Research map / 3D vision / 3D generation
Anisotropic Convolutional Networks for 3D Semantic Scene Completion
Jie Li, Kai Han, Peng Wang, Yu Liu, Xia Yuan
Check 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 |
|---|---|---|---|
| use voxel-wise anisotropic convolution with adaptive kernel selection | AIC-Net · NYUCAD | SSC average IoU: 42.8 -> 45.8 | Improved |
| use voxel-wise anisotropic convolution with adaptive kernel selection | AIC-Net · NYU | SSC average IoU: 32.9 -> 33.3 | Improved |
| use anisotropic convolution rather than fixed-receptive-field modeling | AIC-Net · NYU | scene completion IoU: 61.1 -> 59.2 | Hurt |
| use candidate kernels {3, 5, 7} instead of only kernel 7 (ablation) | AIC-Net · NYUCAD | SSC average IoU: 44.0 -> 45.8 | Improved |
| add candidate kernel 3 to the set {5, 7} (ablation) | AIC-Net · NYUCAD | SSC average IoU: 44.9 -> 45.8 | Improved |
| set all modulation factors to 1, removing adaptive kernel weighting (ablation) | AIC-Net · NYU | SSC average IoU: 33.3 -> 30.7 | Hurt |
| set all modulation factors to 1, removing adaptive kernel weighting (ablation) | AIC-Net · NYUCAD | SSC average IoU: 45.8 -> 42.5 | Hurt |
| replace DDR blocks with AIC modules (ablation) | DDRNet · NYUCAD | SSC-IoU: +1.6% | Improved |
| replace ASPP with an AIC module (ablation) | DDRNet · NYUCAD | SSC average IoU: 42.8 -> 43.4 | Improved |
| replace both DDR blocks and ASPP with AIC modules (ablation) | DDRNet · NYUCAD | SSC average IoU: 42.8 -> 45.2 | Improved |
| use one AIC module in feature fusion instead of two (ablation) | AIC-Net · NYUCAD | SSC-IoU: 45.8 -> 45.2 | Hurt |
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.
- DDRNet — DDRNet: Depth Map Denoising and Refinement for Consumer Depth Cameras Using Cascaded CNNs (ECCV 2018) · better on 1 of 1 shared result
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
- Anisotropic Convolutional Neural Networks for RGB-D based Semantic Scene Completion (TPAMI 2021 · similarity 0.97)
- Context and Geometry Aware Voxel Transformer for Semantic Scene Completion (NeurIPS 2024 · similarity 0.89)
- Unleashing Network Potentials for Semantic Scene Completion (CVPR 2024 · similarity 0.89)
- Voxel Proposal Network via Multi-Frame Knowledge Distillation for Semantic Scene Completion (NeurIPS 2024 · similarity 0.89)
- Memory-Augmented Re-Completion for 3D Semantic Scene Completion (AAAI 2025 · similarity 0.88)
- Three Cars Approaching within 100m! Enhancing Distant Geometry by Tri-Axis Voxel Scanning for Camera-based Semantic Scene Completion (CVPR 2025 · similarity 0.88)
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.
