Real-Time Adaptive Color Correction in Dynamic Projection Mapping

Kurth, Philipp; Lange, Vanessa; Stamminger, Marc; Bauer, Frank

doi:10.1109/ismar50242.2020.00039

Cited by 6 publications

(1 citation statement)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Expanding on established geometric compensation, addressing photometric compensation becomes feasible. Certain methods [12][13][14] compensate for projecting onto textured surfaces by deriving a discrete response function from corresponding pixels in projector and camera images. For photometric compensation on textured Lambertian surfaces [15,16], a linear formula computes the compensation image.…”

Section: Introductionmentioning

confidence: 99%

IDNet: An Inception-like Deformable Non-local Network forProjection Compensation over Non-Flat Textured Surfaces

Zhang,

Yang,

Han

et al. 2023

Preprint

View full text Add to dashboard Cite

Projector compensation on non- at textured surfaces is a challenging task. Existing methods struggleto correct significant distortions. Our approach, IDNet, overcomes these limitations with incorporatingthree Inception-like modules, by which we capture multiscale features using deformable convolutionand non-local attention mechanisms. Specically, we employ multiscale deformable convolutions forgeometric distortions and an Inception-like module for photometric compensation. The addition ofa residual-based non-local attention module further enhances both processes. Experimental results show that IDNet performs as the state-of-the-art comparing with the existing methods.

show abstract