Search for: All records

High-quality large-scale scene rendering requires a scalable representation and accurate camera poses. This research combines tile-based hybrid neural fields with parallel distributive optimization to improve bundle-adjusting neural radiance fields. The proposed method scales with a divide-and-conquer strategy. We partition scenes into tiles, each with a multi-resolution hash feature grid and shallow chained diffuse and specular multilayer perceptrons (MLPs). Tiles unify foreground and background via a spatial contraction function that allows both distant objects in outdoor scenes and planar reflections as virtual images outside the tile. Decomposing appearance with the specular MLP allows a specular-aware warping loss to provide a second optimization path for camera poses. We apply the alternating direction method of multipliers (ADMM) to achieve consensus among camera poses while maintaining parallel tile optimization. Experimental results show that our method outperforms state-of-the-art neural scene rendering method quality by 5%--10% in PSNR, maintaining sharp distant objects and view-dependent reflections across six indoor and outdoor scenes.

 

The application of compressed sensing (CS)-enabled data reconstruction for accelerating magnetic resonance imaging (MRI) remains a challenging problem. This is due to the fact that the information lost in k-space from the acceleration mask makes it difficult to reconstruct an image similar to the quality of a fully sampled image. Multiple deep learning-based structures have been proposed for MRI reconstruction using CS, in both the k-space and image domains, and using unrolled optimization methods. However, the drawback of these structures is that they are not fully utilizing the information from both domains (k-space and image). Herein, we propose a deep learning-based attention hybrid variational network that performs learning in both the k-space and image domains. We evaluate our method on a well-known open-source MRI dataset (652 brain cases and 1172 knee cases) and a clinical MRI dataset of 243 patients diagnosed with strokes from our institution to demonstrate the performance of our network. Our model achieves an overall peak signal-to-noise ratio/structural similarity of 40.92 ± 0.29/0.9577 ± 0.0025 (fourfold) and 37.03 ± 0.25/0.9365 ± 0.0029 (eightfold) for the brain dataset, 31.09 ± 0.25/0.6901 ± 0.0094 (fourfold) and 29.49 ± 0.22/0.6197 ± 0.0106 (eightfold) for the knee dataset, and 36.32 ± 0.16/0.9199 ± 0.0029 (20-fold) and 33.70 ± 0.15/0.8882 ± 0.0035 (30-fold) for the stroke dataset. In addition to quantitative evaluation, we undertook a blinded comparison of image quality across networks performed by a subspecialty trained radiologist. Overall, we demonstrate that our network achieves a superior performance among others under multiple reconstruction tasks.

 

With the requirements to enable data analytics and exploration interactively and efficiently, progressive data processing, especially progressive join, became essential to data science. Join queries are particularly challenging due to the correlation between input datasets which causes the results to be biased towards some join keys. Existing methods carefully control which parts of the input to process in order to improve the quality of progressive results. If the quality is not satisfactory, they will process more data to improve the result. In this paper, we propose an alternative approach that initially seems counter-intuitive but surprisingly works very well. After query processing, we intentionally report fewer results to the user with the goal of improving the quality. The key idea is that if the output is deviated from the correct distribution, we temporarily hide some results to correct the bias. As we process more data, the hidden results are inserted back until the full dataset is processed. The main challenge is that we do not know the correct output distribution while the progressive query is running. In this work, we formally define the progressive join problem with quality and progressive result rate constraints. We propose an input&output quality-aware progressive join framework (QPJ) that (1) provides input control that decides which parts of the input to process; (2) estimates the final result distribution progressively; (3) automatically controls the quality of the progressive output rate; and (4) combines input&output control to enable quality control of the progressive results. We compare QPJ with existing methods and show QPJ can provide the progressive output that can represent the final answer better than existing methods. 

Abstract. Nutrient budgets help to identify the excess or insufficient use of fertilizers and other nutrient sources in agriculture. They allow for the calculation of indicators, such as the nutrient balance (surplus if positive or deficit if negative) and nutrient use efficiency, that help to monitor agricultural productivity and sustainability across the world. We present a global database of country-level budget estimates for nitrogen (N), phosphorus (P) and potassium (K) on cropland. The database, disseminated in FAOSTAT, is meant to provide a global reference, synthesizing and continuously updating the state of the art on this topic. The database covers 205 countries and territories, as well as regional and global aggregates, for the period from 1961 to 2020. Results highlight the wide range in nutrient use and nutrient use efficiencies across geographic regions, nutrients, and time. The average N balance on global cropland has remained fairly steady at about 50–55 kg ha−1 yr−1 during the past 15 years, despite increasing N inputs. Regional trends, however, show recent average N surpluses that range from a low of about 10 kg N ha−1 yr−1 in Africa to more than 90 kg N ha−1 yr−1 in Asia. Encouragingly, average global cropland N use efficiency decreased from about 59 % in 1961 to a low of 43 % in 1988, but it has risen since then to a level of 55 %. Phosphorus deficits are mainly found in Africa, whereas potassium deficits occur in Africa and the Americas. This study introduces improvements over previous work in relation to the key nutrient coefficients affecting nutrient budgets and nutrient use efficiency estimates, especially with respect to nutrient removal in crop products, manure nutrient content, atmospheric deposition and crop biological N fixation rates. We conclude by discussing future research directions and highlighting the need to align statistical definitions across research groups as well as to further refine plant and livestock coefficients and expand estimates to all agricultural land, including nutrient flows in meadows and pastures. Further information is available from https://doi.org/10.5061/dryad.hx3ffbgkh (Ludemann et al., 2023b) as well as the FAOSTAT database (https://www.fao.org/faostat/en/#data/ESB; FAO, 2022a) and is updated annually.