3D Object Detection and Pose Estimation of Unseen Objects in Color Images with Local Surface Embeddings

Autor: Giorgia Pitteri, Slobodan Ilic, Vincent Lepetit, Aurélie Bugeau
Přispěvatelé: Laboratoire Bordelais de Recherche en Informatique (LaBRI), Université de Bordeaux (UB)-Centre National de la Recherche Scientifique (CNRS)-École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB), Corporate technology Siemens, Siemens AG [Munich], IMAGINE [Marne-la-Vallée], Laboratoire d'Informatique Gaspard-Monge (LIGM), École des Ponts ParisTech (ENPC)-Centre National de la Recherche Scientifique (CNRS)-Université Gustave Eiffel-École des Ponts ParisTech (ENPC)-Centre National de la Recherche Scientifique (CNRS)-Université Gustave Eiffel, Pitteri, Giorgia
Jazyk: angličtina
Rok vydání: 2020
Předmět:
FOS: Computer and information sciences
Computer science
Computer Vision and Pattern Recognition (cs.CV)
Computer Science - Computer Vision and Pattern Recognition
CAD
02 engineering and technology
010501 environmental sciences
[INFO] Computer Science [cs]
01 natural sciences
Image (mathematics)
[INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]
Discriminative model
0202 electrical engineering
electronic engineering
information engineering

Computer vision
[INFO]Computer Science [cs]
Limit (mathematics)
Pose
0105 earth and related environmental sciences
business.industry
Deep learning
[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]
Object detection
Embedding
020201 artificial intelligence & image processing
Artificial intelligence
business
Zdroj: 15th Asian Conference on Computer Vision
15th Asian Conference on Computer Vision, Nov 2020, Kyoto (virtual conference), Japan
Computer Vision – ACCV 2020 ISBN: 9783030695248
ACCV (1)
HAL
Popis: International audience; We present an approach for detecting and estimating the 3D poses of objects in images that requires only an untextured CAD model and no training phase for new objects. Our approach combines Deep Learning and 3D geometry: It relies on an embedding of local 3D geometry to match the CAD models to the input images. For points at the surface of objects, this embedding can be computed directly from the CAD model; for image locations, we learn to predict it from the image itself. This establishes correspondences between 3D points on the CAD model and 2D locations of the input images. However, many of these correspondences are ambiguous as many points may have similar local geometries. We show that we can use Mask-RCNN in a class-agnostic way to detect the new objects without retraining and thus drastically limit the number of possible correspondences. We can then robustly estimate a 3D pose from these discriminative correspondences using a RANSAC-like algorithm. We demonstrate the performance of this approach on the T-LESS dataset, by using a small number of objects to learn the embedding and testing it on the other objects. Our experiments show that our method is on par or better than previous methods.
Databáze: OpenAIRE