论文标题
BNV融合：使用双级神经体积融合的密集3D重建
BNV-Fusion: Dense 3D Reconstruction using Bi-level Neural Volume Fusion
论文作者
论文摘要
深度图像流的密集3D重建是许多混合现实和机器人应用的关键。尽管这些年来，基于截短的签名距离函数（TSDF）融合的方法已经提高了该领域，但TSDF体积表示形式面临着在稳定性到噪声测量和维持细节水平之间达到平衡的面临。我们提出了双层神经体积融合（BNV融合），该融合利用了神经隐式表示和神经渲染的最新进展，用于致密3D重建。为了将新的深度图逐步整合到全球神经隐式表示中，我们提出了一种新型的双层融合策略，该策略既考虑效率和重建质量，逐渐设计。我们在定量和定性上评估了多个数据集上提出的方法，证明了对现有方法的显着改善。
Dense 3D reconstruction from a stream of depth images is the key to many mixed reality and robotic applications. Although methods based on Truncated Signed Distance Function (TSDF) Fusion have advanced the field over the years, the TSDF volume representation is confronted with striking a balance between the robustness to noisy measurements and maintaining the level of detail. We present Bi-level Neural Volume Fusion (BNV-Fusion), which leverages recent advances in neural implicit representations and neural rendering for dense 3D reconstruction. In order to incrementally integrate new depth maps into a global neural implicit representation, we propose a novel bi-level fusion strategy that considers both efficiency and reconstruction quality by design. We evaluate the proposed method on multiple datasets quantitatively and qualitatively, demonstrating a significant improvement over existing methods.
