TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Datasets/Hypersim

Hypersim

3d meshesImagesPoint cloudRGB-DCustom

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

10-shot image generation/mIoU10-shot image generation/mIoU (test)10-shot image generation/PQ10-shot image generation/PQ (test)3D/Delta < 1.253D/RMSE3D/absolute relative error3D Semantic Segmentation/mIoU3D Semantic Segmentation/mIoU (test)Depth Estimation/Delta < 1.25Depth Estimation/RMSEDepth Estimation/absolute relative errorPanoptic Segmentation/PQPanoptic Segmentation/PQ (test)Panoptic Segmentation/mIoUPanoptic Segmentation/mIoU (test)Semantic Segmentation/mIoUSemantic Segmentation/mIoU (test)Semantic Segmentation/PQSemantic Segmentation/PQ (test)

Statistics

Papers
108
Benchmarks
20

Links

Homepage

Tasks

10-shot image generation2D Object Detection3D3D Object Detection3D Panoptic Segmentation3D Pose Estimation3D Reconstruction3D Semantic Segmentation3D Shape Recognition3D Shape ReconstructionDepth EstimationInstance SegmentationIntrinsic Image DecompositionInverse RenderingMonocular Depth EstimationMulti-Task LearningPanoptic SegmentationSemantic SegmentationSingle-View 3D Reconstruction