Research map / 3D vision / 3D generation
Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding
Mike Roberts, Jason Ramapuram, Anurag Ranjan, Atulit Kumar, Miguel Angel Bautista, Nathan Paczan, Russ Webb, Joshua M. Susskind
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 |
|---|---|---|---|
| pre-train on Hypersim before fine-tuning on full NYUv2 | U-Net ResNet-34 · NYUv2 13-class segmentation | mIoU: 45.2 -> 51.6 | Improved |
| pre-train on Hypersim before fine-tuning on full NYUv2 | U-Net ResNet-34 · NYUv2 40-class segmentation | mIoU: 31.4 -> 36.4 | Improved |
| pre-train on Hypersim and fine-tune on only 25% of NYUv2 | U-Net ResNet-34 · NYUv2 13-class segmentation | mIoU: 45.2 -> 46.4 | Improved |
| pre-train on Hypersim and fine-tune on only 25% of NYUv2 | U-Net ResNet-34 · NYUv2 40-class segmentation | mIoU: 31.4 -> 29.0 | Hurt |
| pre-train on Hypersim and fine-tune on only 50% of NYUv2 | U-Net ResNet-34 · NYUv2 40-class segmentation | mIoU: 31.4 -> 32.7 | Improved |
| pre-train on Hypersim and fine-tune on 50% rather than 25% of NYUv2 (ablation) | U-Net ResNet-34 · NYUv2 40-class segmentation | mIoU: 29.0 -> 32.7 | Improved |
| pre-train on Hypersim and fine-tune on 100% rather than 50% of NYUv2 (ablation) | U-Net ResNet-34 · NYUv2 13-class segmentation | mIoU: 49.1 -> 51.6 | Improved |
| pre-train Mesh R-CNN on Hypersim before fine-tuning on Pix3D | Mesh R-CNN · Pix3D S2 test | AP mesh: 28.8 -> 29.6 | Improved |
| pre-train Mesh R-CNN on Hypersim before fine-tuning on Pix3D | Mesh R-CNN · Pix3D S2 test | AP mask: 63.9 -> 64.6 | Improved |
| pre-train Mesh R-CNN on Hypersim before fine-tuning on Pix3D | Mesh R-CNN · Pix3D S2 test | AP box: 72.2 -> 72.7 | Improved |
Closest papers by meaning
- OpenRooms: An Open Framework for Photorealistic Indoor Scene Datasets (CVPR 2021 · similarity 0.91)
- Large Spatial Model: End-to-end Unposed Images to Semantic 3D (NeurIPS 2024 · similarity 0.88)
- SceneFun3D: Fine-Grained Functionality and Affordance Understanding in 3D Scenes (CVPR 2024 · similarity 0.87)
- SceneSplat++: A Large Dataset and Comprehensive Benchmark for Language Gaussian Splatting (NeurIPS 2025 · similarity 0.87)
- InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts (NeurIPS 2025 · similarity 0.87)
- Intrinsic Image Diffusion for Indoor Single-view Material Estimation (CVPR 2024 · 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.
