Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published October 2023 | Published
Conference Paper

Pixel-Aligned Recurrent Queries for Multi-View 3D Object Detection

  • 1. ROR icon California Institute of Technology

Abstract

We present PARQ - a multi-view 3D object detector with transformer and pixel-aligned recurrent queries. Unlike previous works that use learnable features or only encode 3D point positions as queries in the decoder, PARQ leverages appearance-enhanced queries initialized from reference points in 3D space and updates their 3D location with recurrent cross-attention operations. Incorporating pixel-aligned features and cross attention enables the model to encode the necessary 3D-to-2D correspondences and capture global contextual information of the input images. PARQ outperforms prior best methods on the ScanNet and ARKitScenes datasets, learns and detects faster, is more robust to distribution shifts in reference points, can leverage additional input views without retraining, and can adapt inference compute by changing the number of recurrent iterations. Code is available at https://ymingxie.github.io/parq.

Copyright and License

© 2023 IEEE.

Additional details

Created:
February 13, 2024
Modified:
February 13, 2024