Three-dimensional Reconstruction has drawn much attention in computer vision. Generating a dense point cloud from a single image is a more challenging task. However, generating dense point clouds directly costs expensively in calculation and memory and may cause the network hard to train. In this work, we propose a two-stage training dense point cloud generation network. We first train our attention-based sparse point cloud generation network to generate a sparse point cloud from a single image. Then we train our dense point cloud generation network to densify the generated sparse point cloud. After combining the two stages and finetuning, we obtain an end-to-end network that generates a dense point cloud from a single image. Through evaluation of both synthetic and real-world datasets, we demonstrate that our approach outperforms state of the art works in dense point cloud generation.
Succinate
dehydrogenase (SDH) inhibitor is one of the research
hotspots for the development of fungicides. Herein, we describe the
design and synthesis of N-methoxy-(biphenyl-ethyl)-pyrazole-carboxamide
derivatives with enhanced fungicidal activity by employing fragment
combination strategy. The SDH enzymatic activity was evaluated for
24 title compounds, and compound 7s was identified as
the highest activity against porcine SDH with an IC50 value
of 0.014 μM, 205-fold greater than that of fluxapyroxad. Furthermore,
the greenhouse experiments showed that compound 7u exhibited
potent fungicidal activity against wheat powdery mildew with an EC50 value of 0.633 mg/L, higher activity than fluxapyroxad and
benzovindiflupyr. The computational results showed that the fluorine
atom substituted on the pyrazole ring formed an extra dipolar–dipolar
interaction with C_S42 and then increased the van der Waals interaction
between the compound and SDH. The structural and mechanistic insights
obtained from the present work will provide a valuable clue to developing
novel SDH inhibitors.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.