mlsanityData to 7 Oct 2026

SAIL-VOS 3D: A Synthetic Dataset and Baselines for Object Detection and 3D Mesh Reconstruction from Video Data

arXiv 2105.08612 ↗First posted 18 May 2021cs.CV cs.GR cs.LGcited by 38

Not on the map. Why?

Abstract (arXiv)

Extracting detailed 3D information of objects from video data is an important goal for holistic scene understanding. While recent methods have shown impressive results when reconstructing meshes of objects from a single image, results often remain ambiguous as part of the object is unobserved. Moreover, existing image-based datasets for mesh reconstruction don't permit to study models which integrate temporal information. To alleviate both concerns we present SAIL-VOS 3D: a synthetic video dataset with frame-by-frame mesh annotations which extends SAIL-VOS. We also develop first baselines for reconstruction of 3D meshes from video data via temporal models. We demonstrate efficacy of the proposed baseline on SAIL-VOS 3D and Pix3D, showing that temporal information improves reconstruction quality. Resources and additional information are available at http://sailvos.web.illinois.edu.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). Builds on 51 of its 89 references that are in the map. First posted on arXiv 18 May 2021.

Builds on

51 of 89 references.

References · 51

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2017Mask R-CNNcited by 7,259
  4. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  5. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  6. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  7. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  8. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  9. 2017The 2017 DAVIS Challenge on Video Object Segmentationcited by 942
  10. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 878
  11. 2016Playing for Data: Ground Truth from Computer Gamescited by 816
  12. 2020Convolutional Occupancy Networkscited by 760
38 more
  1. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
  2. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  3. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  4. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  5. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 521
  6. 2016Semantic Scene Completion from a Single Depth Imagecited by 468
  7. 2017Joint 2D-3D-Semantic Data for Indoor Scene Understandingcited by 404
  8. 2020PolyGen: An Autoregressive Generative Model of 3D Meshescited by 267
  9. 2016Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesiscited by 219
  10. 2018Pix3D: Dataset and Methods for Single-Image 3D Shape Modelingcited by 218
  11. 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 205
  12. 2016Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks?cited by 194
  13. 2017Learning a Multi-View Stereo Machinecited by 194
  14. 2017Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputscited by 189
  15. 2018DeepV2D: Video to Depth with Differentiable Structure from Motioncited by 185
  16. 2019CvxNet: Learnable Convex Decompositioncited by 173
  17. 2017Playing for Benchmarkscited by 169
  18. 2019Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Imagescited by 164
  19. 2019PQ-NET: A Generative Part Seq2Seq Network for 3D Shapescited by 118
  20. 2017MarrNet: 3D Shape Reconstruction via 2.5D Sketchescited by 108
  21. 2019Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformationcited by 103
  22. 2020Virtual Multi-view Fusion for 3D Semantic Segmentationcited by 99
  23. 2018Learning to Detect and Track Visible and Occluded Body Joints in a Virtual Worldcited by 81
  24. 2016IM2CADcited by 78
  25. 20173D-PRNN: Generating Shape Primitives with Recurrent Neural Networkscited by 77
  26. 2020Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB Imagecited by 72
  27. 2020OASIS: A Large-Scale Dataset for Single Image 3D in the Wildcited by 62
  28. 2020NodeSLAM: Neural Object Descriptors for Multi-View Shape Reconstructioncited by 61
  29. 2018Robust Watertight Manifold Surface Generation Method for ShapeNet Modelscited by 58
  30. 2015Multi-view 3D Models from Single Images with a Convolutional Networkcited by 57
  31. 2018Multi-view Consistency as Supervisory Signal for Learning Shape and Pose Predictioncited by 52
  32. 2017A Dataset for Developing and Benchmarking Active Visioncited by 50
  33. 2017Factoring Shape, Pose, and Layout from the 2D Image of a 3D Scenecited by 50
  34. 2019GEOMetrics: Exploiting Geometric Structure for Graph-Encoded Objectscited by 27
  35. 2017SilNet : Single- and Multi-View Reconstruction by Learning from Silhouettescited by 24
  36. 2020Reconstructing NBA Playerscited by 24
  37. 2018Soccer on Your Tabletopcited by 20
  38. 2019Simultaneous multi-view instance detection with learned geometric soft-constraintscited by 11

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 6; 2023: 5; 2024: 10; 2025: 4; 2026: 10.

38 papers.

Sort:

By area:

  1. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 395
  2. 2025MapAnything: Universal Feed-Forward Metric 3D Reconstructioncited by 295
  3. 2024Rethinking Inductive Biases for Surface Normal Estimationcited by 122
  4. 2023DCFace: Synthetic Face Generation with Dual Condition Diffusion Modelcited by 116
  5. 2021Playing for 3D Human Recoverycited by 63
  6. 2022CASA: Category-agnostic Skeletal Animal Reconstructioncited by 35
  7. 2024LRM-Zero: Training Large Reconstruction Models with Synthesized Datacited by 35
  8. 2025Any4D: Unified Feed-Forward Metric 4D Reconstructioncited by 32
  9. 2022Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point Cloudscited by 28
  10. 2024Recent Trends in 3D Reconstruction of General Non-Rigid Scenescited by 28
  11. 2025MVSAnywhere: Zero-Shot Multi-View Stereocited by 26
  12. 20244D Panoptic Scene Graph Generationcited by 22
26 more
  1. 2024Towards a Universal Synthetic Video Detector: From Face or Background Manipulations to Fully AI-Generated Contentcited by 22
  2. 2026VGGT-Omegacited by 20
  3. 2022PSP-HDRI+: A Synthetic Dataset Generator for Pre-Training of Human-Centric Computer Vision Modelscited by 15
  4. 2023SAD: Segment Any RGBDcited by 14
  5. 2022A Feature-space Multimodal Data Augmentation Technique for Text-video Retrievalcited by 13
  6. 2021PeopleSansPeople: A Synthetic Data Generator for Human-Centric Computer Visioncited by 11
  7. 2021Class-agnostic Reconstruction of Dynamic Objects from Videoscited by 8
  8. 2024SEED4D: A Synthetic Ego--Exo Dynamic 4D Data Generator, Driving Dataset and Benchmarkcited by 8
  9. 2023TAO-Amodal: A Benchmark for Tracking Any Object Amodallycited by 7
  10. 2025Learning 4D Panoptic Scene Graph Generation from Rich 2D Visual Scenecited by 6
  11. 2023M3Act: Learning from Synthetic Human Group Activitiescited by 5
  12. 2024WheelPose: Data Synthesis Techniques to Improve Pose Estimation Performance on Wheelchair Userscited by 5
  13. 2022Occupancy Planes for Single-view RGB-D Human Reconstructioncited by 4
  14. 2024GTA-HDR: A Large-Scale Synthetic Dataset for HDR Image Reconstructioncited by 4
  15. 2026X-Lens: Real-Time Metric Depth Estimation with Heterogeneous Camerascited by 3
  16. 2024Facing Asymmetry -- Uncovering the Causal Link between Facial Symmetry and Expression Classifiers using Synthetic Interventionscited by 2
  17. 2026SimpleProc: Fully Procedural Synthetic Data from Simple Rules for Multi-View Stereocited by 2
  18. 2026Cambrian-P: Pose-Grounded Video Understandingcited by 2
  19. 2026VLM3: Vision Language Models Are Native 3D Learnerscited by 2
  20. 2026TurboVGGT: Fast Visual Geometry Reconstruction with Adaptive Alternating Attentioncited by 1
  21. 2022Panoptic Segmentation using Synthetic and Real Datacited by 0
  22. 2023PDIWS: Thermal Imaging Dataset for Person Detection in Intrusion Warning Systemscited by 0
  23. 2026Complet4R: Geometric Complete 4D Reconstructioncited by 0
  24. 2026Time-Aware Assistive Navigationcited by 0
  25. 2026VGGT-Prime: Compute-Adaptive Mixture-of-Heads for Efficient Visual Geometry Transformerscited by 0
  26. 2026Revisiting Multi-View Stereo: A Sequence-to-Sequence Formulationcited by 0