Research map / 3D vision / 3D generation
ReliefSAM: A Geometry-Augmented Multi-Prior Adapter for Bas-Relief Segmentation
YIHANG CHEN, Xiang Lyu, Rui Xu, Jiao PAN, Fadjar Thufail, Brahmantara Brahmantara, JIAQING LIU, Satoshi Tanaka, Liang Li
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 prior alone to RGB-only SAM-Adapter (ablation) | SAM-Adapter · Bas-relief human figure segmentation (test) | IoU (%): 91.25 -> 89.97 | Hurt |
| add edge prior alone to RGB-only SAM-Adapter (ablation) | SAM-Adapter · Bas-relief human figure segmentation (test) | IoU (%): 91.25 -> 90.52 | Hurt |
| add both depth and edge priors to RGB-only SAM-Adapter (ablation) | SAM-Adapter · Bas-relief human figure segmentation (test) | IoU (%): 91.25 -> 91.78 | Improved |
| add both depth and edge priors to RGB-only SAM-Adapter (ablation) | SAM-Adapter · Bas-relief human figure segmentation (test) | Dice (%): 95.37 -> 95.65 | Improved |
| add depth prior alone (ablation) | SAM-Adapter · Bas-relief human figure segmentation (test) | precision vs recall: precision 94.50 -> 95.37, recall 96.31 -> 93.89 | Mixed |
| add edge prior alone (ablation) | SAM-Adapter · Bas-relief human figure segmentation (test) | precision vs recall: precision 94.50 -> 92.65, recall 96.31 -> 97.43 | Mixed |
| use adapter-based injection with frozen encoder instead of decoder-only fine-tuning | SAM ViT-B · Bas-relief human figure segmentation (test) | IoU (%): 83.82 -> 91.25 | Improved |
| ReliefSAM versus decoder-only fine-tuning | SAM ViT-B · Bas-relief human figure segmentation (test) | IoU and Dice: +7.96 IoU, +4.70 Dice | Improved |
Closest papers by meaning
- Large Spatial Model: End-to-end Unposed Images to Semantic 3D (NeurIPS 2024 · similarity 0.85)
- DepthMaster: Unified Monocular Depth Estimation for Perspective and Panoramic Images (NeurIPS 2026 · similarity 0.84)
- SemAlign3D: Semantic Correspondence between RGB-Images through Aligning 3D Object-Class Representations (CVPR 2025 · similarity 0.83)
- Feat2GS: Probing Visual Foundation Models with Gaussian Splatting (CVPR 2025 · similarity 0.83)
- SD-MVS: Segmentation-Driven Deformation Multi-View Stereo with Spherical Refinement and EM Optimization (AAAI 2024 · similarity 0.83)
- Geometry-Guided Semantic Reconstruction for 3D Instance Segmentation (NeurIPS 2026 · 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.
