SOTAVerified

3D Point Cloud Interpolation

Point cloud interpolation is a fundamental problem for 3D computer vision. Given a low temporal resolution (frame rate) point cloud sequence, the target of interpolation is to generate a smooth point cloud sequence with high temporal resolution (frame rate).

Papers

Showing 16 of 6 papers

TitleStatusHype
NeuralPCI: Spatio-temporal Neural Field for 3D Point Cloud Multi-frame Non-linear InterpolationCode1
IDEA-Net: Dynamic 3D Point Cloud Interpolation via Deep Embedding AlignmentCode1
PointINet: Point Cloud Frame Interpolation NetworkCode1
Linear Spherical Sliced Optimal Transport: A Fast Metric for Comparing Spherical Data0
Learning Spatial-Temporal Embeddings for Sequential Point Cloud Frame InterpolationCode0
Spatial-Temporal Consistency Refinement Network for Dynamic Point Cloud Frame InterpolationCode0
Show:102550

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1NSFPCD1.22Unverified
2IDEA-NetCD1.02Unverified
3PointINetCD0.96Unverified
4PV-RAFTCD0.92Unverified
5NeuralPCICD0.54Unverified
#ModelMetricClaimedVerifiedStatus
1NSFPCD1.75Unverified
2PV-RAFTCD1.64Unverified
3PointINetCD1.06Unverified
4NeuralPCICD0.8Unverified