Datasets › Hypersim

Hypersim

Introduced by Mike Roberts et al. in Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding archive 2025-07-28

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)PaperCode
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.

DateSamples 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

Custom

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