Research map / 3D vision / 3D generation
Monocular Occupancy Prediction for Scalable Indoor Scenes
Hongxiao Yu, Yuqi Wang, Yuntao Chen, Zhaoxiang Zhang
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 |
|---|---|---|---|
| replace MonoScene with ISO (depth branch + D-FLoSP) on NYUv2 | MonoScene · NYUv2 | mIoU: 26.94 -> 31.25 | Improved |
| add voxel-depth fusion to baseline (ablation) | ISO · NYUv2 | mIoU: 27.13 -> 31.25 | Improved |
| add BEV-depth fusion to baseline (ablation) | ISO · NYUv2 | mIoU: 27.13 -> 27.14 | No clear effect |
| add voxel-depth fusion to baseline (ablation) | ISO · Occ-ScanNet-mini | mIoU: 38.95 -> 39.08 | No clear effect |
| add BEV-depth fusion to baseline (ablation) | ISO · Occ-ScanNet-mini | mIoU: 38.95 -> 38.48 | Hurt |
| fine-tune (learn) the pre-trained depth module (ablation) | ISO with Depth-Anything · NYUv2 | mIoU: 29.57 -> 31.02 | Improved |
| use Depth-Anything instead of ZoeDepth (ablation) | ISO · NYUv2 | mIoU: 29.40 -> 31.02 | Improved |
| add multi-scale depth distribution weighting (ablation) | ISO with learned Depth-Anything · NYUv2 | mIoU: 31.25 -> 31.02 | Hurt |
| add multi-scale depth to frozen Depth-Anything (ablation) | ISO · NYUv2 | mIoU: 29.28 -> 29.57 | Improved |
| train on 100% instead of 10% of Occ-ScanNet (ablation) | ISO · Occ-ScanNet | mIoU: 9.57 -> 28.71 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- MonoScene — MonoScene: Monocular 3D Semantic Scene Completion (CVPR 2022) · better on 4 of 4 shared results
- NDC-Scene — NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Space (ICCV 2023) · 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
- AdaOcc: Adaptive 3D Occupancy Prediction for Embodied Tasks (NeurIPS 2026 · similarity 0.89)
- Learning Occupancy for Monocular 3D Object Detection (CVPR 2024 · similarity 0.89)
- Cam4DOcc: Benchmark for Camera-Only 4D Occupancy Forecasting in Autonomous Driving Applications (CVPR 2024 · similarity 0.88)
- ViPOcc: Leveraging Visual Priors from Vision Foundation Models for Single-View 3D Occupancy Prediction (AAAI 2025 · similarity 0.88)
- Exploiting Continuous Motion Clues for Vision-Based Occupancy Prediction (AAAI 2025 · similarity 0.88)
- ODG: Occupancy Prediction Using Dual Gaussians (NeurIPS 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.
