AI Paper Atlas

Research map / Benchmarks / ScanObjectNN OBJ-BG

ScanObjectNN OBJ-BG leaderboard

48 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on ScanObjectNN OBJ-BG. Best accuracy: 99.48 (TopAdapter, ICML 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.

ScanObjectNN OBJ-BG · accuracy

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

#accuracy ↑MethodPaperTopic
199.48TopAdapter
PointGPT-L
TopAdapter: Topology-Aware Prompt Tuning for Efficient Point Cloud Understanding
ICML 2026 · Table 1
Point cloud classification
298.97GAPrompt++
best backbone per dataset (no voting)
GAPrompt++: Multi-Granular Geometry-Aware Point Cloud Prompt for 3D Vision Model
TPAMI 2026 · Table 1
Point cloud classification
398.97GAPrompt
PointGPT-L
GAPrompt: Geometry-Aware Point Cloud Prompt for 3D Vision Model
ICML 2025 · Table 1
Point cloud classification
497.52PointRWKV w/ vot.PointRWKV: Efficient RWKV-Like Model for Hierarchical Point Cloud Learning
AAAI 2025 · Table 1
Point cloud classification
597.2PointGPT-LPointGPT: Auto-regressively Generative Pre-training from Point Clouds
NeurIPS 2023 · Table 1
Point cloud classification
695.7PointChain (Mamba)PointChain: Learning Generalizable Point Cloud Representations via Structural Chain Modeling
AAAI 2026 · Table 1
Point cloud classification
795.53Point-SRAPoint-SRA: Self-Representation Alignment for 3D Representation Learning
AAAI 2026 · Table 1
Point cloud classification
895.52PCP-MAEPCP-MAE: Learning to Predict Centers for Point Masked Autoencoders
NeurIPS 2024 · Classification results table
Point cloud classification
995.18StruMamba3DStruMamba3D: Exploring Structural Mamba for Self-supervised Point Cloud Representation Learning
ICCV 2025 · Table 1
Point cloud classification
1095.18DAP-MAE
ReCon-SMC
DAP-MAE: Domain-Adaptive Point Cloud Masked Autoencoder for Effective Cross-Domain Learning
ICCV 2025 · Table 1
Point cloud classification
24 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

ScanObjectNN OBJ-BG · overall accuracy

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

4 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.