mlsanityData to 7 Oct 2026

Explaining Human Preferences via Metrics for Structured 3D Reconstruction

arXiv 2503.08208 ↗First posted 11 Mar 2025cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

"What cannot be measured cannot be improved" while likely never uttered by Lord Kelvin, summarizes effectively the driving force behind this work. This paper presents a detailed discussion of automated metrics for evaluating structured 3D reconstructions. Pitfalls of each metric are discussed, and an analysis through the lens of expert 3D modelers' preferences is presented. A set of systematic "unit tests" are proposed to empirically verify desirable properties, and context aware recommendations regarding which metric to use depending on application are provided. Finally, a learned metric distilled from human expert judgments is proposed and analyzed. The source code is available at https://github.com/s23dr/wireframe-metrics-iccv2025

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 18 of its 37 references that are in the map. First posted on arXiv 11 Mar 2025.

Builds on

18 of 37 references.

References · 18

  1. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  2. 2024Qwen2.5-Coder Technical Reportcited by 1,151
  3. 2020Image Matching across Wide Baselines: From Paper to Practicecited by 224
  4. 2018Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarkingcited by 189
  5. 2015MOTChallenge 2015: Towards a Benchmark for Multi-Target Trackingcited by 133
  6. 2015A Novel Performance Evaluation Methodology for Single-Target Trackerscited by 113
  7. 2024SceneScript: Reconstructing Scenes With An Autoregressive Structured Language Modelcited by 95
  8. 2024Scene Coordinate Reconstruction: Posing of Image Collections via Incremental Learning of a Relocalizercited by 73
  9. 2019End-to-End Wireframe Parsingcited by 72
  10. 2024BOP Challenge 2023 on Detection, Segmentation and Pose Estimation of Seen and Unseen Rigid Objectscited by 60
  11. 2021PC2WF: 3D Wireframe Reconstruction from Raw Point Cloudscited by 33
  12. 2021HEAT: Holistic Edge Attention Transformer for Structured Reconstructioncited by 29
6 more
  1. 2023Building3D: An Urban-Scale Dataset and Benchmarks for Learning Roof Structures from Point Cloudscited by 24
  2. 2023SepicNet: Sharp Edges Recovery by Parametric Inference of Curves in 3D Shapescited by 13
  3. 2022HoW-3D: Holistic 3D Wireframe Perception from a Single Imagecited by 12
  4. 2022Learning to Construct 3D Building Wireframes from 3D Line Cloudscited by 9
  5. 2023PBWR: Parametric Building Wireframe Reconstruction from Aerial LiDAR Point Cloudscited by 5
  6. 2024APC2Mesh: Bridging the gap from occluded building faccades to full 3D modelscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Can These Views Be One Scene? Evaluating Multiview 3D Consistency when 3D Foundation Models Hallucinatecited by 0
  2. 2026Edge Prediction for Roof Wireframe Reconstruction with Transformerscited by 0
  3. 2026S23DR 2026 Winning Solutioncited by 0