Traditional neural radiance fields for rendering novel views require intensive input images and pre-scene optimization,which limits their practical applications.We propose a generalization method to infer scenes from ...Traditional neural radiance fields for rendering novel views require intensive input images and pre-scene optimization,which limits their practical applications.We propose a generalization method to infer scenes from input images and perform high-quality rendering without pre-scene optimization named SG-NeRF(Sparse-Input Generalized Neural Radiance Fields).Firstly,we construct an improved multi-view stereo structure based on the convolutional attention and multi-level fusion mechanism to obtain the geometric features and appearance features of the scene from the sparse input images,and then these features are aggregated by multi-head attention as the input of the neural radiance fields.This strategy of utilizing neural radiance fields to decode scene features instead of mapping positions and orientations enables our method to perform cross-scene training as well as inference,thus enabling neural radiance fields to generalize for novel view synthesis on unseen scenes.We tested the generalization ability on DTU dataset,and our PSNR(peak signal-to-noise ratio)improved by 3.14 compared with the baseline method under the same input conditions.In addition,if the scene has dense input views available,the average PSNR can be improved by 1.04 through further refinement training in a short time,and a higher quality rendering effect can be obtained.展开更多
Research on neural radiance fields for novel view synthesis has experienced explosive growth with the development of new models and extensions.The NeRF(Neural Radiance Fields)algorithm,suitable for underwater scenes o...Research on neural radiance fields for novel view synthesis has experienced explosive growth with the development of new models and extensions.The NeRF(Neural Radiance Fields)algorithm,suitable for underwater scenes or scattering media,is also evolving.Existing underwater 3D reconstruction systems still face challenges such as long training times and low rendering efficiency.This paper proposes an improved underwater 3D reconstruction system to achieve rapid and high-quality 3D reconstruction.First,we enhance underwater videos captured by a monocular camera to correct the image quality degradation caused by the physical properties of the water medium and ensure consistency in enhancement across frames.Then,we perform keyframe selection to optimize resource usage and reduce the impact of dynamic objects on the reconstruction results.After pose estimation using COLMAP,the selected keyframes undergo 3D reconstruction using neural radiance fields(NeRF)based on multi-resolution hash encoding for model construction and rendering.In terms of image enhancement,our method has been optimized in certain scenarios,demonstrating effectiveness in image enhancement and better continuity between consecutive frames of the same data.In terms of 3D reconstruction,our method achieved a peak signal-to-noise ratio(PSNR)of 18.40 dB and a structural similarity(SSIM)of 0.6677,indicating a good balance between operational efficiency and reconstruction quality.展开更多
基金supported by the Zhengzhou Collaborative Innovation Major Project under Grant No.20XTZX06013the Henan Provincial Key Scientific Research Project of China under Grant No.22A520042。
文摘Traditional neural radiance fields for rendering novel views require intensive input images and pre-scene optimization,which limits their practical applications.We propose a generalization method to infer scenes from input images and perform high-quality rendering without pre-scene optimization named SG-NeRF(Sparse-Input Generalized Neural Radiance Fields).Firstly,we construct an improved multi-view stereo structure based on the convolutional attention and multi-level fusion mechanism to obtain the geometric features and appearance features of the scene from the sparse input images,and then these features are aggregated by multi-head attention as the input of the neural radiance fields.This strategy of utilizing neural radiance fields to decode scene features instead of mapping positions and orientations enables our method to perform cross-scene training as well as inference,thus enabling neural radiance fields to generalize for novel view synthesis on unseen scenes.We tested the generalization ability on DTU dataset,and our PSNR(peak signal-to-noise ratio)improved by 3.14 compared with the baseline method under the same input conditions.In addition,if the scene has dense input views available,the average PSNR can be improved by 1.04 through further refinement training in a short time,and a higher quality rendering effect can be obtained.
基金This work was supported by the Key Research and Development Program of Hainan Province(Grant Nos.ZDYF2023GXJS163,ZDYF2024GXJS014)National Natural Science Foundation of China(NSFC)(Grant Nos.62162022,62162024)+2 种基金the Major Science and Technology Project of Hainan Province(Grant No.ZDKJ2020012)Hainan Provincial Natural Science Foundation of China(Grant No.620MS021)Youth Foundation Project of Hainan Natural Science Foundation(621QN211).
文摘Research on neural radiance fields for novel view synthesis has experienced explosive growth with the development of new models and extensions.The NeRF(Neural Radiance Fields)algorithm,suitable for underwater scenes or scattering media,is also evolving.Existing underwater 3D reconstruction systems still face challenges such as long training times and low rendering efficiency.This paper proposes an improved underwater 3D reconstruction system to achieve rapid and high-quality 3D reconstruction.First,we enhance underwater videos captured by a monocular camera to correct the image quality degradation caused by the physical properties of the water medium and ensure consistency in enhancement across frames.Then,we perform keyframe selection to optimize resource usage and reduce the impact of dynamic objects on the reconstruction results.After pose estimation using COLMAP,the selected keyframes undergo 3D reconstruction using neural radiance fields(NeRF)based on multi-resolution hash encoding for model construction and rendering.In terms of image enhancement,our method has been optimized in certain scenarios,demonstrating effectiveness in image enhancement and better continuity between consecutive frames of the same data.In terms of 3D reconstruction,our method achieved a peak signal-to-noise ratio(PSNR)of 18.40 dB and a structural similarity(SSIM)of 0.6677,indicating a good balance between operational efficiency and reconstruction quality.