Papers › Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling
Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling
Xingyuan Sun, Jiajun Wu, Xiuming Zhang, Zhoutong Zhang, Chengkai Zhang, Tianfan Xue, Joshua B. Tenenbaum, William T. Freeman
We study 3D shape modeling from a single image and make contributions to it in three aspects. First, we present Pix3D, a large-scale benchmark of diverse image-shape pairs with pixel-level 2D-3D alignment. Pix3D has wide applications in shape-related tasks including reconstruction, retrieval, viewpoint estimation, etc. Building such a large-scale dataset, however, is highly challenging; existing datasets either contain only synthetic data, or lack precise alignment between 2D images and 3D shapes, or only have a small number of images. Second, we calibrate the evaluation criteria for 3D shape reconstruction through behavioral studies, and use them to objectively and systematically benchmark cutting-edge reconstruction algorithms on Pix3D. Third, we design a novel model that simultaneously performs 3D reconstruction and pose estimation; our multi-task learning approach achieves state-of-the-art performance on both tasks.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Datasets
Introduced by this paper, per the archive.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 3D Shape Classification | Pix3D | MarrNet extension (w/o Pose) | R@1 | 0.53 | #1 of 3 | Archive leaderboard | report |
| 3D Shape Classification | Pix3D | MarrNet extension (w/o Pose) | R@16 | 0.85 | #1 of 3 | Archive leaderboard | report |
| 3D Shape Classification | Pix3D | MarrNet extension (w/o Pose) | R@2 | 0.62 | #1 of 3 | Archive leaderboard | report |
| 3D Shape Classification | Pix3D | MarrNet extension (w/o Pose) | R@32 | 0.90 | #1 of 3 | Archive leaderboard | report |
| 3D Shape Classification | Pix3D | MarrNet extension (w/o Pose) | R@4 | 0.71 | #1 of 3 | Archive leaderboard | report |
| 3D Shape Classification | Pix3D | MarrNet extension (w/o Pose) | R@8 | 0.78 | #1 of 3 | Archive leaderboard | report |
| 3D Shape Reconstruction | Pix3D | MarrNet extension (w/ Pose) | CD | 0.119 | #4 of 5 | Archive leaderboard | report |
| 3D Shape Reconstruction | Pix3D | MarrNet extension (w/ Pose) | EMD | 0.118 | #4 of 5 | Archive leaderboard | report |
| 3D Shape Reconstruction | Pix3D | MarrNet extension (w/ Pose) | IoU | 0.282 | #4 of 5 | 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