一种单视图江豚三维模型重建方法  

A SINGLE-VIEW 3D MODEL RECONSTRUCTION METHOD FOR YANGTZE FINLESS PORPOISE

作　　者：黄志勇[1,2,3] 杨晨龙 石小涛[2,4] 华喜锋 涂法宪 丁妥君 佘雅丽 向梦丽 HUANG Zhi-Yong;YANG Chen-Long;SHI Xiao-Tao;HUA Xi-Feng;TU Fa-Xian;DING Tuo-Jun;SHE Ya-Li;XIANG Meng-Li(Key Laboratory of Intelligent Vision Monitoring for Hydroelectric Engineering,Hubei Provincial University,China Three Gorges University,Yichang 443002,China;International Science and Technology Cooperation Base for Fish Passage Technology in Hubei Province,China Three Gorges University,Yichang 443002,China;School of Computer and Information Science,China Three Gorges University,Yichang 443002,China;College of Hydraulic&Environmental Engineering,China Three Gorges University,Yichang 443002,China)

机构地区：[1]三峡大学湖北省水电工程智能视觉监测重点实验室,宜昌443002 [2]三峡大学湖北省鱼类过坝技术国际科技合作基地,宜昌443002 [3]三峡大学计算机与信息学院,宜昌443002 [4]三峡大学水利与环境学院,宜昌443002

出　　处：《水生生物学报》2025年第4期88-98,共11页Acta Hydrobiologica Sinica

基　　金：国家自然科学基金(52279069)资助。

摘　　要：在江豚三维重建领域,存在水下图像色偏失真、江豚数据集不足、获取江豚多视角图像困难等问题,而新兴方法尚未出现针对江豚的应用研究。为了解决这些难题,文章提出了一种结合扩散模型和神经辐射场的单视图江豚三维模型重建方法。首先,改进水下图像增强方法,有效地解决水下图像色偏失真的问题。其次,自制江豚多视角图像数据集,微调视角条件扩散模型,实现由单视图合成多视角图像,为单张图像重建江豚提供了新思路。最后,由神经辐射场进行重建,得到江豚三维模型。对江豚三维重建的结果使用平均倒角距离和法向量一致性进行了对比评估,平均倒角距离低于现有方法,法向量一致性高于现有方法,表明文章方法能够有效重建出符合江豚体色及形态的三维模型,合成新视角图像PSNR、SSIM、LPIPS值分别为38.968、0.972和0.294,效果优于现有方法,经过水下图像增强的重建结果的平均倒角距离值最低为0.428,法向量一致性最高达到0.882。In the field of 3D reconstruction of Yangtze finless porpoises,challenges such as underwater image color distortion,limited datasets,and difficulty in capturing multi-view images of Yangtze porpoises remain significant.Emerging methods have yet to address these issues specifically for Yangtze finless porpoises.To tackle these challenges,this paper proposes a novel single-view 3D reconstruction method for Yangtze finless porpoises,combining diffusion models and neural radiance fields.First,an improved underwater image enhancement technique is developed to effectively address the issue of underwater color distortion.Second,a custom multi-view image dataset of Yangtze finless porpoises is created to fine-tune a view-conditioned diffusion model,enabling the synthesis of multi-view images from a single view.This provides a new approach for reconstructing Yangtze finless porpoises from a single image.Finally,a neural radiance field is employed to reconstruct the 3D model of the porpoise.The reconstruction results were evaluated using the average chamfer distance(ACD)and normal consistency(NC).The proposed method achieved lower ACD and higher NC compared to existing methods,demonstrating its effectiveness in reconstructing 3D models that accurately capture the coloration and morphology of Yangtze finless porpoises.The synthesized multiview images achieved PSNR,SSIM,and LPIPS values of 38.968,0.972,and 0.294,respectively,surpassing the performance of existing methods.Additionally,the reconstruction results after underwater image enhancement yielded the lowest ACD of 0.428 and the highest NC of 0.882,further highlighting the superiority of the proposed approach.

关 键 词：扩散模型 新视角合成 神经辐射场 三维重建 长江江豚 

分 类 号：Q-334[生物学]