mlsanityData to 14 Oct 2026

LaRI: Layered Ray Intersections for Single-view 3D Geometric Reasoning

arXiv 2504.18424 ↗First posted 25 Apr 2025cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

We present Layered Ray Intersections (LaRI), a fully supervised method for occluded geometry reasoning from a single image. Unlike conventional depth estimation, which is limited to visible surfaces, LaRI predicts multiple surfaces intersected by the camera rays using layered point maps. Compared to the existing approaches that leverage neural implicit representations or iterative refinement, LaRI achieves complete scene reconstruction in one feed-forward pass, enabling efficient and view-aligned geometric reasoning to underpin both object-level and scene-level tasks. We further propose to predict the ray stopping index, which identifies valid intersecting pixels and layers from LaRI's output. To better underpin and evaluate this task, we build an annotation pipeline using rendering engines, construct annotations for five public datasets, including synthetic and real-world data covering 3D objects and scenes. As a generic method, LaRI's performance is validated in object-level and scene-level reconstruction tasks.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 86 of its 108 references that are in the map. First posted on arXiv 25 Apr 2025.

Builds on

86 of 108 references.

References · 86

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2023Segment Anythingcited by 8,234
  5. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  6. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  7. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  8. 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
  9. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  10. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
  11. 2022Video Diffusion Modelscited by 2,305
  12. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
38 more
  1. 2021Vision Transformers for Dense Predictioncited by 1,803
  2. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  3. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  4. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,540
  5. 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
  6. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
  7. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,489
  8. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,420
  9. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,360
  10. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
  11. 2024Grounding Image Matching in 3D with MASt3Rcited by 983
  12. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 979
  13. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 849
  14. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 784
  15. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 770
  16. 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 764
  17. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 739
  18. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 657
  19. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 612
  20. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 588
  21. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 560
  22. 2025Continuous 3D Perception Model with Persistent Statecited by 548
  23. 2023Zero123++: a Single Image to Consistent Multi-view Diffusion Base Modelcited by 521
  24. 2024MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motioncited by 442
  25. 2024InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Modelscited by 433
  26. 2023Tri-Perspective View for Vision-Based 3D Semantic Occupancy Predictioncited by 409
  27. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 404
  28. 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 395
  29. 20203D-FRONT: 3D Furnished Rooms with layOuts and semaNTicscited by 380
  30. 2023Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Imagecited by 365
  31. 2023Splatter Image: Ultra-Fast Single-View 3D Reconstructioncited by 364
  32. 2024SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusioncited by 364
  33. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 363
  34. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 342
  35. 2019DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstructioncited by 333
  36. 2023SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Drivingcited by 316
  37. 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generationcited by 301
  38. 2024MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervisioncited by 299

50 most cited of 86 All 86 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

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

8 papers.

  1. 2025AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backendcited by 20
  2. 2026Pixal3D: Pixel-Aligned 3D Generation from Imagescited by 14
  3. 2026NOVA3R: Non-pixel-aligned Visual Transformer for Amodal 3D Reconstructioncited by 7
  4. 2025RaySt3R: Predicting Novel Depth Maps for Zero-Shot Object Completioncited by 5
  5. 2026World Tracing: Generative Pixel-Aligned Geometry Beyond the Visiblecited by 5
  6. 2025Room Envelopes: A Synthetic Dataset for Indoor Layout Reconstruction from Imagescited by 0
  7. 2026VolFill: Single-View Amodal 3D Scene Reconstruction with Volumetric Flow Matchingcited by 0
  8. 2026Building Rome from a Single Imagecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Reg3D: Reconstructive Geometry Instruction Tuning for 3D Scene Understanding
  2. 2024Boosting Self-Supervision for Single-View Scene Completion via Knowledge Distillation
  3. 2026SceneBench: A Hierarchical Benchmark for Vision-Language Understanding of 3D Scenes
  4. 2026RouteBridge: Reliability-Routed Bidirectional Distillation Between Neural Radiance Fields and 3D Gaussian Splatting
  5. 20243DSRBench: A Comprehensive 3D Spatial Reasoning Benchmark
  6. 2026Synthesizing Multimodal Geometry Datasets from Scratch and Enabling Visual Alignment via Plotting Code
  7. 2026MetaReason: Precise Interleaved Multimodal Reasoning via Editing Meta Information for Solving Geometry Problems
  8. 2026Make Geometry Matter for Spatial Reasoning