mlsanityData to 14 Oct 2026

SuperPrimitive: Scene Reconstruction at a Primitive Level

arXiv 2312.05889 ↗First posted 10 Dec 2023cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

Joint camera pose and dense geometry estimation from a set of images or a monocular video remains a challenging problem due to its computational complexity and inherent visual ambiguities. Most dense incremental reconstruction systems operate directly on image pixels and solve for their 3D positions using multi-view geometry cues. Such pixel-level approaches suffer from ambiguities or violations of multi-view consistency (e.g. caused by textureless or specular surfaces). We address this issue with a new image representation which we call a SuperPrimitive. SuperPrimitives are obtained by splitting images into semantically correlated local regions and enhancing them with estimated surface normal directions, both of which are predicted by state-of-the-art single image neural networks. This provides a local geometry estimate per SuperPrimitive, while their relative positions are adjusted based on multi-view observations. We demonstrate the versatility of our new representation by addressing three 3D reconstruction tasks: depth completion, few-view structure from motion, and monocular dense visual odometry.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 34 of its 58 references that are in the map. First posted on arXiv 10 Dec 2023.

Builds on

34 of 58 references.

References · 34

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2023Segment Anythingcited by 8,234
  3. 2021Vision Transformers for Dense Predictioncited by 1,803
  4. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
  5. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
  6. 2020ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAMcited by 878
  7. 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 615
  8. 2020Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understandingcited by 604
  9. 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 575
  10. 2016Direct Sparse Odometrycited by 485
  11. 2021NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Videocited by 241
  12. 2020Non-Local Spatial Propagation Network for Depth Completioncited by 195
22 more
  1. 2018DeepV2D: Video to Depth with Differentiable Structure from Motioncited by 185
  2. 2018CodeSLAM - Learning a Compact, Optimisable Representation for Dense Visual SLAMcited by 152
  3. 2020DeepFactors: Real-Time Probabilistic Dense Monocular SLAMcited by 117
  4. 2021Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimationcited by 116
  5. 2020TartanVO: A Generalizable Learning-based VOcited by 108
  6. 2021TransformerFusion: Monocular RGB Scene Reconstruction using Transformerscited by 106
  7. 2018PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Imagecited by 105
  8. 2018Fusion++: Volumetric Object-Level SLAMcited by 98
  9. 2019Unsupervised Depth Completion from Visual Inertial Odometrycited by 89
  10. 2018QuadricSLAM: Dual Quadrics from Object Detections as Landmarks in Object-oriented SLAMcited by 86
  11. 2022SimpleRecon: 3D Reconstruction Without 3D Convolutionscited by 83
  12. 2019How do neural networks see depth in single images?cited by 82
  13. 2018PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Imagecited by 77
  14. 2020NodeSLAM: Neural Object Descriptors for Multi-View Shape Reconstructioncited by 61
  15. 2021Unsupervised Depth Completion with Calibrated Backprojection Layerscited by 61
  16. 2021Learning Topology from Synthetic Data for Unsupervised Depth Completioncited by 38
  17. 2022Monitored Distillation for Positive Congruent Depth Completioncited by 24
  18. 2023Monocular Visual-Inertial Depth Estimationcited by 18
  19. 2023Learning a Depth Covariance Functioncited by 16
  20. 2023NeuSE: Neural SE(3)-Equivariant Embedding for Long-Term Object-Based Simultaneous Localization and Mappingcited by 10
  21. 2023PlaneRecTR++: Unified Query Learning for Joint 3D Planar Reconstruction and Pose Estimationcited by 6
  22. 2022Simultaneous Localisation and Mapping with Quadric Surfacescited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 3; 2026: 5.

11 papers.

  1. 2024MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priorscited by 205
  2. 2025ViSTA-SLAM: Visual SLAM with Symmetric Two-view Associationcited by 16
  3. 2025G4Splat: Geometry-Guided Gaussian Splatting with Generative Priorcited by 10
  4. 2026SPEAR: A Simulator for Photorealistic Embodied AI Researchcited by 4
  5. 2024FusionSense: Bridging Common Sense, Vision, and Touch for Robust Sparse-View Reconstructioncited by 2
  6. 2024MultiDepth: Multi-Sample Priors for Refining Monocular Metric Depth Estimations in Indoor Scenescited by 1
  7. 20254D Primitive-Mach'e: Glueing Primitives for Persistent 4D Scene Reconstructioncited by 1
  8. 2026PlanaReLoc: Camera Relocalization in 3D Planar Primitives via Region-Based Structure Matchingcited by 0
  9. 2026DecoRec: Decomposed 3D Scene Reconstruction from Single-View Images via Object-Level Diffusioncited by 0
  10. 2026PixVOD: Pixel-Distributed Direct Visual Odometry and Depth Estimationcited by 0
  11. 2026BLASt3R: Bundle Adjustment of Any Image Set with Multi-View Matching and Monocular Priorscited by 0