2D3D-MATR: 2D-3D Matching Transformer for Detection-free Registration between Images and Point Clouds
This addresses the challenge of accurate image-to-point cloud registration for applications like robotics and augmented reality, offering a significant performance improvement over existing methods.
The paper tackles the problem of cross-modality registration between images and point clouds by proposing 2D3D-MATR, a detection-free method that uses a coarse-to-fine transformer-based pipeline with multi-scale patch matching. The result shows it outperforms the previous state-of-the-art P2-Net by around 20 percentage points on inlier ratio and over 10 points on registration recall on two public benchmarks.
The commonly adopted detect-then-match approach to registration finds difficulties in the cross-modality cases due to the incompatible keypoint detection and inconsistent feature description. We propose, 2D3D-MATR, a detection-free method for accurate and robust registration between images and point clouds. Our method adopts a coarse-to-fine pipeline where it first computes coarse correspondences between downsampled patches of the input image and the point cloud and then extends them to form dense correspondences between pixels and points within the patch region. The coarse-level patch matching is based on transformer which jointly learns global contextual constraints with self-attention and cross-modality correlations with cross-attention. To resolve the scale ambiguity in patch matching, we construct a multi-scale pyramid for each image patch and learn to find for each point patch the best matching image patch at a proper resolution level. Extensive experiments on two public benchmarks demonstrate that 2D3D-MATR outperforms the previous state-of-the-art P2-Net by around $20$ percentage points on inlier ratio and over $10$ points on registration recall. Our code and models are available at https://github.com/minhaolee/2D3DMATR.