Research map / 3D vision / 3D generation
Sketch2Model: View-Aware 3D Modeling From Single Free-Hand Sketches
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Condition mesh generation on the viewpoint, using the predicted viewpoint | Sketch2Model · ShapeNet-Synthetic test | voxel IoU: 0.582 -> 0.584 | Helped |
| Condition mesh generation on the ground-truth viewpoint | Sketch2Model · ShapeNet-Synthetic test | Chamfer Distance: 1.551 -> 1.368 | Helped |
| Use predicted viewpoint in the view-aware generator | Sketch2Model · ShapeNet-Sketch | 2D silhouette IoU: 0.716 -> 0.745 | Helped |
| Add feature-space domain adaptation (ablation) | Sketch2Model · ShapeNet-Sketch (7 classes) | voxel IoU: 0.470 -> 0.475; 0.483 -> 0.489 | Helped |
| Add random view reinforced training (ablation) | Sketch2Model · ShapeNet-Synthetic test | voxel IoU: 0.516 (0.569) -> 0.566 (0.536) | Mixed |
| Add a shape discriminator alongside random view reinforced training (ablation) | Sketch2Model · ShapeNet-Synthetic test | voxel IoU: 0.566 (0.536) -> 0.580 (0.565) | Helped |
| Add multi-scale progressive training to RVR and SD (ablation) | Sketch2Model · ShapeNet-Synthetic test | voxel IoU: 0.580 (0.565) -> 0.601 (0.584) | Helped |
| Use CycleGAN-generated fake sketches instead of the reported adaptation approach (ablation) | Sketch2Model · ShapeNet-Sketch | voxel IoU | No clear effect |
Closest papers by meaning
- Diff3DS: Generating View-Consistent 3D Sketch via Differentiable Curve Rendering (ICLR 2025 · similarity 0.88)
- Rapid 3D Model Generation with Intuitive 3D Input (CVPR 2024 · similarity 0.87)
- ARMesh: Autoregressive Mesh Generation via Next-Level-of-Detail Prediction (NeurIPS 2025 · similarity 0.85)
- MeshArt: Generating Articulated Meshes with Structure-Guided Transformers (CVPR 2025 · similarity 0.85)
- Sculpt3D: Multi-View Consistent Text-to-3D Generation with Sparse 3D Prior (CVPR 2024 · similarity 0.85)
- Cue3D: Quantifying the Role of Image Cues in Single-Image 3D Generation (NeurIPS 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.