Papers › MegaPose: 6D Pose Estimation of Novel Objects via Render & Compare

MegaPose: 6D Pose Estimation of Novel Objects via Render & Compare

13 Dec 2022arXiv:2212.06870archive 2025-07-28

Yann Labbé, Lucas Manuelli, Arsalan Mousavian, Stephen Tyree, Stan Birchfield, Jonathan Tremblay, Justin Carpentier, Mathieu Aubry, Dieter Fox, Josef Sivic

We introduce MegaPose, a method to estimate the 6D pose of novel objects, that is, objects unseen during training. At inference time, the method only assumes knowledge of (i) a region of interest displaying the object in the image and (ii) a CAD model of the observed object. The contributions of this work are threefold. First, we present a 6D pose refiner based on a render&compare strategy which can be applied to novel objects. The shape and coordinate system of the novel object are provided as inputs to the network by rendering multiple synthetic views of the object's CAD model. Second, we introduce a novel approach for coarse pose estimation which leverages a network trained to classify whether the pose error between a synthetic rendering and an observed image of the same object can be corrected by the refiner. Third, we introduce a large-scale synthetic dataset of photorealistic images of thousands of objects with diverse visual and shape properties and show that this diversity is crucial to obtain good generalization performance on novel objects. We train our approach on this large synthetic dataset and apply it without retraining to hundreds of novel objects in real images from several pose estimation benchmarks. Our approach achieves state-of-the-art performance on the ModelNet and YCB-Video datasets. An extensive evaluation on the 7 core datasets of the BOP challenge demonstrates that our approach achieves performance competitive with existing approaches that require access to the target objects during training. Code, dataset and trained models are available on the project page: https://megapose6d.github.io/.

PaperPDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

Code

megapose6d/megapose6d mentioned on GitHubpytorchNOASSERTION 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 Object Detection6D Pose EstimationObjectPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Object Detection DTTD-Mobile MegaPose-RGBD ADD AUC 49.02 #3 of 5 Archive leaderboard report
3D Object Detection DTTD-Mobile MegaPose-RGBD ADD-S AUC 62.44 #3 of 5 Archive leaderboard report
6D Pose Estimation DTTD-Mobile MegaPose-RGBD (refined) ADD AUC 49.02 #2 of 8 Archive leaderboard report
6D Pose Estimation DTTD-Mobile MegaPose-RGBD (refined) ADD-S AUC 62.44 #2 of 8 Archive leaderboard report
6D Pose Estimation DTTD-Mobile MegaPose-RGBD (refined) AR CH 8.77 #2 of 8 Archive leaderboard report
6D Pose Estimation DTTD-Mobile MegaPose-RGBD (refined) AR CoU 17.73 #2 of 8 Archive leaderboard report
6D Pose Estimation DTTD-Mobile MegaPose-RGBD (refined) AR pCH 57 #2 of 8 Archive leaderboard report
6D Pose Estimation DTTD-Mobile MegaPose-RGBD (Coarse) AR CH 6.67 #8 of 8 Archive leaderboard report
6D Pose Estimation DTTD-Mobile MegaPose-RGBD (Coarse) AR CoU 13.72 #8 of 8 Archive leaderboard report
6D Pose Estimation DTTD-Mobile MegaPose-RGBD (Coarse) AR pCH 58.05 #8 of 8 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.

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