Accurately matching points across different images, viewing the same object or scene, is a crucial step in many computer vision tasks. Local image descriptors must handle image transformations in order to provide invariance to viewing conditions, such as illumination and perspective changes. However, most of them are not designed to cope with non-rigid deformations. In this project, we focus on improving local image description techniques to correctly handle non-rigid deformations, while also improving their discriminative power.

GeoBit (ICCV 2019)

GeoBit is a handcrafted binary descriptor that combines appearance and geometric information from RGB-D images to handle isometric non-rigid deformations. It leverages geodesic isocurve information, from heat flow in the surface manifold, to select the feature binary tests.

Visit the page for additional information, code and paper access.

GeoPatch (In Review)

GeoPatch is a learning-based descriptor designed with a shallow convolutional neural network.  The network is trained using weight -sharing siamese triplets of geodesic image patches. Rotations in the geodesic patches are represented by shifts (1D coordinate translations). The network is then trained with translated data augmented patches to provide rotation invariance.

Further details coming after the review process.


Copyright Notice

The datasets available for download in this page are published under the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) License. This means you must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use. You may not use the material for commercial purposes.

Dataset of Deformable RGB-D Images (Presented at ICCV’19):
Kinect 1 Sequences (38 MB) : This dataset contains six different real-world objects under different deformation levels and illumination changes. The RGB-D images were acquired at 640 x 480 resolution with a Kinect 1 sensor. Each image has approximately 50 manually annotated keypoints.

Simulation (26 MB) : This dataset is composed of simulated RGB-D sequences (640 x 480 pixels) with a physics cloth engine simulation. Several textured clothes are subjected to challenging non-rigid deformation, illumination, rotation and scale changes. The keypoints in this sequence are selected with Harris score in the first reference texture image, and their exact correspondence overtime are tracked in the simulation.

Extended Dataset (Journal Submission under Peer Review):
Kinect 2 Sequences (1.1 GB) : This dataset contains five additional real-world objects acquired with a Kinect 2 sensor at 1920 x 1080 resolution images. We provide image sequences for each of the five objects containing different levels of deformations: light, medium and heavy deformations. Accurate 80 pointwise correspondences are automatically obtained with a motion capture system.

Dataset File Format: All datasets follow the same format: Color images are stored as 8-bit PNG and depth images are stored as 16-bit PNG images in millimetres. The intrinsics.xml file contains the intrinsic parameters of the camera, allowing the reconstruction of the pointcloud. Each image also has a respective .csv file, where each line consists of a keypoint number (ID), its 2D image coordinates and a boolean flag indicating if the keypoint is visible in the current keyframe. The keypoints are selected in the reference image, therefore all keypoints are visible in the reference frame.


[ICCV 2019] Erickson R. Nascimento and Guilherme Potje and Renato Martins and Felipe Chamone and Mario F. M. Campos and Ruzena Bajcsy. GEOBIT: A Geodesic-Based Binary Descriptor Invariant to Non-Rigid Deformations for RGB-D Images, 2019 IEEE International Conference on Computer Vision (ICCV), 2019.
Visit the page for more information and paper access.


This project is supported by CAPES, CNPq, and FAPEMIG.


Guilherme Augusto Potje

PhD Student

Renato José Martins

Post-doctoral Researcher

Felipe Cadar Chamone

Undergraduate Student

Ruzena Bajcsy