Research map / 3D vision / Depth and stereo
Global Transport for Fluid Reconstruction With Learned Self-Supervision
Erik Franz, Barbara Solenthaler, Nils Thuerey
Check 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 |
|---|---|---|---|
| replace per-frame density variables with one initial density advected across the sequence (ablation) | fluid reconstruction · Synthetic multi-view | transport RMSE: 0.0291 -> 1.4e-7 | Improved |
| add coupled optimization with transport losses (ablation) | Forward reconstruction · Synthetic multi-view | transport RMSE: 0.1222 -> 0.0291 | Improved |
| add multi-scale reconstruction to coupled optimization (ablation) | C · Synthetic multi-view | transport RMSE: 0.0291 -> 0.0505 | Hurt |
| add the learned discriminator for unseen views (ablation) | Glob-Trans · Real single-view, five random views | FID: 151.2 -> 140.3 | Improved |
| add a temporal discriminator (ablation) | Full · Real single-view, five random views | FID: 140.3 -> 147.3 | Hurt |
| add forward temporal coupling (ablation) | Single-frame reconstruction · Synthetic multi-view | transport RMSE: 0.1352 -> 0.1222 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- TomoFluid — TomoFluid: Reconstructing Dynamic Fluid From Sparse View Videos (CVPR 2020) · better on 0 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Flow Field Reconstruction with Sensor Placement Policy Learning (NeurIPS 2025 · similarity 0.86)
- PEINR: A Physics-enhanced Implicit Neural Representation for High-Fidelity Flow Field Reconstruction (ICML 2025 · similarity 0.86)
- Flux4D: Flow-based Unsupervised 4D Reconstruction (NeurIPS 2025 · similarity 0.85)
- FluidNexus: 3D Fluid Reconstruction and Prediction from a Single Video (CVPR 2025 · similarity 0.85)
- Beckmann Transport Models: From Autonomous Flows to One-Step Maps (NeurIPS 2026 · similarity 0.85)
- Light Transport-aware Diffusion Posterior Sampling for Single-View Reconstruction of 3D Volumes (CVPR 2025 · similarity 0.84)
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.
