Three-dimensional scene reconstruction from a set of two-dimensional images remains a significant and challenging research task in computer vision. Existing algorithms struggle to effectively model the relationships between images captured at different times, resulting in poor rendering quality for large-scale environments. To address this challenge, this paper proposes a neural surfels fusion splatting algorithm for real-time scene reconstruction. The algorithm progressively builds and updates scene models from streaming input data, incorporating neural surfel representations based on 2D Gaussian primitives and a fusion mechanism based on Gated Recurrent Units (GRU). First, the algorithm achieves perspective-correct rendering by integrating Gaussian surfel splatting into the rendering pipeline and employing explicit ray-splat intersections, thereby enhancing depth consistency and geometric fidelity across multiple viewpoints. Then, to further improve the quality of reconstructed surfaces, the method combines depth pulling and normal consistency regularization, promoting smoother surface reconstruction and facilitating high-quality mesh extraction. The algorithm's performance was evaluated on two large-scale indoor/outdoor scene reconstruction datasets: DeepBlending and Tanks&Temples. Extensive experimental results demonstrate that the algorithm outperforms existing methods in both quantitative and qualitative assessments.
ChengJ, ZhangL Y, ChenQ H, et al. A review of visual SLAM methods for autonomous driving vehicles[J]. Engineering Applications of Artificial Intelligence, 2022, 114: 104992.
[2]
KazerouniI A, FitzgeraldL, DoolyG, et al. A survey of state-of-the-art on visual SLAM[J]. Expert Systems with Applications, 2022, 205: 117734.
[3]
LeeT J, KimC H, ChoD D. A monocular vision sensor-based efficient SLAM method for indoor service robots[J]. IEEE Transactions on Industrial Electronics, 2018, 66(1): 318-328.
[4]
WeiY, LiuS H, RaoY M, et al. Nerfingmvs: Guided optimization of neural radiance fields for indoor multi-view stereo[C]∥Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021: 5610-5619.
[5]
ChenZ, WangC, GuoY C, et al. Structnerf: Neural radiance fields for indoor scenes with structural hints[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(12): 15694-15705.
[6]
LiuJ L, NieQ, LiuY, et al. Nerf-loc: Visual localization with conditional neural radiance field[C]∥IEEE International Conference on Robotics and Automation(ICRA), London, United Kingdom, 2023: 9385-9392.
[7]
KerblB, KopanasG, LeimkühlerT, et al. 3D gaussian splatting for real-time radiance field rendering[J]. ACM Trans. Graph., 2023, 42(4): 139:1-14.
[8]
StierN, RanjanA, ColburnA, et al. Finerecon: Depth-aware feed-forward network for detailed 3d reconstruction[C]∥Proceedings of the IEEE/CVF International Conference on Computer Vision, Paris, France, 2023: 18377-18386.
[9]
WeiW F, WangJ, XieX, et al. Real-time dense visual slam with neural factor representation[J]. Electronics, 2024, 13(16): 3332.
[10]
TretschkE, KairandaN, BrM, et al. State of the art in dense monocular non‐rigid 3D reconstruction[J]. Computer Graphics Forum, 2023, 42(2): 485-520.
[11]
HedmanP, PhilipJ, PriceT, et al. Deep blending for free-viewpoint image-based rendering[J]. ACM Transactions on Graphics, 2018, 37(6): 1-15.
[12]
KnapitschA, ParkJ, ZhouQ Y, et al. Tanks and temples: benchmarking large-scale scene reconstruction[J]. ACM Transactions on Graphics, 2017, 36(4): 1-13.
[13]
GuédonA, LepetitV. Sugar: Surface-aligned gaussian splatting for efficient 3d mesh reconstruction and high-quality mesh rendering[C]∥Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA, 2024: 5354-5363.
[14]
WangP, LiuL, LiuY, et al. Neus: learning neural implicit surfaces by volume rendering for multi-view reconstruction[J]. arXiv preprint arXiv:2021.
[15]
ZhangR, IsolaP, EfrosA A, et al. The unreasonable effectiveness of deep features as a perceptual metric[C]∥Proceedings of the IEEE conference on computer vision and pattern recognition, Salt Lake City, UT, USA, 2018: 586-595.