Papers › MarrNet: 3D Shape Reconstruction via 2.5D Sketches

MarrNet: 3D Shape Reconstruction via 2.5D Sketches

8 Nov 2017NeurIPS 2017 12arXiv:1711.03129archive 2025-07-28

Jiajun Wu, Yifan Wang, Tianfan Xue, Xingyuan Sun, William T. Freeman, Joshua B. Tenenbaum

3D object reconstruction from a single image is a highly under-determined problem, requiring strong prior knowledge of plausible 3D shapes. This introduces challenges for learning-based approaches, as 3D object annotations are scarce in real images. Previous work chose to train on synthetic data with ground truth 3D information, but suffered from domain adaptation when tested on real data. In this work, we propose MarrNet, an end-to-end trainable model that sequentially estimates 2.5D sketches and 3D object shape. Our disentangled, two-step formulation has three advantages. First, compared to full 3D shape, 2.5D sketches are much easier to be recovered from a 2D image; models that recover 2.5D sketches are also more likely to transfer from synthetic to real data. Second, for 3D reconstruction from 2.5D sketches, systems can learn purely from synthetic data. This is because we can easily render realistic 2.5D sketches without modeling object appearance variations in real images, including lighting, texture, etc. This further relieves the domain adaptation problem. Third, we derive differentiable projective functions from 3D shape to 2.5D sketches; the framework is therefore end-to-end trainable on real images, requiring no human annotations. Our model achieves state-of-the-art performance on 3D shape reconstruction.

PaperPDFConference PDF

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

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

3D Object Reconstruction3D Object Reconstruction From A Single Image3D Reconstruction3D Shape ReconstructionDomain AdaptationObjectObject Reconstruction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Shape Classification Pix3D MarrNet R@1 0.42 #2 of 3 Archive leaderboard report
3D Shape Classification Pix3D MarrNet R@16 0.71 #2 of 3 Archive leaderboard report
3D Shape Classification Pix3D MarrNet R@2 0.51 #2 of 3 Archive leaderboard report
3D Shape Classification Pix3D MarrNet R@32 0.78 #2 of 3 Archive leaderboard report
3D Shape Classification Pix3D MarrNet R@4 0.57 #2 of 3 Archive leaderboard report
3D Shape Classification Pix3D MarrNet R@8 0.64 #2 of 3 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