论文标题
时间将说明：新的前景和时间多视图3D对象检测的基线
Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detection
论文作者
论文摘要
尽管最近仅相机的3D检测方法利用了多个时间段，但它们使用的有限历史可显着阻碍时间融合可以改善对象感知的程度。观察到现有作品的多帧图像的融合是时间立体声匹配的实例，我们发现性能受到了互动的阻碍，而介于1）匹配分辨率的低粒度和2）较小的多视图设置受到有限历史记录使用产生的。我们的理论和经验分析表明，不同像素和深度的观点之间的最佳时间差异显着变化，因此有必要在长期历史上融合许多时间段。在调查的基础上，我们建议从图像观测的悠久历史记录中产生成本量，并使用更最佳的多视图匹配设置来补偿粗糙但有效的匹配分辨率。此外，我们增加了用于长期，与短期，细粒度匹配的长期匹配的人均单眼深度预测，并发现长期和短期的时间融合是高度互补的。在保持高效率的同时，我们的框架设置了Nuscenes上的最新最先进，在测试集上获得了第一名，并在5.2％的地图上优于先前的最佳艺术，而在验证集上则优于3.7％的NDS。代码将发布$ \ href {https://github.com/divadi/solofusion} {there。} $
While recent camera-only 3D detection methods leverage multiple timesteps, the limited history they use significantly hampers the extent to which temporal fusion can improve object perception. Observing that existing works' fusion of multi-frame images are instances of temporal stereo matching, we find that performance is hindered by the interplay between 1) the low granularity of matching resolution and 2) the sub-optimal multi-view setup produced by limited history usage. Our theoretical and empirical analysis demonstrates that the optimal temporal difference between views varies significantly for different pixels and depths, making it necessary to fuse many timesteps over long-term history. Building on our investigation, we propose to generate a cost volume from a long history of image observations, compensating for the coarse but efficient matching resolution with a more optimal multi-view matching setup. Further, we augment the per-frame monocular depth predictions used for long-term, coarse matching with short-term, fine-grained matching and find that long and short term temporal fusion are highly complementary. While maintaining high efficiency, our framework sets new state-of-the-art on nuScenes, achieving first place on the test set and outperforming previous best art by 5.2% mAP and 3.7% NDS on the validation set. Code will be released $\href{https://github.com/Divadi/SOLOFusion}{here.}$
