Colonoscopy reconstruction is pivotal for diagnosing colorectal cancer. However, accurate long-sequence colonoscopy reconstruction faces three major challenges (1) dissimilarity among segments of the colon due to its meandering and convoluted shape; (2) co-existence of simple and intricately folded geometry structures; (3) sparse viewpoints due to constrained camera trajectories. To tackle these challenges, we introduce a new reconstruction framework based on neural radiance field (NeRF), named ColonNeRF, which leverages neural rendering for novel view synthesis of long-sequence colonoscopy. Specifically, to reconstruct the entire colon in a piecewise manner, our ColonNeRF introduces a region division and integration module, effectively reducing shape dissimilarity and ensuring geometric consistency in each segment. To learn both the simple and complex geometry in a unified framework, our ColonNeRF incorporates a multi-level fusion module that progressively models the colon regions from easy to hard. Additionally, to overcome the challenges from sparse views, we devise a DensiNet module for densifying camera poses under the guidance of semantic consistency. We conduct extensive experiments on both synthetic and real-world datasets to evaluate our ColonNeRF. Quantitatively, our ColonNeRF outperforms existing methods on two benchmarks over four evaluation metrics. Notably, our LPIPS-ALEX scores exhibit a substantial increase of about 67%-85% on the SimCol-to-3D dataset. Qualitatively, our reconstruction visualizations show much clearer textures and more accurate geometric details. These sufficiently demonstrate our superior performance over the state-of-the-art methods.

To replicate the success of text-to-image (T2I) generation, recent works employ large-scale video datasets to train a text-to-video (T2V) generator. Despite their promising results, such paradigm is computationally expensive. In this work, we propose a new T2V generation setting—One-Shot Video Tuning, where only one text-video pair is presented. Our model is built on state-of-the-art T2I diffusion models pre-trained on massive image data. We make two key observations (1) T2I models can generate still images that represent verb terms; (2) extending T2I models to generate multiple images concurrently exhibits surprisingly good content consistency. To further learn continuous motion, we introduce Tune-A-Video, which involves a tailored spatio-temporal attention mechanism and an efficient one-shot tuning strategy. At inference, we employ DDIM inversion to provide structure guidance for sampling. Extensive qualitative and numerical experiments demonstrate the remarkable ability of our method across various applications.

With the development of society, carbon emissions are increasing. The key organisms to maintain the stability of the carbon cycle are fungi that can be easily seen and ignored. In this paper, we selected several fungi to establish the model of decomposition and reproduction so that we can understand the role they played. First of all, we studied several physiological indexes of fungi, and established the degradation model through multiple regression analysis, and multiple linear regression equation for the relationship between decomposition rate, growth rate, unit volume density of mycelium, temperature and humidity tolerance. Next, we established the competitive growth model based on logistic model, simulated the competitive growth process of strains with different growth rates, humidity tolerance, and the total decomposition rate. In order to be closer to the real situation, we set up the competitive growth model among four species. By arranging fungal communities randomly to simulate different biodiversity, we analyzed the effects on the decomposition rate in the case of that the environmental temperature and humidity changed by 10% respectively. After that, we established a growth prediction model based on ARIMA. By querying the climate data of five typical climates, we established the competitive growth model with 4 combinations, and we obtained a short-term model, a medium-term trend and a longtern forecast to describe growth, reproduction and decomposition rate. In order to refine the strains of the pressure of competition and the influence of the distance between the strains of competition, we have established improved competition evolution model based on the cellular automata theory of population. The model helped us comprehend the competition between species on a micro level. All these analyses showed us the significance of biodiversity and the great role decomposers play in Earth.