Research map / 3D vision / Depth and stereo
SliceNet: Deep Dense Depth Estimation From a Single Indoor Panorama Using a Slice-Based Representation
Giovanni Pintore, Marco Agus, Eva Almansa, Jens Schneider, Enrico Gobbetti
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 the slice-based architecture for depth prediction | SliceNet · Stanford2D3D | MRE: 0.1209 -> 0.0744 | Improved |
| use the slice-based architecture for depth prediction | SliceNet · Matterport3D | MRE: 0.2048 -> 0.1764 | Improved |
| use the slice-based architecture for depth prediction | SliceNet · 360D | MRE: 0.0615 -> 0.0467 | Improved |
| use the last 4 ResNet-50 layers instead of only the last layer (ablation) | SliceNet slicing encoder · Structured3D | δ1: 0.6845 -> 0.7045 | Improved |
| add LSTM refinement to the sliced bottleneck (ablation) | SliceNet · Structured3D | δ1: 0.7045 -> 0.9492 | Improved |
| add the gradient component to the loss (ablation) | SliceNet · Structured3D | MAE: 0.1223 -> 0.1180 | Improved |
| add the gradient component to the loss (ablation) | SliceNet · Structured3D | MRE: 0.0147 -> 0.0147 | No clear effect |
| introduce camera inclination errors of ±2° (ablation) | SliceNet · Matterport3D | δ1: 0.8716 -> 0.7256 | Hurt |
| introduce camera inclination errors of ±5° (ablation) | SliceNet · Matterport3D | δ1: 0.8716 -> 0.6879 | Hurt |
| introduce camera inclination errors of ±2° (ablation) | SliceNet · Structured3D | δ1: 0.9085 -> 0.8776 | Hurt |
| introduce camera inclination errors of ±5° (ablation) | SliceNet · Structured3D | δ1: 0.9085 -> 0.8527 | Hurt |
Later papers that compared with this method
2 later accepted papers report SliceNet as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- ACDNet: Adaptively Combined Dilated Convolution for Monocular Panorama Depth Estimation (AAAI 2022 · better on 2 of 3 shared results)
- PanoFormer: Panorama Transformer for Indoor 360° Depth Estimation (ECCV 2022 · better on 2 of 2 shared results)
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
- Depth Estimation From Indoor Panoramas With Neural Scene Representation (CVPR 2023 · similarity 0.89)
- PanoFormer: Panorama Transformer for Indoor 360° Depth Estimation (ECCV 2022 · similarity 0.89)
- Toward Practical Monocular Indoor Depth Estimation (CVPR 2022 · similarity 0.88)
- Indoor Panorama Planar 3D Reconstruction via Divide and Conquer (CVPR 2021 · similarity 0.88)
- Guiding Monocular Depth Estimation Using Depth-Attention Volume (ECCV 2020 · similarity 0.88)
- Joint 3D Layout and Depth Prediction from a Single Indoor Panorama Image (ECCV 2020 · 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.
