A Caltech Library Service

Mesh R-CNN

Gkioxari, Georgia and Malik, Jitendra and Johnson, Justin (2019) Mesh R-CNN. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV). IEEE , Piscataway, NJ, pp. 9784-9794. ISBN 978-1-7281-4803-8.

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item:


Rapid advances in 2D perception have led to systems that accurately detect objects in real-world images. However, these systems make predictions in 2D, ignoring the 3D structure of the world. Concurrently, advances in 3D shape prediction have mostly focused on synthetic benchmarks and isolated objects. We unify advances in these two areas. We propose a system that detects objects in real-world images and produces a triangle mesh giving the full 3D shape of each detected object. Our system, called Mesh R-CNN, augments Mask R-CNN with a mesh prediction branch that outputs meshes with varying topological structure by first predicting coarse voxel representations which are converted to meshes and refined with a graph convolution network operating over the mesh's vertices and edges. We validate our mesh prediction branch on ShapeNet, where we outperform prior work on single-image shape prediction. We then deploy our full Mesh R-CNN system on Pix3D, where we jointly detect objects and predict their 3D shapes.

Item Type:Book Section
Related URLs:
URLURL TypeDescription ItemDiscussion Paper
Malik, Jitendra0000-0003-3695-1580
Johnson, Justin0000-0002-1251-088X
Record Number:CaltechAUTHORS:20221215-789777000.18
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:118378
Deposited By: George Porter
Deposited On:19 Dec 2022 20:56
Last Modified:19 Dec 2022 22:39

Repository Staff Only: item control page