Datasets › Hypersim
Hypersim
For many fundamental scene understanding tasks, it is difficult or impossible to obtain per-pixel ground truth labels from real images. Hypersim is a photorealistic synthetic dataset for holistic indoor scene understanding. It contains 77,400 images of 461 indoor scenes with detailed per-pixel labels and corresponding ground truth geometry.
Source: https://github.com/apple/ml-hypersim Image Source: https://github.com/apple/ml-hypersim
Benchmarks archive 2025-07-28
All 4 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.
| First row (archive order) | Paper | Code | ||||
|---|---|---|---|---|---|---|
| Semantic Segmentation | Hypersim | EMSANet (2x ResNet-34 NBt1D) mIoU 49.74 | PanopticNDT: Efficient and Robust Panoptic Mapping | tui-nicr/emsanet +3 | 5 | Compare |
| 3D Semantic Segmentation | Hypersim | PanopticNDT (10cm) mIoU 45.43 | PanopticNDT: Efficient and Robust Panoptic Mapping | tui-nicr/emsanet +3 | 2 | Compare |
| Monocular Depth Estimation | Hypersim | ScaleDepth-NK Delta < 1.25 0.413 | ScaleDepth: Decomposing Metric Depth Estimation into... | RuijieZhu94/mmdepth | 1 | Compare |
| Panoptic Segmentation | Hypersim | EMSANet (2x ResNet-34 NBt1D) PQ 34.95 | PanopticNDT: Efficient and Robust Panoptic Mapping | tui-nicr/emsanet +3 | 1 | Compare |
Papers archive 2025-07-28
3 shown of 3 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 108. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.
| Date | Samples run Syntology | |||
|---|---|---|---|---|
| ScaleDepth: Decomposing Metric Depth Estimation into Scale Prediction and Relative Depth Estimation | 1 | 1 | 11 Jul 2024 | not harvested |
| PanopticNDT: Efficient and Robust Panoptic Mapping | 4 | 4 | 24 Sep 2023 | ran 0 of 12 samples (12 unverified) |
| MultiMAE: Multi-modal Multi-task Masked Autoencoders | 1 | 4 | 4 Apr 2022 | not harvested |
Dataset loaders archive 2025-07-28
1 loader as listed in the archive; links are outbound and not re-checked here.
Tasks archive 2025-07-28
License archive 2025-07-28
Modalities archive 2025-07-28
Languages archive 2025-07-28
No language tagged.
Variants archive 2025-07-28
- Hypersim
1 variant name, as the archive lists them.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections