AI Paper Atlas

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

ICCV 2021 · 3D vision › 3D generation · approach: Generative indoor scene synthesis · 446 citations (OpenAlex)

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 changedWhereMeasuredEffect
pre-train on Hypersim before fine-tuning on full NYUv2U-Net ResNet-34 · NYUv2 13-class segmentationmIoU: 45.2 -> 51.6Improved
pre-train on Hypersim before fine-tuning on full NYUv2U-Net ResNet-34 · NYUv2 40-class segmentationmIoU: 31.4 -> 36.4Improved
pre-train on Hypersim and fine-tune on only 25% of NYUv2U-Net ResNet-34 · NYUv2 13-class segmentationmIoU: 45.2 -> 46.4Improved
pre-train on Hypersim and fine-tune on only 25% of NYUv2U-Net ResNet-34 · NYUv2 40-class segmentationmIoU: 31.4 -> 29.0Hurt
pre-train on Hypersim and fine-tune on only 50% of NYUv2U-Net ResNet-34 · NYUv2 40-class segmentationmIoU: 31.4 -> 32.7Improved
pre-train on Hypersim and fine-tune on 50% rather than 25% of NYUv2 (ablation)U-Net ResNet-34 · NYUv2 40-class segmentationmIoU: 29.0 -> 32.7Improved
pre-train on Hypersim and fine-tune on 100% rather than 50% of NYUv2 (ablation)U-Net ResNet-34 · NYUv2 13-class segmentationmIoU: 49.1 -> 51.6Improved
pre-train Mesh R-CNN on Hypersim before fine-tuning on Pix3DMesh R-CNN · Pix3D S2 testAP mesh: 28.8 -> 29.6Improved
pre-train Mesh R-CNN on Hypersim before fine-tuning on Pix3DMesh R-CNN · Pix3D S2 testAP mask: 63.9 -> 64.6Improved
pre-train Mesh R-CNN on Hypersim before fine-tuning on Pix3DMesh R-CNN · Pix3D S2 testAP box: 72.2 -> 72.7Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy