2021/04/22 by Ji Hou, Hou, Ji, Saining Xie +7 · 3 citations
Computer Science · Earth and Planetary Sciences · Engineering · #3D Shape Modeling and Analysis #3D Surveying and Cultural Heritage #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Human Pose and Action Recognition
paper · pdf · doi:10.48550/arxiv.2104.11225
openalex publication_date 2021/04/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Recent advances in 3D perception have shown impressive progress in understanding geometric structures of 3Dshapes and even scenes. Inspired by these advances in geometric understanding, we aim to imbue image-based perception with representations learned under geometric constraints. We introduce an approach to learn view-invariant,geometry-aware representations for network pre-training, based on multi-view RGB-D data, that can then be effectively transferred to downstream 2D tasks. We propose to employ contrastive learning under both multi-view im-age constraints and image-geometry constraints to encode3D priors into learned 2D representations. This results not only in improvement over 2D-only representation learning on the image-based tasks of semantic segmentation, instance segmentation, and object detection on real-world in-door datasets, but moreover, provides significant improvement in the low data regime. We show a significant improvement of 6.0% on semantic segmentation on full data as well as 11.9% on 20% data against baselines on ScanNet.