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

Homepage

Benchmarks

Add a new result Link an existing benchmark

Task	Dataset Variant	Best Model
Semantic Segmentation	Hypersim	EMSANet
3D Semantic Segmentation	Hypersim	PanopticNDT
Panoptic Segmentation	Hypersim	EMSANet
3D Panoptic Segmentation	Hypersim	PanopticNDT
Monocular Depth Estimation	Hypersim	ScaleDepth-NK