Neural Radiance Fields (NeRF) have been successfully applied in various aerial scenes, yet they face challenges with sparse views due to limited supervision. The acquisition of dense aerial views is often prohibitive, as unmanned aerial vehicles (UAVs) may encounter constraints in perspective range and energy constraints. In this work, we introduce Multiplane Prior guided NeRF (MPNeRF), a novel approach tailored for few-shot aerial scene rendering-marking a pioneering effort in this domain. Our key insight is that the intrinsic geometric regularities specific to aerial imagery could be leveraged to enhance NeRF in sparse aerial scenes. By investigating NeRF's and Multiplane Image (MPI)'s behavior, we propose to guide the training process of NeRF with a Multiplane Prior. The proposed Multiplane Prior draws upon MPI's benefits and incorporates advanced image comprehension through a SwinV2 Transformer, pre-trained via SimMIM. Our extensive experiments demonstrate that MPNeRF outperforms existing state-of-the-art methods applied in non-aerial contexts, by tripling the performance in SSIM and LPIPS even with three views available. We hope our work offers insights into the development of NeRF-based applications in aerial scenes with limited data.
This article presents a case study of the stability of the south anchorage of Taizhou Yangtze River Bridge in China. The gravity anchorage was embedded in soil and designed according to the current code of China. The code-based stability assessment is based on two-dimensional (2D) analyses under the assumption of plane strain conditions. Two typical failure modes of sliding and overturning are considered separately. The 2D plane strain model assumes the size of a structure in one dimension is significantly larger than the sizes in the other two dimensions. It is, thus, unsuitable for gravity anchorage because its sizes are similar in all three dimensions. Additionally, the effect of surrounding soil is ignored apart from the base friction in the anti-sliding stability assumption leading to the conservative design. Therefore, a three-dimensional model is more appropriate. Three-dimensional finite element model combined with strength reduction method is used to analyse the stability of anchorage. Reduced-scale model tests are used to calibrate the numerical model. The results show that the code-based design is indeed too conservative. The effects of stiffness and strength of the surrounding soil on the stability of anchorage are investigated through parametric studies to facilitate the economical design of gravity anchorage.
Existing diffusion-based video editing methods have achieved impressive results in motion editing. Most of the existing methods focus on the motion alignment between the edited video and the reference video. However, these methods do not constrain the background and object content of the video to remain unchanged, which makes it possible for users to generate unexpected videos. In this paper, we propose a one-shot video motion editing method called Edit-Your-Motion that requires only a single text-video pair for training. Specifically, we design the Detailed Prompt-Guided Learning Strategy (DPL) to decouple spatio-temporal features in space-time diffusion models. DPL separates learning object content and motion into two training stages. In the first training stage, we focus on learning the spatial features (the features of object content) and breaking down the temporal relationships in the video frames by shuffling them. We further propose Recurrent-Causal Attention (RC-Attn) to learn the consistent content features of the object from unordered video frames. In the second training stage, we restore the temporal relationship in video frames to learn the temporal feature (the features of the background and object's motion). We also adopt the Noise Constraint Loss to smooth out inter-frame differences. Finally, in the inference stage, we inject the content features of the source object into the editing branch through a two-branch structure (editing branch and reconstruction branch). With Edit-Your-Motion, users can edit the motion of objects in the source video to generate more exciting and diverse videos. Comprehensive qualitative experiments, quantitative experiments and user preference studies demonstrate that Edit-Your-Motion performs better than other methods.
After a general disease checking and safety evaluation of the bridge, it summarizes the typical disease which appears after a bridge’s long-term operation, analyses the reason of producing disease and discusses the reinforce methods, finally it contraposingly summarizes the problems which should be adverted in the course of bridge protection.
Abstract In the process of urban transportation construction, it is inevitable that the new bridges will be adjacent to the existing tunnels. According to the spatial relationship between the new bridge and the existing tunnel, a three-dimension finite differential model of the pile-tunnel interaction is established by a numerical simulation method. The influence of the upper load of the new bridge on the adjacent tunnel is simulated, with the results of the numerical simulation method and the Boussinesq method are compared. It is found that the results of numerical simulation are verified by the Boussinesq method, with the deviation less than 10%. Moreover, the horizontal deformation of the tunnel is central-symmetrically distributed, and the symmetrical point of the horizontal deformation and the position of maximum vertical deformation are both near the midpoint of the two cushion caps. Besides, the deformation of the tunnel is mainly vertical. Last but not least, the influence of the construction and operation of the pile foundation of the bridge on the rails in the existing tunnel meets the control criteria. Therefore, the methods of analysis and parameters in this paper can provide a reference for similar projects.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
