Neural radiance fields (NeRF) appeared recently as a powerful tool to generate realistic views of objects and confined areas. Still, they face serious challenges with open scenes, where the camera has unrestricted movement and content can appear at any distance. In such scenarios, current NeRF-inspired models frequently yield hazy or pixelated outputs, suffer slow training times, and might display irregularities, because of the challenging task of reconstructing an extensive scene from a limited number of images. We propose a new framework to boost the performance of NeRF-based architectures yielding significantly superior outcomes compared to the prior work. Our solution overcomes several obstacles that plagued earlier versions of NeRF, including handling multiple video inputs, selecting keyframes, and extracting poses from real-world frames that are ambiguous and symmetrical. Furthermore, we applied our framework, dubbed as \"Pre-NeRF 360\", to enable the use of the Nutrition5k dataset
Seminari «CVUB Seminar: Machine Learning Applications in Genomics»
Seminari
Data:
24/03/23
Horari:
15:00h
Lloc:
Hybrid (Teams / IMUB)
A càrrec de:
Petia Radeva
Organització:
Computer Vision and Machine Learning Group
Observacions:
This seminar will provide an overview of the field of genomics and the different data modalities that are commonly used, such as scRNA-seq and spatial transcriptomics. We will also cover traditional stat and ML techniques that are commonly used in the analysis of genomic data, including multiple hypothesis correction and dimensionality reduction. In addition, we will present a newly developed method to perform in silico cell sex deconvolution from single-cell data based on a generative model. This method will allow researchers to accurately identify the sex of individual cells, which is important for many applications in genomics research. Sex deconvolution is particularly important in cases where multiple samples have to be pooled together, as sex can be a confounding variable during analysis. Overall, this seminar will provide a brief overview of SoTA techniques and methods used in the analysis of genomic data, and their potential to further our understanding of biological systems.
La web de la Facultat de Matemàtiques i Informàtica utilitza "cookies" per millorar l'experiència de navegació. Si segueixes navegant entendrem que ho acceptes.D'acordMés informació
