Projecting sparse LiDAR depth into predicted structural features and injecting them into learned image codecs consistently improves rate-distortion performance on KITTI and Waymo.
Pointpainting: Sequen- tial fusion for 3d object detection,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Sparse Point Clouds Assisted Learned Image Compression
Projecting sparse LiDAR depth into predicted structural features and injecting them into learned image codecs consistently improves rate-distortion performance on KITTI and Waymo.