2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) · 2023 · 13 citations · 24 references
ComputingComputer ScienceComputer VisionMachine LearningMachine Vision3D ReconstructionData CompressionDeep LearningImage CompressionImage ReconstructionNeural NetworksArchitecture SearchCanonical QuantizationNetwork CapacityNetwork WeightNeural Architecture SearchNeural Network QuantizationNon-uniform QuantizationQuantization
The role of quantization within implicit/coordinate neural networks is still not fully understood. We note that using a canonical fixed quantization scheme during training produces poor performance at low bit-rates due to the network weight distributions changing over the course of training. In this work, we show that a non-uniform quantization of neural weights can lead to significant improvements. Specifically, we demonstrate that a clustered quantization enables improved reconstruction. Finally, by characterising a trade-off between quantization and network capacity, we demonstrate that it is possible (while memory inefficient) to reconstruct signals using binary neural networks. We demonstrate our findings experimentally on 2D image reconstruction and 3D radiance fields; and show that simple quantization methods and architecture search can achieve compression of NeRF to less than 16kb with minimal loss in performance (323x smaller than the original NeRF).
24
Image quality assessment: from error visibility to structural similarity
Zhou Wang, Alan C. Bovik, Hamid R. Sheikh et al. · IEEE Transactions on Image Processing · 2004 · 56K citations
Advances in neural information processing systems 7
Computers & Mathematics with Applications · 1996 · 14.4K citations
The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
Richard Zhang, Phillip Isola, Alexei A. Efros et al. · 2018 · 12.4K citations
Computer vision: algorithms and applications
Choice Reviews Online · 2011 · 4K citations