Research map / 3D vision / 3D generation
SeisMark: A Large-Scale Open Benchmark for Robust 3D Seismic Fault Detection
Min Jun Park, Joseph Stitt, Robert Graham Clapp, Ilan Naiman, Artem Goncharuk, Kevin F. Smith
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| evaluate on high-intensity styled texture instead of Clean | FaultSeg3D (V1) · SeisMark, recall at T=1 | recall: 0.804 -> 0.305 (Aus-High) | Hurt |
| train with real-data labeled slices (Fault-Net) versus synthetic-only detectors | Fault-Net · SeisMark styled variants | IoU: 0.384 vs 0.237 (RGF, Australia Low) | Improved |
| curriculum of more realistic noise (V2 vs V1) | FaultSeg3D+ · SeisMark styled variants | recall at T=1: 0.305 -> 0.388 (Aus-High) | Improved |
| diffusion styling at low intensity versus Clean | FaultSeg3D+ · SeisMark, precision at T=1 | precision: 0.676 -> 0.902 (F3-Low) | Improved |
| diffusion styling at low intensity versus Clean | Fault-Net · SeisMark, precision at T=1 | precision: 0.805 -> 0.868 (F3-Low) | Improved |
| raise texture intensity from Low to High | North Sea style · structural fidelity | SSIM: 0.92 -> 0.88 | Hurt |
| raise texture intensity from Low to High | Australia style · structural fidelity | GMC: 0.93 -> 0.90 | Hurt |
| raise texture intensity from Low to High | RGF · SeisMark | IoU: 0.238 -> 0.151 (North Sea) | Hurt |
| evaluate on Clean data only | FaultSeg3D, FaultSeg3D+, Fault-Net · SeisMark Clean | recall at T=1: Recall ≈0.79–0.81 | No clear effect |
| strict tolerance T=0 versus T>=1 | all detectors · SeisMark | F1: 0.415 -> 0.549 (V1 Clean, T=0 to T=1) | Hurt |
Closest papers by meaning
- Cracks in the Foundation: A Civil Infrastructure Dataset to Challenge Vision Foundation Models (NeurIPS 2026 · similarity 0.81)
- Broadband Ground Motion Synthesis by Diffusion Model with Minimal Condition (ICML 2025 · similarity 0.81)
- SeafloorAI: A Large-scale Vision-Language Dataset for Seafloor Geological Survey (NeurIPS 2024 · similarity 0.81)
- A Unified Framework for Forward and Inverse Problems in Subsurface Imaging using Latent Space Translations (ICLR 2025 · similarity 0.81)
- Towards Automated Petrography (NeurIPS 2025 · similarity 0.80)
- PEACE: Empowering Geologic Map Holistic Understanding with MLLMs (CVPR 2025 · similarity 0.80)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
