AI Paper Atlas

Research map / Benchmarks / SUN RGB-D

SUN RGB-D leaderboard

62 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on SUN RGB-D. Best mIoU: 55 (Ours (Swin-L), CVPR 2025).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

SUN RGB-D · mIoU

17 papers, each with its best reported number for its own method; higher is better.

7 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

SUN RGB-D · accuracy

16 papers, each with its best reported number for its own method; higher is better.

6 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

SUN RGB-D · mAP@0.25

16 papers, each with its best reported number for its own method; higher is better.

#mAP@0.25 ↑MethodPaperTopic
168H2A2
TR3D
H^2A^2: Homogeneity-Aware and Heterogeneity-Aware Feature Perception for Unified Indoor 3D Object Detection
CVPR 2026 · Table 1
3D detection and driving
267.6MVNet
CAGroup3D
Multi-View Representation is What You Need for Point-Cloud Pre-Training
ICLR 2024 · Table 2
Segmentation and detection
367.1ConDaFormer
CAGroup3D
ConDaFormer: Disassembled Transformer with Local Structure Enhancement for 3D Point Cloud Understanding
NeurIPS 2023 · Table: Detection results on SU
Point cloud classification
466.8CAGroup3DCAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Clouds
NeurIPS 2022 · Table 3D detection results
3D detection and driving
564.5GroupFree6,256 + X-3D
GroupFree6,256
X-3D: Explicit 3D Structure Modeling for Point Cloud Recognition
CVPR 2024 · Table 4
Point cloud classification
664.3GroupFree3D+LG3DLabel-Guided Auxiliary Training Improves 3D Object Detector
ECCV 2022 · Table 1
Segmentation and detection
763.7CO-Net (large)CO-Net: Learning Multiple Point Cloud Tasks at Once with A Cohesive Network
ICCV 2023 · Table 3
Point cloud classification
863Group-Free (L6, O256)
PointNet++
Group-Free 3D Object Detection via Transformers
ICCV 2021 · Table 2
Segmentation and detection
961.2ShapeFormer + SGM
VoteNet
AShapeFormer: Semantics-Guided Object-Level Active Shape Encoding for 3D Object Detection via Transformers
CVPR 2023 · Table 3
3D detection and driving
1061CorrelaBoost
VoteNet
Correlation Field for Boosting 3D Object Detection in Structured Scenes
AAAI 2022 · Table 2
3D detection and driving
6 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

SUN RGB-D · mAP@0.25 (val)

12 papers, each with its best reported number for its own method; higher is better.

2 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

SUN RGB-D · mAP@0.5 (val)

11 papers, each with its best reported number for its own method; higher is better.

1 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

SUN RGB-D · mAP@0.5

11 papers, each with its best reported number for its own method; higher is better.

#mAP@0.5 ↑MethodPaperTopic
151.7MVNet
CAGroup3D
Multi-View Representation is What You Need for Point-Cloud Pre-Training
ICLR 2024 · Table 2
Segmentation and detection
251.4H2A2
TR3D
H^2A^2: Homogeneity-Aware and Heterogeneity-Aware Feature Perception for Unified Indoor 3D Object Detection
CVPR 2026 · Table 1
3D detection and driving
350.2CAGroup3DCAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Clouds
NeurIPS 2022 · Table 3D detection results
3D detection and driving
449.9ConDaFormer
CAGroup3D
ConDaFormer: Disassembled Transformer with Local Structure Enhancement for 3D Point Cloud Understanding
NeurIPS 2023 · Table: Detection results on SU
Point cloud classification
547.5GroupFree3D+LG3DLabel-Guided Auxiliary Training Improves 3D Object Detector
ECCV 2022 · Table 1
Segmentation and detection
645.2Group-Free (L6, O256)
PointNet++
Group-Free 3D Object Detection via Transformers
ICCV 2021 · Table 2
Segmentation and detection
744.6CO-Net (large)CO-Net: Learning Multiple Point Cloud Tasks at Once with A Cohesive Network
ICCV 2023 · Table 3
Point cloud classification
838.5VoteNet (Ours)
VoteNet
A Unified Query-Based Paradigm for Point Cloud Understanding
CVPR 2022 · Indoor detection results table
Point cloud classification
937.7CorrelaBoost
VoteNet
Correlation Field for Boosting 3D Object Detection in Structured Scenes
AAAI 2022 · Table 2
3D detection and driving
1037.3MM-3DScene + VoteNet
VoteNet
MM-3DScene: 3D Scene Understanding by Customizing Masked Modeling With Informative-Preserved Reconstruction and Self-Distilled Consistency
CVPR 2023 · Table 3D object detection resu
3D generation
1 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.