mlsanityData to 7 Oct 2026

Atlas: End-to-End 3D Scene Reconstruction from Posed Images

arXiv 2003.10432 ↗First posted 23 Mar 2020cs.CVcited by 206

Not on the map. Why?

Abstract (arXiv)

We present an end-to-end 3D reconstruction method for a scene by directly regressing a truncated signed distance function (TSDF) from a set of posed RGB images. Traditional approaches to 3D reconstruction rely on an intermediate representation of depth maps prior to estimating a full 3D model of a scene. We hypothesize that a direct regression to 3D is more effective. A 2D CNN extracts features from each image independently which are then back-projected and accumulated into a voxel volume using the camera intrinsics and extrinsics. After accumulation, a 3D CNN refines the accumulated features and predicts the TSDF values. Additionally, semantic segmentation of the 3D model is obtained without significant computation. This approach is evaluated on the Scannet dataset where we significantly outperform state-of-the-art baselines (deep multiview stereo followed by traditional TSDF fusion) both quantitatively and qualitatively. We compare our 3D semantic segmentation to prior methods that use a depth sensor since no previous work attempts the problem with only RGB input.

Key facts. Cited by 206 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 21; 2022: 30; 2023: 45; 2024: 57; 2025: 28; 2026: 25.

206 papers.

Sort:

By area:

  1. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 586
  2. 2023SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Drivingcited by 310
  3. 2022Cross-view Transformers for real-time Map-view Semantic Segmentationcited by 264
  4. 2022Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representationcited by 243
  5. 2021NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Videocited by 241
  6. 2024MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priorscited by 198
  7. 2021NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereocited by 191
  8. 2023Point-SLAM: Dense Neural Point Cloud-based SLAMcited by 160
  9. 2022ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fieldscited by 158
  10. 2021ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detectioncited by 157
  11. 2022M2BEV: Multi-Camera Joint 3D Detection and Segmentation with Unified Birds-Eye View Representationcited by 155
  12. 2024GaussianFormer: Scene as Gaussians for Vision-Based 3D Semantic Occupancy Predictioncited by 155
38 more
  1. 2023Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splattingcited by 152
  2. 2022NeuMesh: Learning Disentangled Neural Mesh-based Implicit Field for Geometry and Texture Editingcited by 141
  3. 2021Improving neural implicit surfaces geometry with patch warpingcited by 136
  4. 2024DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshingcited by 136
  5. 2021Unconstrained Scene Generation with Locally Conditioned Radiance Fieldscited by 130
  6. 2022NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priorscited by 125
  7. 2022Neural 3D Scene Reconstruction with the Manhattan-world Assumptioncited by 123
  8. 2021NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenescited by 119
  9. 2024Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splatscited by 111
  10. 2021TransformerFusion: Monocular RGB Scene Reconstruction using Transformerscited by 107
  11. 2022SimpleRecon: 3D Reconstruction Without 3D Convolutionscited by 83
  12. 2024GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Predictioncited by 83
  13. 2022Neural 3D Reconstruction in the Wildcited by 79
  14. 2024GaussianWorld: Gaussian World Model for Streaming 3D Occupancy Predictioncited by 66
  15. 2022GO-Surf: Neural Feature Grid Optimization for Fast, High-Fidelity RGB-D Surface Reconstructioncited by 61
  16. 2022VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstructioncited by 61
  17. 2023Fully Sparse 3D Occupancy Predictioncited by 61
  18. 2023NeO 360: Neural Fields for Sparse View Synthesis of Outdoor Scenescited by 53
  19. 2024Loopy-SLAM: Dense Neural SLAM with Loop Closurescited by 48
  20. 2021VolumeFusion: Deep Depth Fusion for 3D Scene Reconstructioncited by 44
  21. 2021MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutionscited by 43
  22. 2023Dense RGB SLAM with Neural Implicit Mapscited by 42
  23. 2023Fast-BEV: A Fast and Strong Bird's-Eye View Perception Baselinecited by 40
  24. 2024Scaling Diffusion Models to Real-World 3D LiDAR Scene Completioncited by 40
  25. 2021TANDEM: Tracking and Dense Mapping in Real-time using Deep Multi-view Stereocited by 39
  26. 2021StereoPIFu: Depth Aware Clothed Human Digitization via Stereo Visioncited by 38
  27. 2021VoRTX: Volumetric 3D Reconstruction With Transformers for Voxelwise View Selection and Fusioncited by 38
  28. 2023SNAP: Self-Supervised Neural Maps for Visual Positioning and Semantic Understandingcited by 38
  29. 2023Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitivescited by 37
  30. 2024OccFusion: Multi-Sensor Fusion Framework for 3D Semantic Occupancy Predictioncited by 32
  31. 2021Input-level Inductive Biases for 3D Reconstructioncited by 31
  32. 2022NeuralHDHair: Automatic High-fidelity Hair Modeling from a Single Image Using Implicit Neural Representationscited by 31
  33. 2021Continual Neural Mapping: Learning An Implicit Scene Representation from Sequential Observationscited by 30
  34. 2022Pseudo-Stereo for Monocular 3D Object Detection in Autonomous Drivingcited by 30
  35. 2024Scaling 4D Representationscited by 30
  36. 2022PlaneMVS: 3D Plane Reconstruction from Multi-View Stereocited by 29
  37. 2024SceneGraphLoc: Cross-Modal Coarse Visual Localization on 3D Scene Graphscited by 29
  38. 2024Monocular Occupancy Prediction for Scalable Indoor Scenescited by 29

50 most cited of 206 All 206 (JSON)