Research map / 3D vision / Depth and stereo
Dionysus: Recovering Scene Structures by Dividing Into Semantic Pieces
Likang Wang, Lei Chen
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 Dionysus instead of DeepVideoMVS (Fusion) | ScanNet depth reconstruction · ScanNet test | Abs Diff: 0.1182 -> 0.1069 | Improved |
| use Dionysus instead of DeepVideoMVS (Fusion) | ScanNet depth reconstruction · ScanNet test | Time: 30 ms -> 30 ms | No clear effect |
| add the semantic head for semantic-based depth selection (ablation) | Dionysus · ScanNet test | Abs Diff: 0.1225 -> 0.1069 | Improved |
| add the semantic head for semantic-based depth selection (ablation) | Dionysus · ScanNet test | Abs Rel: 0.0633 -> 0.0524 | Improved |
| add the semantic head for semantic-based depth selection (ablation) | Dionysus · ScanNet test | Sq Rel: 0.0192 -> 0.0161 | Improved |
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.
- DPSNet — DPSNet: End-to-end Deep Plane Sweep Stereo (ICLR 2019) · better on 6 of 6 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
- PE3R: Perception-Efficient 3D Reconstruction (CVPR 2026 · similarity 0.88)
- Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoning (CVPR 2024 · similarity 0.88)
- SceneCode: Monocular Dense Semantic Reconstruction Using Learned Encoded Scene Representations (CVPR 2019 · similarity 0.87)
- MESC-3D:Mining Effective Semantic Cues for 3D Reconstruction from a Single Image (CVPR 2025 · similarity 0.87)
- Large Spatial Model: End-to-end Unposed Images to Semantic 3D (NeurIPS 2024 · similarity 0.86)
- RefineAny3D: Depth Refinement as Semantic Alignment for Monocular 3D Detection (NeurIPS 2026 · 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.
