. |
| first_indexed | 2024-09-25T04:32:27Z |
| format | Conference item |
| id | oxford-uuid:c4cb7021-528a-4202-8399-9fa7ded1cc5f |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-09-25T04:32:27Z |
| publishDate | 2014 |
| publisher | Curran Associates |
| record_format | dspace |
| spelling | oxford-uuid:c4cb7021-528a-4202-8399-9fa7ded1cc5f2024-09-02T15:24:47ZHigher order priors for joint intrinsic image, objects, and attributes estimationConference itemhttp://purl.org/coar/resource_type/c_5794uuid:c4cb7021-528a-4202-8399-9fa7ded1cc5fEnglishSymplectic ElementsCurran Associates2014Vineet, VRother, CTorr, PHSMany methods have been proposed to recover the intrinsic scene properties such as shape, reflectance and illumination from a single image. However, most of these models have been applied on laboratory datasets. In this work we explore the synergy effects between intrinsic scene properties recovered from an image, and the objects and attributes present in the scene. We cast the problem in a joint energy minimization framework; thus our model is able to encode the strong correlations between intrinsic properties (reflectance, shape, illumination), objects (table, tv-monitor), and materials (wooden, plastic) in a given scene. We tested our approach on the NYU and Pascal datasets, and observe both qualitative and quantitative improvements in the overall accuracy. |
| spellingShingle | Vineet, V Rother, C Torr, PHS Higher order priors for joint intrinsic image, objects, and attributes estimation |
| title | Higher order priors for joint intrinsic image, objects, and attributes estimation |
| title_full | Higher order priors for joint intrinsic image, objects, and attributes estimation |
| title_fullStr | Higher order priors for joint intrinsic image, objects, and attributes estimation |
| title_full_unstemmed | Higher order priors for joint intrinsic image, objects, and attributes estimation |
| title_short | Higher order priors for joint intrinsic image, objects, and attributes estimation |
| title_sort | higher order priors for joint intrinsic image objects and attributes estimation |
| work_keys_str_mv | AT vineetv higherorderpriorsforjointintrinsicimageobjectsandattributesestimation AT rotherc higherorderpriorsforjointintrinsicimageobjectsandattributesestimation AT torrphs higherorderpriorsforjointintrinsicimageobjectsandattributesestimation |