Research map / 3D vision / 3D generation
ForkNet: Multi-Branch Volumetric Semantic Completion From a Single Depth Image
Yida Wang, David Joseph Tan, Nassir Navab, Federico Tombari
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 SDF-semantic consistency loss with latent-sampled pairs (ablation) | ForkNet · SUNCG semantic scene completion | average IoU (%): 58.2 -> 63.4 | Improved |
| add geometric completion branch (ablation) | ForkNet · SUNCG semantic scene completion | average IoU (%): 62.3 -> 63.4 | Improved |
| add SDF-semantic consistency loss with latent-sampled pairs (ablation) | ForkNet · NYU semantic scene completion | average IoU (%): 34.7 -> 37.1 | Improved |
| add geometric completion branch (ablation) | ForkNet · NYU semantic scene completion | average IoU (%): 36.5 -> 37.1 | Improved |
| add SDF-semantic consistency loss with latent-sampled pairs (ablation) | ForkNet · SUNCG scene completion | IoU (%): 82.0 -> 86.9 | Improved |
| add geometric completion branch (ablation) | ForkNet · SUNCG scene completion | IoU (%): 82.3 -> 86.9 | Improved |
| add SDF-semantic consistency loss with latent-sampled pairs (ablation) | ForkNet · NYU scene completion | IoU (%): 61.1 -> 63.4 | Improved |
| add geometric completion branch (ablation) | ForkNet · NYU scene completion | IoU (%): 62.6 -> 63.4 | Improved |
| add SDF-semantic consistency loss with latent-sampled pairs (ablation) | ForkNet · ShapeNet object completion (single category) | average IoU (%): 80.4 -> 84.1 | Improved |
| add SDF-semantic consistency loss with latent-sampled pairs (ablation) | ForkNet · 3D-RecGAN real-world object completion | average IoU (%): 20.3 -> 23.8 | Improved |
| ForkNet vs VVNet on SUNCG full-volume semantic completion | ForkNet · SUNCG semantic scene completion | average IoU (%): 66.7 vs 63.4 | Hurt |
| ForkNet vs SaTNet on NYU semantic completion | ForkNet · NYU semantic scene completion | average IoU (%): 34.4 -> 37.1 | Improved |
Closest papers by meaning
- Semantic Scene Completion From a Single Depth Image (CVPR 2017 · similarity 0.93)
- See and Think: Disentangling Semantic Scene Completion (NeurIPS 2018 · similarity 0.90)
- Point Cloud Semantic Scene Completion from RGB-D Images (AAAI 2021 · similarity 0.90)
- SDFormer: Vision-based 3D Semantic Scene Completion via SAM-assisted Dual-channel Voxel Transformer (ICCV 2025 · similarity 0.90)
- Voxel Proposal Network via Multi-Frame Knowledge Distillation for Semantic Scene Completion (NeurIPS 2024 · similarity 0.89)
- Context and Geometry Aware Voxel Transformer for Semantic Scene Completion (NeurIPS 2024 · similarity 0.89)
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.
