Research map / 3D vision / 3D generation
NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Space
Jiawei Yao, Chuming Li, Keqiang Sun, Yingjie Cai, Hao Li, Wanli Ouyang, Hongsheng Li
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 |
|---|---|---|---|
| extend 2D features to NDC space with dual decoder instead of FLoSP lifting with heavy 3D UNet (ablation) | NDC-Scene · NYUv2 | mIoU: 27.69 -> 29.03 | Improved |
| extend 2D features to NDC space with dual decoder instead of FLoSP lifting (ablation) | NDC-Scene · SemanticKITTI val | IoU: 37.15 -> 37.24 | No clear effect |
| put 3D computation in NDC space instead of camera space (ablation) | NDC-Scene · NYUv2 | mIoU: 28.10 -> 29.03 | Improved |
| put 3D computation in NDC space instead of camera space (ablation) | NDC-Scene · SemanticKITTI val | IoU: 37.20 -> 37.24 | No clear effect |
| use depth adaptive attention instead of naive feature addition (ablation) | NDC-Scene · NYUv2 | mIoU: 28.22 -> 29.03 | Improved |
| use depth adaptive attention instead of naive feature addition (ablation) | NDC-Scene · SemanticKITTI val | mIoU: 11.22 -> 12.70 | Improved |
| use NDC-Scene instead of MonoScene on NYUv2 | monocular SSC · NYUv2 test | mIoU: 26.94 -> 29.03 | Improved |
| use NDC-Scene instead of MonoScene on SemanticKITTI | monocular SSC · SemanticKITTI val | mIoU: 11.50 -> 12.70 | Improved |
| randomly rotate target space by up to 15 degrees (pose ambiguity test) (ablation) | NDC-Scene vs MonoScene · NYUv2 test | mIoU: NDC-Scene 29.03 -> 22.39; MonoScene 26.94 -> 16.71 | Hurt |
Later papers that compared with this method
5 later accepted papers report NDC-Scene as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.
- AdaSFormer: Adaptive Serialized Transformers for Monocular Semantic Scene Completion from Indoor Environments (CVPR 2026 · better on 1 of 1 shared result)
- Monocular Semantic Scene Completion via Masked Recurrent Networks (ICCV 2025 · better on 4 of 4 shared results)
- Global-Aware Monocular Semantic Scene Completion with State Space Models (ICCV 2025 · better on 2 of 2 shared results)
- OccScene: Semantic Occupancy-based Cross-task Mutual Learning for 3D Scene Generation (TPAMI 2025 · better on 1 of 1 shared result)
- Monocular Occupancy Prediction for Scalable Indoor Scenes (ECCV 2024 · better on 2 of 2 shared results)
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.
- MonoScene — MonoScene: Monocular 3D Semantic Scene Completion (CVPR 2022) · better on 5 of 5 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
- Global-Aware Monocular Semantic Scene Completion with State Space Models (ICCV 2025 · similarity 0.91)
- MonoScene: Monocular 3D Semantic Scene Completion (CVPR 2022 · similarity 0.91)
- Bi-SSC: Geometric-Semantic Bidirectional Fusion for Camera-based 3D Semantic Scene Completion (CVPR 2024 · similarity 0.88)
- H2GFormer: Horizontal-to-Global Voxel Transformer for 3D Semantic Scene Completion (AAAI 2024 · similarity 0.88)
- Context and Geometry Aware Voxel Transformer for Semantic Scene Completion (NeurIPS 2024 · similarity 0.87)
- Memory-Augmented Re-Completion for 3D Semantic Scene Completion (AAAI 2025 · similarity 0.87)
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.
