Efficient Reflectance Capture with a Deep Gated Mixture-of-Experts
We present a novel framework to efficiently acquire near-planar anisotropic reflectance in a pixel-independent fashion, using a deep gated mixtureof-experts. While existing work employs a unified network to handle all possible input, our network automatically learns to condition on the input for enhanced reconstruction. We train a gating module to select one out of a number of specialized decoders for reflectance reconstruction, based on photometric measurements, essentially trading generality for quality. A common, pre-trained latent transform module is also appended to each decoder, to offset the burden of the increased number of decoders. In addition, the illumination conditions during acquisition can be jointly optimized. The effectiveness of our framework is validated on a wide variety of challenging samples using a near-field lightstage. Compared with the state-of-the-art technique, our results are improved at the same input bandwidth, and our bandwidth can be reduced to about 1/3 for equal-quality results.
Code (0)
등록된 구현이 없습니다.
Tasks
DecoderMixture-of-ExpertsSimilar Papers 제목 키워드 기반
Spatial Mixture-of-Experts
Many data have an underlying dependence on spatial location; it may be weather on the Earth, a simulation on a mesh, or a registered image. Yet this feature is rarely taken advantage of, and violates common assumptions m…
Mixture-of-ExpertsHorseshoe Mixtures-of-Experts (HS-MoE)
Horseshoe mixtures-of-experts (HS-MoE) models provide a Bayesian framework for sparse expert selection in mixture-of-experts architectures. We combine the horseshoe prior's adaptive global-local shrinkage with input-depe…
Gaussian Process-Gated Hierarchical Mixtures of Experts
In this paper, we propose novel Gaussian process-gated hierarchical mixtures of experts (GPHMEs). Unlike other mixtures of experts with gating models linear in the input, our model employs gating functions built with Gau…
Gaussian ProcessesVariational InferenceGM-MoE: Low-Light Enhancement with Gated-Mechanism Mixture-of-Experts
Low-light enhancement has wide applications in autonomous driving, 3D reconstruction, remote sensing, surveillance, and so on, which can significantly improve information utilization. However, most existing methods lack …
3D ReconstructionAutonomous DrivingImage EnhancementLow-Light Image Enhancement+2IntrinSeqNet: Learning to Estimate the Reflectance from Varying Illumination
Intrinsic image decomposition describes an image based on its reflectance and shading components. In this paper we tackle the problem of estimating the diffuse reflectance from a sequence of images captured from a fixed …
Intrinsic Image Decomposition