Research map / 3D vision / 3D generation
Multi-View Silhouette and Depth Decomposition for High Resolution 3D Object Representation
Read the paperCheck 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 |
|---|---|---|---|
| Use six-view MVD super-resolution rather than nearest-neighbor upsampling | 32³ ShapeNet objects · ShapeNet Car, Chair, Plane at 256³ | IoU: Car: 73.2 -> 89.9; Chair: 54.9 -> 68.5; Plane: 39.9 -> 71.1 | Helped |
| Use MVD instead of HSP for RGB-image reconstruction | Data_HSP · Car, Chair, Plane at 256³ | IoU: Car: 70.1 -> 72.7; Chair: 37.8 -> 40.1; Plane: 56.1 -> 56.4 | Helped |
| Use MVD instead of OGN for RGB-image reconstruction | Data_3D-R2N2 · Car at 256³ | IoU: 78.2 -> 80.7 | Helped |
| Use MVD rather than Pixel2Mesh for surface reconstruction | Data_3D-R2N2 · 13 ShapeNet classes, mean | F1: 59.72 -> 66.39 | Helped |
| Add the silhouette network to depth variation prediction (ablation) | MVD super-resolution · ShapeNet Car, Chair, Plane at 256³ | IoU: Car: 80.6 -> 89.9; Chair: 58.5 -> 68.5; Plane: 50.5 -> 71.1 | Helped |
| Add the depth variation network to silhouette prediction (ablation) | MVD super-resolution · ShapeNet Car, Chair, Plane at 256³ | IoU: Car: 86.9 -> 89.9; Chair: 67.3 -> 68.5; Plane: 70.2 -> 71.1 | Helped |
Closest papers by meaning
- Synthesizing 3D Shapes via Modeling Multi-View Depth Maps and Silhouettes With Deep Generative Networks (CVPR 2017 · similarity 0.90)
- Slice3D: Multi-Slice Occlusion-Revealing Single View 3D Reconstruction (CVPR 2024 · similarity 0.86)
- Make-A-Shape: a Ten-Million-scale 3D Shape Model (ICML 2024 · similarity 0.86)
- What You See is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANs (CVPR 2024 · similarity 0.86)
- Decompositional Neural Scene Reconstruction with Generative Diffusion Prior (CVPR 2025 · similarity 0.86)
- Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention (NeurIPS 2025 · similarity 0.86)
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.