RAI-Net: Range-Adaptive LiDAR Point Cloud Frame Interpolation Network

Zhao, Lili; Zhu, Zezhi; Lin, Xuhu; Guo, Xuezhou; Yin, Qian; Wang, Wenyi; Chen, Jianwen

doi:10.1109/bmsb53066.2021.9547131

Cited by 7 publications

(1 citation statement)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…image can map to the same location in the target, which creates an ambiguity that in the context of deep learning needs to be resolved differentiably. Softmax splatting is a recent solution to this problem [44], which has already found many applications [16,17,23,33,70]. However, we have found a numerical instability in the way softmax splatting is implemented, which we subsequently outline and address.…”

Section: Stable Softmax Splattingmentioning

confidence: 91%

Softmax Splatting for Video Frame Interpolation

Niklaus

Liu

2020

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

340

263

View full text Add to dashboard Cite

Frame interpolation is an essential video processing technique that adjusts the temporal resolution of an image sequence. An effective approach to perform frame interpolation is based on splatting, also known as forward warping. Specifically, splatting can be used to warp the input images to an arbitrary temporal location based on an optical flow estimate. A synthesis network, also sometimes referred to as refinement network, can then be used to generate the output frame from the warped images. In doing so, it is common to not only warp the images but also various feature representations which provide rich contextual cues to the synthesis network. However, while this approach has been shown to work well and enables arbitrary-time interpolation due to using splatting, the involved synthesis network is prohibitively slow. In contrast, we propose to solely rely on splatting to synthesize the output without any subsequent refinement. This splatting-based synthesis is much faster than similar approaches, especially for multi-frame interpolation, while enabling new state-of-the-art results at high resolutions.

show abstract