</> Code with Papers by Syntology

Datasets › Pix3D

Pix3D

Introduced by Xingyuan Sun et al. in Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling1 Jan 2018 archive 2025-07-28

The Pix3D dataset is 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.

Source: http://pix3d.csail.mit.edu/ Image Source: http://pix3d.csail.mit.edu/

HomepageBenchmarksPapers JSON

Benchmarks archive 2025-07-28

All 5 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
3D Shape Reconstruction Pix3D IM3D CD 0.0672 Holistic 3D Scene Understanding from a Single Image with... chengzhag/Implicit3DUnderstanding 5 Compare
3D Shape Classification Pix3D MarrNet extension (w/o Pose) R@1 0.53 Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling xingyuansun/pix3d 3 Compare
3D Shape Modeling Pix3D S1 Mesh R-CNN box AP 94.0 Mesh R-CNN facebookresearch/pytorch3d +6 1 Compare
3D Shape Modeling Pix3D S2 Mesh R-CNN box AP 72.2 Mesh R-CNN facebookresearch/pytorch3d +6 1 Compare
Pose Estimation Pix3D Mid-Level based Percentage correct 74.55 Object Pose Estimation using Mid-level Visual Representations n-nejatishahidin/pose_from_mid-level 1 Compare

Papers archive 2025-07-28

9 shown of 9 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 142. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
Object Pose Estimation using Mid-level Visual Representations 1 1 2 Mar 2022 not harvested
Holistic 3D Scene Understanding from a Single Image with Implicit Representation 1 1 11 Mar 2021 not harvested
Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image 1 1 27 Feb 2020 ran 2 of 9 samples (7 unverified)
Deep Mesh Reconstruction from Single RGB Images via Topology Modification Networks 1 1 1 Sep 2019 ran 1 of 12 samples (11 unverified)
Mesh R-CNN 7 2 6 Jun 2019 not harvested
Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling 1 2 12 Apr 2018 not harvested
AtlasNet: A Papier-Mâché Approach to Learning 3D Surface Generation 3 1 15 Feb 2018 ran 3 of 3 samples (0 unverified; 3 pointer-only for licence)
MarrNet: 3D Shape Reconstruction via 2.5D Sketches 0 1 8 Nov 2017 not harvested
Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling 3 1 24 Oct 2016 ran 3 of 3 samples (0 unverified)

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

Pose Estimation3D Shape Reconstruction3D Shape Modeling3D Shape Classification

License archive 2025-07-28

CC BY 4.0

Modalities archive 2025-07-28

Images3D

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • Pix3D S2
  • Pix3D S1
  • Pix3D

3 variant names, as the archive lists them.

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