High Dynamic Range (HDR) imaging with modulo cam-eras involves solving a challenging inverse problem, where degradation occurs due to the modulo operation applied to the target HDR …

Zhao et al. [58] used a modulo camera that is able to wrap the high radiance of dynamic range scene pe-riodically and save modulo information, then used Markov Random Field to unwrap …

To this aim we designed a CNN structure inspired from demosaicing algorithms and directed at classifying image blocks by their position in the image modulo (2 x 2).

Without additional illumination modules, passive 3D imaging systems exploit unconven-tional sensors for HDR imaging, such as single-photon avalanche diodes [17], quanta image sensors …

Mod-Squad: Designing Mixtures of Experts As Modular Multi-Task Learners Zitian Chen1, Yikang Shen2, Mingyu Ding3, Zhenfang Chen2, Hengshuang Zhao3, Erik Learned-Miller1, Chuang …

Positional learning trains the model to learn the modulo-2 position of pixels, leveraging the translation-invariance of CNN to replicate the underlying mosaic and its potential inconsistencies.

Abstract In late fusion, each modality is processed in a separate unimodal Convolutional Neural Network (CNN) stream and the scores of each modality are fused at the end. Due to its …

Consequently, the original phase image, which exhibits strong smoothness, is degraded to a wrapped version with both incorrect values and artificial discontinuities induced by the modulo …

Complete methods such as Satisfiabil-ity Modulo Theory (SMT) [8, 15, 20] or Mixed-Integer Pro-gramming (MIP) [5, 9, 35] provide exact robustness bounds but are expensive to implement.

At several stages in the Winograd transformations, modulo operations are used, requiring dedicated hardware. For an 8-bit Winograd-based convolution in the residue number system, …