Codesota · Benchmark · sun-rgb-dHome/Leaderboards/Vision & Documents/Document OCR/sun-rgb-d
Unknown

sun-rgb-d.

sun-rgb-d is a state-of-the-art machine learning benchmark indexed on Codesota. This page tracks published model results, top scores per metric, and the SOTA timeline for sun-rgb-d.

Paper ↗Leaderboard ↓
§ 01 · SOTA history

Year over year.

§ 02 · Leaderboard

Results by metric.

Found a wrong score or missing run?
Use row edits to send a sourced correction into moderation.
Add / edit result ↗Report issue ↗

Iou

Iou is the reported evaluation metric for sun-rgb-d. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Higher is better

Trust tiers for Iouverifiedpapervendorcommunityunverified
RankModelTrustScoreYearLinksFix
01PesRec
From abstract: "79.7% 3D IoU for the estimation of layout on the commonly-used SUN RGB-D datasets". Paper: PesRec — A parametric estimation method for indoor semantic scene reconstruction from a single image. JAG Vol.133, Sep 2024. DOI: 10.1016/j.jag.2024.104135. Evaluation protocol may differ from free-space voxel IoU used by IM3D/Total3D.
verified79.72024Source ↗Looks wrong?
02IM3D
From paper: Holistic 3D Scene Understanding from a Single Image with Implicit Representation
verified64.42021Paper ↗Code ↗Looks wrong?
03ImVoxelNet
From paper: ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection
verified59.32021Paper ↗Code ↗Looks wrong?
04Total3D joint
From paper: Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image
verified59.22020Paper ↗Code ↗Looks wrong?
05Total w/o. joint
From paper: Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image
verified57.62020Paper ↗Code ↗Looks wrong?
06Cooperative
From paper: Cooperative Holistic Scene Understanding: Unifying 3D Object, Layout, and Camera Pose Estimation
verified56.92018Paper ↗Code ↗Looks wrong?
07Holistic
From paper: Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image
verified54.92018Paper ↗Code ↗Looks wrong?
083DGP
From paper: Understanding Indoor Scenes Using 3D Geometric Phrases
verified19.22013Paper ↗Looks wrong?

Camera Pitch

Camera Pitch is the reported evaluation metric for sun-rgb-d. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Higher is better

Trust tiers for Camera Pitchverifiedpapervendorcommunityunverified
RankModelTrustScoreYearLinksFix
01Holistic
From paper: Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image
verified7.602018Paper ↗Code ↗Looks wrong?
02Total w/o. joint
From paper: Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image
verified3.682020Paper ↗Code ↗Looks wrong?
03Cooperative
From paper: Cooperative Holistic Scene Understanding: Unifying 3D Object, Layout, and Camera Pose Estimation
verified3.282018Paper ↗Code ↗Looks wrong?
04Total3D joint
From paper: Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image
verified3.152020Paper ↗Code ↗Looks wrong?
05IM3D
From paper: Holistic 3D Scene Understanding from a Single Image with Implicit Representation
verified2.982021Paper ↗Code ↗Looks wrong?
06ImVoxelNet
From paper: ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection
verified2.632021Paper ↗Code ↗Looks wrong?

Camera Roll

Camera Roll is the reported evaluation metric for sun-rgb-d. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Higher is better

Trust tiers for Camera Rollverifiedpapervendorcommunityunverified
RankModelTrustScoreYearLinksFix
01Holistic
From paper: Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image
verified3.122018Paper ↗Code ↗Looks wrong?
02Total w/o. joint
From paper: Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image
verified2.592020Paper ↗Code ↗Looks wrong?
03Cooperative
From paper: Cooperative Holistic Scene Understanding: Unifying 3D Object, Layout, and Camera Pose Estimation
verified2.192018Paper ↗Code ↗Looks wrong?
04IM3D
From paper: Holistic 3D Scene Understanding from a Single Image with Implicit Representation
verified2.112021Paper ↗Code ↗Looks wrong?
05Total3D joint
From paper: Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image
verified2.092020Paper ↗Code ↗Looks wrong?
06ImVoxelNet
From paper: ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection
verified1.962021Paper ↗Code ↗Looks wrong?
§ 04 · Submit a result

Add to the leaderboard.

← Back to Document OCR