FastPCI通过结构引导的运动估计，实现点云帧插值的高速高精度。
FastPCI: Motion-Structure Guided Fast Point Cloud Frame Interpolation
- 融合卷积与Transformer的金字塔架构，增强局部与长程特征学习。
- 在KITTI上使Chamfer Distance降低26.6%，速度比SOTA快10倍以上。
- 适合需要实时点云重建的自动驾驶与3D视觉任务。
点云帧插值是一项挑战性任务，涉及跨帧的精确场景流估计并保持几何结构。现有方法通常依赖预训练运动估计算器或测试时的密集优化，导致插值精度下降或推理时间过长。本文提出FastPCI，采用金字塔卷积-变压器架构进行点云帧插值。该混合架构提升了局部与长距离特征学习能力，金字塔网络提供多尺度特征并减少计算量。此外，FastPCI设计了独特的双向运动-结构模块，以更准确地估计场景流。其设计基于两点：（1）精确的场景流能保持3D结构；（2）前一时刻的点云应可通过未来时刻的逆向运动重构。大量实验表明，FastPCI显著优于当前最优方法PointINet和NeuralPCI，KITTI数据集上Chamfer Distance分别降低26.6%和18.3%，且推理速度分别提升10倍以上和600倍以上。代码已开源于https://github.com/genuszty/FastPCI。
原文摘要 · Abstract (English)
Point cloud frame interpolation is a challenging task that involves accurate scene flow estimation across frames and maintaining the geometry structure. Prevailing techniques often rely on pre-trained motion estimators or intensive testing-time optimization, resulting in compromised interpolation accuracy or prolonged inference. This work presents FastPCI that introduces Pyramid Convolution-Transformer architecture for point cloud frame interpolation. Our hybrid Convolution-Transformer improves the local and long-range feature learning, while the pyramid network offers multilevel features and reduces the computation. In addition, FastPCI proposes a unique Dual-Direction Motion-Structure block for more accurate scene flow estimation. Our design is motivated by two facts: (1) accurate scene flow preserves 3D structure, and (2) point cloud at the previous timestep should be reconstructable using reverse motion from future timestep. Extensive experiments show that FastPCI significantly outperforms the state-of-the-art PointINet and NeuralPCI with notable gains (e.g. 26.6% and 18.3% reduction in Chamfer Distance in KITTI), while being more than 10x and 600x faster, respectively. Code is available at https://github.com/genuszty/FastPCI
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。