AI Paper Atlas

Research map / Benchmarks / NuScenes Mean

NuScenes Mean leaderboard

11 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on NuScenes Mean. Best Success: 61.04 (CompTrack, AAAI 2026).

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.

NuScenes Mean · Success

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

#Success ↑MethodPaperTopic
161.04CompTrackCompTrack: Information Bottleneck-Guided Low-Rank Dynamic Token Compression for Point Cloud Tracking
AAAI 2026 · Table 2
Point cloud classification
259.84P2P-voxelP2P: Part-to-Part Motion Cues Guide a Strong Tracking Framework for LiDAR Point Clouds
IJCV 2025 · Table 5
Point cloud classification
355.75StreamTrackModeling Continuous Motion for 3D Point Cloud Object Tracking
AAAI 2024 · Table: Performance comparison
Point cloud classification
452.1SCVTrackRobust 3D Tracking with Quality-Aware Shape Completion
AAAI 2024 · NuScenes and WOD table
Shape and surface completion
551.1HVTrack
DGCNN
3D Single-object Tracking in Point Clouds with High Temporal Variation
ECCV 2024 · Table (nuScenes)
Point cloud classification
650.4GLT-TGLT-T: Global-Local Transformer Voting for 3D Single Object Tracking in Point Clouds
AAAI 2023 · Table 2
Point cloud classification
749.23M²-TrackBeyond 3D Siamese Tracking: A Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds
CVPR 2022 · NuScenes and WOD results table
Point cloud classification
841.76BATBox-Aware Feature Enhancement for Single Object Tracking on Point Clouds
ICCV 2021 · Table 1
Point cloud classification
931.8SyncTrackSynchronize Feature Extracting and Matching: A Single Branch Framework for 3D Object Tracking
ICCV 2023 · Table 2
Point cloud classification
1030.6M3SOT-F1M3SOT: Multi-Frame, Multi-Field, Multi-Space 3D Single Object Tracking
AAAI 2024 · Table: Comparison with the SOT
Point cloud classification
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.