paper-with-me

홈 › Papers

Efficient Reflectance Capture with a Deep Gated Mixture-of-Experts

2022-03-29 · Xiaohe Ma, Yaxin Yu, Hongzhi Wu, Kun Zhou

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.

📄 PDF Abstract BibTeX arXiv:2203.15258

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderMixture-of-Experts

Similar Papers 제목 키워드 기반

Spatial Mixture-of-Experts

2022-11-24 · Nikoli Dryden, Torsten Hoefler

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-Experts

Horseshoe Mixtures-of-Experts (HS-MoE)

2026-01-14 · Nick Polson, Vadim Sokolov arxiv

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

2023-02-09 · Yuhao Liu, Marzieh Ajirak, Petar Djuric

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 Inference

GM-MoE: Low-Light Enhancement with Gated-Mechanism Mixture-of-Experts

2025-03-10 · Minwen Liao, Hao Bo Dong, Xinyi Wang, Ziyang Yan 외

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+2

IntrinSeqNet: Learning to Estimate the Reflectance from Varying Illumination

2019-06-13 · Grégoire Nieto, Mohammad Rouhani, Philippe Robert

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