Papers › Mesh R-CNN

Mesh R-CNN

6 Jun 2019ICCV 2019 10arXiv:1906.02739archive 2025-07-28

Georgia Gkioxari, Jitendra Malik, Justin Johnson

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.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

IMAC-projects/mesh-deformation mentioned on GitHubpytorch report
Penguinazor/mse.wem.project mentioned on GitHub report
facebookresearch/meshrcnn mentioned on GitHubpytorch report
facebookresearch/pytorch3d mentioned on GitHubpytorchNOASSERTION report
huang229/auto_tooth_arrangement mentioned on GitHubpytorch report
theycallmepeter/pytorch3d_PBR mentioned on GitHubpytorchNOASSERTION report
xhxuciedu/3DHand mentioned on GitHubApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Shape ModelingPrediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Shape Modeling Pix3D S1 Mesh R-CNN box AP 94.0 #1 of 1 Archive leaderboard report
3D Shape Modeling Pix3D S1 Mesh R-CNN mask AP 88.4 #1 of 1 Archive leaderboard report
3D Shape Modeling Pix3D S1 Mesh R-CNN mesh AP 51.1 #1 of 1 Archive leaderboard report
3D Shape Modeling Pix3D S2 Mesh R-CNN box AP 72.2 #1 of 1 Archive leaderboard report
3D Shape Modeling Pix3D S2 Mesh R-CNN mask AP 63.9 #1 of 1 Archive leaderboard report
3D Shape Modeling Pix3D S2 Mesh R-CNN mesh AP 28.8 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

ConvolutionRoIAlignSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections