TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/Pix3D: Dataset and Methods for Single-Image 3D Shape Model...

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

2018-04-12CVPR 2018 63D Shape Modeling3D Shape ReconstructionPose Estimation3D ReconstructionMulti-Task LearningViewpoint EstimationRetrieval
PaperPDFCode

Abstract

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.

Results

TaskDatasetMetricValueModel
3DPix3DCD0.119MarrNet extension (w/ Pose)
3DPix3DEMD0.118MarrNet extension (w/ Pose)
3DPix3DIoU0.282MarrNet extension (w/ Pose)
3DPix3DR@10.53MarrNet extension (w/o Pose)
3DPix3DR@160.85MarrNet extension (w/o Pose)
3DPix3DR@20.62MarrNet extension (w/o Pose)
3DPix3DR@320.9MarrNet extension (w/o Pose)
3DPix3DR@40.71MarrNet extension (w/o Pose)
3DPix3DR@80.78MarrNet extension (w/o Pose)
3D Shape ReconstructionPix3DCD0.119MarrNet extension (w/ Pose)
3D Shape ReconstructionPix3DEMD0.118MarrNet extension (w/ Pose)
3D Shape ReconstructionPix3DIoU0.282MarrNet extension (w/ Pose)

Related Papers

$π^3$: Scalable Permutation-Equivariant Visual Geometry Learning2025-07-17Revisiting Reliability in the Reasoning-based Pose Estimation Benchmark2025-07-17DINO-VO: A Feature-based Visual Odometry Leveraging a Visual Foundation Model2025-07-17From Neck to Head: Bio-Impedance Sensing for Head Pose Estimation2025-07-17AthleticsPose: Authentic Sports Motion Dataset on Athletic Field and Evaluation of Monocular 3D Pose Estimation Ability2025-07-17AutoPartGen: Autogressive 3D Part Generation and Discovery2025-07-17SGCL: Unifying Self-Supervised and Supervised Learning for Graph Recommendation2025-07-17From Roots to Rewards: Dynamic Tree Reasoning with RL2025-07-17