Research map / 3D vision / Depth and stereo
Guardians of the Hair: Rescuing Soft Boundaries in Depth, Stereo, and Novel Views
Xiang Zhang, Yang Zhang, Lukas Mehl, Markus Gross, Christopher Schroers
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 |
|---|---|---|---|
| add depth fixer to Depth Anything V2 | Depth Anything V2 · AIM-500 | ER (%): 6.50 -> 13.08 | Improved |
| add depth fixer to Depth Pro | Depth Pro · AIM-500 | DBE acc: 3.80 -> 2.30 | Improved |
| add depth fixer to UniDepthV2 | UniDepthV2 · P3M-10K | EP (%): 20.82 -> 37.71 | Improved |
| add depth fixer | Depth Anything V2 · NYUv2 zero-shot | AbsRel: 4.27 -> 4.27 | No clear effect |
| add depth fixer | UniDepthV2 · DIODE | AbsRel: 23.94 -> 23.87 | No clear effect |
| add depth fixer before warping (ablation) | warped DAv2 baseline · Marvel-10K stereo image conversion | SIoU: 0.3097 -> 0.3118 | Improved |
| add scene painter (ablation) | warping + depth fixer · Marvel-10K stereo image conversion | LPIPS: 0.1458 -> 0.1246 | Improved |
| add scene painter (ablation) | warping + depth fixer · Marvel-10K stereo image conversion | PSNR: 36.28 -> 35.82 | Hurt |
| add color fuser (ablation) | depth fixer + scene painter · Marvel-10K stereo image conversion | PSNR: 35.82 -> 36.59 | Improved |
| add color fuser (ablation) | depth fixer + scene painter · Marvel-10K stereo image conversion | LPIPS: 0.1246 -> 0.0909 | Improved |
| use HairGuard instead of SplatDiff | SplatDiff · AIM-500 novel view synthesis | FID: 19.26 -> 18.82 | Improved |
| use HairGuard instead of SplatDiff | SplatDiff · P3M-10K novel view synthesis | CLIP-F: 99.09 -> 99.11 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Depth Pro — Depth Pro: Sharp Monocular Metric Depth in Less Than a Second (ICLR 2025) · better on 3 of 3 shared results
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
- MonoHair: High-Fidelity Hair Modeling from a Monocular Video (CVPR 2024 · similarity 0.87)
- $\alpha$Depth: Learning Single-Pass Soft Boundary Decomposition for Stereo Conversion (NeurIPS 2026 · similarity 0.86)
- DiffLocks: Generating 3D Hair from a Single Image using Diffusion Models (CVPR 2025 · similarity 0.84)
- Perm: A Parametric Representation for Multi-Style 3D Hair Modeling (ICLR 2025 · similarity 0.84)
- PatchFusion: An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimation (CVPR 2024 · similarity 0.83)
- Dr.Hair: Reconstructing Scalp-Connected Hair Strands without Pre-Training via Differentiable Rendering of Line Segments (CVPR 2024 · similarity 0.83)
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.
