针对单个物体深度范围更小的特点，自适应调整深度采样以提升三维重建精度。
IA-MVS: Instance-Focused Adaptive Depth Sampling for Multi-View Stereo
- 按每个物体实例自适应缩小深度假设范围，聚焦精细估计。
- 引入实例内深度连续性过滤机制，减少错误累积，提升鲁棒性。
- 设计基于条件概率的置信度评估模型，适用于MVSNet类框架。
基于渐进式深度假设缩小的多视图立体（MVS）模型已取得显著进展。然而，现有方法未充分利用单个物体的深度覆盖范围小于整个场景这一特性，限制了深度估计精度的进一步提升。此外，初始阶段的误差会随过程积累。本文提出实例自适应多视图立体（IA-MVS），通过缩小深度假设范围并针对每个实例进行精细化处理，提升深度估计精度。同时，引入基于实例内深度连续性先验的过滤机制，增强鲁棒性。针对现有置信度估计在点云上可能降低IA-MVS性能的问题，我们构建了基于条件概率的详细数学模型。该方法可广泛应用于基于MVSNet的模型，无需额外训练开销。在DTU基准测试中达到当前最优表现。代码已开源：https://github.com/KevinWang73106/IA-MVS。
原文摘要 · Abstract (English)
Multi-view stereo (MVS) models based on progressive depth hypothesis narrowing have made remarkable advancements. However, existing methods haven't fully utilized the potential that the depth coverage of individual instances is smaller than that of the entire scene, which restricts further improvements in depth estimation precision. Moreover, inevitable deviations in the initial stage accumulate as the process advances. In this paper, we propose Instance-Adaptive MVS (IA-MVS). It enhances the precision of depth estimation by narrowing the depth hypothesis range and conducting refinement on each instance. Additionally, a filtering mechanism based on intra-instance depth continuity priors is incorporated to boost robustness. Furthermore, recognizing that existing confidence estimation can degrade IA-MVS performance on point clouds. We have developed a detailed mathematical model for confidence estimation based on conditional probability. The proposed method can be widely applied in models based on MVSNet without imposing extra training burdens. Our method achieves state-of-the-art performance on the DTU benchmark. The source code is available at https://github.com/KevinWang73106/IA-MVS.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。