Browse State-of-the-Art › 3D Object Recognition
3D Object Recognition
32 papers with code · 4 benchmarks · 8 datasets archive 2025-07-28
3D object recognition is the task of recognising objects from 3D data.
Note that there are related tasks you can look at, such as 3D Object Detection which have more leaderboards.
(Image credit: Look Further to Recognize Better)
Description from the archive archive 2025-07-28; Papers-with-Code links inside it are rewritten to this site.
Benchmarks archive 2025-07-28
4 leaderboard tables shown for this task, 4 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| ModelNet40 (6 rows) | R2-MLP-36 | R2-MLP: Round-Roll MLP for Multi-View 3D Object Recognition | code | — | Compare |
| Cube Engraving (1 row) | MeshWalker (ours) | MeshWalker: Deep Mesh Understanding by Random Walks | code | — | Compare |
| SHREC11, Split10-10 (1 row) | MeshWalker (ours) | MeshWalker: Deep Mesh Understanding by Random Walks | code | — | Compare |
| SHREC11, Split16-4 (1 row) | MeshWalker (ours) | MeshWalker: Deep Mesh Understanding by Random Walks | code | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
8 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 97 · with a code link: 32 · where Syntology ran a sample: 4 (3 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (4 of 97 tagged: 3 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 97 of 97, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
25 Oct 2019 4 repositories listedBlenderProc is a modular procedural pipeline, which helps in generating real looking images for the training of convolutional neural networks.
-
24 Oct 2016 3 repositories listed Syntology 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)We study the problem of 3D object generation.
-
20 Nov 2022 2 repositories listedRecently, vision architectures based exclusively on multi-layer perceptrons (MLPs) have gained much attention in the computer vision community.
-
25 Oct 2021 2 repositories listed Syntology official (archive's flag): 3 ran · 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples) · 3 pointer-only (licence)Nevertheless, multi-view CNN models cannot model the communications between patches from different views, limiting its effectiveness in 3D object recognition.
-
25 Jul 2019 2 repositories listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)In this paper we propose a neural message passing approach to augment an input 3D indoor scene with new objects matching their surroundings.
-
20 May 2016 2 repositories listedEach field probing filter is a set of probing points --- sensors that perceive the space.
-
12 Apr 2016 2 repositories listedEmpirical results from these two types of CNNs exhibit a large gap, indicating that existing volumetric CNN architectures and approaches are unable to fully exploit the power of 3D representations.
-
12 May 2015 2 repositories listedWe have implemented a convolutional neural network designed for processing sparse three-dimensional input data.
-
16 Jun 2025 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)Recent advancements in deep learning have greatly enhanced 3D object recognition, but most models are limited to closed-set scenarios, unable to handle unknown samples in real-world applications.
-
12 May 2025 1 repository listedExperimental results in the Nuscenes, SemanticKITTI, and Waymo datasets demonstrate that the proposed method achieves competitive performance, with an approximately 16x reduction in model size and a nearly 1.
-
17 Dec 2024 1 repository listedAdversarial attacks pose significant challenges in 3D object recognition, especially in scenarios involving multi-view analysis where objects can be observed from varying angles.
-
21 Sep 2024 1 repository listedSemi-supervised learning (SSL) has shown its effectiveness in learning effective 3D representation from a small amount of labelled data while utilizing large unlabelled data.
-
2 Apr 2024 1 repository listedThis paper presents a novel universal perturbation method for generating robust multi-view adversarial examples in 3D object recognition.
-
19 Mar 2024 1 repository listedTaking advantage of multi-view aggregation presents a promising solution to tackle challenges such as occlusion and missed detection in multi-object tracking and detection.
-
19 Oct 2023 1 repository listedIn this work, we address the challenging task of 3D object recognition without the reliance on real-world 3D labeled data.
-
3 Oct 2022 1 repository listedRobots operating in human-centered environments, such as retail stores, restaurants, and households, are often required to distinguish between similar objects in different contexts with a high degree of accuracy.
-
21 Jul 2022 1 repository listedIn 3D, existing benchmarks are small in size and approaches specialize in few object categories and specific domains, e. g. urban driving scenes.
-
11 Dec 2021 1 repository listedData augmentation is an important technique to reduce overfitting and improve learning performance, but existing works on data augmentation for 3D point cloud data are based on heuristics.
-
8 Oct 2021 1 repository listedWith the proposition of neural networks for point clouds, deep learning has started to shine in the field of 3D object recognition while researchers have shown an increased interest to investigate the reliability of…
-
23 Sep 2021 1 repository listedIn this paper, we proposed a hybrid model architecture consists of a dynamically growing dual-memory recurrent neural network (GDM) and an autoencoder to tackle object recognition and grasping simultaneously.
-
15 Sep 2020 1 repository listedTowards addressing this challenge, we propose a new deep transfer learning approach based on a dynamic architectural method to make robots capable of open-ended learning about new 3D object categories.
-
9 Jun 2020 1 repository listedEach walk is organized as a list of vertices, which in some manner imposes regularity on the mesh.
-
27 Feb 2020 1 repository listedPrevious research has shown that points' sparsity, rotation and positional inherent variance can lead to a significant drop in the performance of point cloud based classification techniques.
-
17 Sep 2019 1 repository listedIn this paper, we first analyse the data distributions and interaction of foreground and background, then propose the foreground-background separated monocular depth estimation (ForeSeE) method, to estimate the…
-
4 Jun 2019 1 repository listedWe improve upon these methods by introducing a view clustering and pooling layer based on dominant sets.
-
17 Apr 2019 1 repository listedIn this study, we present an analysis of model-based ensemble learning for 3D point-cloud object classification and detection.
-
8 Feb 2019 1 repository listedNowadays, service robots are appearing more and more in our daily life.
-
23 Aug 2018 1 repository listedWith the recent proliferation of deep learning, various deep models with different representations have achieved the state-of-the-art performance.
-
30 May 2018 1 repository listedThe multi-level voxel representation consists of a coarse voxel grid that contains volumetric information of the 3D object.
-
16 Mar 2018 1 repository listedMost existing 3D object recognition algorithms focus on leveraging the strong discriminative power of deep learning models with softmax loss for the classification of 3D data, while learning discriminative features with…
-
13 Nov 2017 1 repository listed
-
17 May 2017 1 repository listed
-
Aligning Text, Images, and 3D Structure Token-by-Token9 Jun 2025 0 repositories listed
-
LM-MCVT: A Lightweight Multi-modal Multi-view Convolutional-Vision Transformer Approach for 3D Object Recognition27 Apr 2025 0 repositories listed
-
Occlusion-aware Text-Image-Point Cloud Pretraining for Open-World 3D Object Recognition15 Feb 2025 0 repositories listed
-
Formula-Supervised Visual-Geometric Pre-training20 Sep 2024 0 repositories listed
-
Beyond Viewpoint: Robust 3D Object Recognition under Arbitrary Views through Joint Multi-Part Representation4 Jul 2024 0 repositories listed
-
3D Instance Segmentation Using Deep Learning on RGB-D Indoor Data19 Jun 2024 0 repositories listed
-
MM-Mixing: Multi-Modal Mixing Alignment for 3D Understanding28 May 2024 0 repositories listed
-
Deep Models for Multi-View 3D Object Recognition: A Review23 Apr 2024 0 repositories listed
-
SUGAR: Pre-training 3D Visual Representations for Robotics1 Apr 2024 0 repositories listed
-
Fine-grained 3D object recognition: an approach and experiments28 Jun 2023 0 repositories listed
-
Deep Graph Reprogramming28 Apr 2023 0 repositories listed
-
InOR-Net: Incremental 3D Object Recognition Network for Point Cloud Representation20 Feb 2023 0 repositories listed
-
Early or Late Fusion Matters: Efficient RGB-D Fusion in Vision Transformers for 3D Object Recognition3 Oct 2022 0 repositories listed
-
TANDEM3D: Active Tactile Exploration for 3D Object Recognition19 Sep 2022 0 repositories listed
-
Deep Optical Coding Design in Computational Imaging27 Jun 2022 0 repositories listed
-
RendNet: Unified 2D/3D Recognizer With Latent Space Rendering21 Jun 2022 0 repositories listed
-
Towards Robust 3D Object Recognition with Dense-to-Sparse Deep Domain Adaptation7 May 2022 0 repositories listed
-
Lifelong Ensemble Learning based on Multiple Representations for Few-Shot Object Recognition4 May 2022 0 repositories listed
-
Neural Part Priors: Learning to Optimize Part-Based Object Completion in RGB-D Scans17 Mar 2022 0 repositories listed
-
Sparse Depth Completion with Semantic Mesh Deformation Optimization10 Dec 2021 0 repositories listed
-
6D Pose Estimation with Combined Deep Learning and 3D Vision Techniques for a Fast and Accurate Object Grasping11 Nov 2021 0 repositories listed
-
Self-Supervised Modality-Invariant and Modality-Specific Feature Learning for 3D Objects29 Sep 2021 0 repositories listed
-
Spectral Processing and Optimization of Static and Dynamic 3D Geometries15 Jul 2021 0 repositories listed
-
Offboard 3D Object Detection from Point Cloud Sequences8 Mar 2021 0 repositories listed
-
Self-Supervised Multi-View Learning via Auto-Encoding 3D Transformations1 Mar 2021 0 repositories listed
-
Seeing by haptic glance: reinforcement learning-based 3D object Recognition15 Feb 2021 0 repositories listed
-
3D Object Recognition By Corresponding and Quantizing Neural 3D Scene Representations30 Oct 2020 0 repositories listed
-
Rotation-Invariant Local-to-Global Representation Learning for 3D Point Cloud7 Oct 2020 0 repositories listed
-
Open-Ended Fine-Grained 3D Object Categorization by Combining Shape and Texture Features in Multiple Colorspaces19 Sep 2020 0 repositories listed
-
Minimal Adversarial Examples for Deep Learning on 3D Point Clouds27 Aug 2020 0 repositories listed
-
Active Perception using Light Curtains for Autonomous Driving5 Aug 2020 0 repositories listed
-
3D Object Detection Method Based on YOLO and K-Means for Image and Point Clouds21 Apr 2020 0 repositories listed
-
YOLO and K-Means Based 3D Object Detection Method on Image and Point Cloud21 Apr 2020 0 repositories listed
-
Investigating the Importance of Shape Features, Color Constancy, Color Spaces and Similarity Measures in Open-Ended 3D Object Recognition10 Feb 2020 0 repositories listed
-
Variable-Viewpoint Representations for 3D Object Recognition8 Feb 2020 0 repositories listed
-
Interactive Open-Ended Learning for 3D Object Recognition19 Dec 2019 0 repositories listed
-
L3DOC: Lifelong 3D Object Classification12 Dec 2019 0 repositories listed
-
Representation Learning on Unit Ball with 3D Roto-Translational Equivariance30 Nov 2019 0 repositories listed
-
Learning Relationships for Multi-View 3D Object Recognition1 Oct 2019 0 repositories listed
-
Look Further to Recognize Better: Learning Shared Topics and Category-Specific Dictionaries for Open-Ended 3D Object Recognition26 Jul 2019 0 repositories listed
-
Class-specific Anchoring Proposal for 3D Object Recognition in LIDAR and RGB Images22 Jul 2019 0 repositories listed
-
Mitigating the Hubness Problem for Zero-Shot Learning of 3D Objects15 Jul 2019 0 repositories listed
-
A Performance Evaluation of Correspondence Grouping Methods for 3D Rigid Data Matching5 Jul 2019 0 repositories listed
-
MV-C3D: A Spatial Correlated Multi-View 3D Convolutional Neural Networks15 Jun 2019 0 repositories listed
-
Y-GAN: A Generative Adversarial Network for Depthmap Estimation from Multi-camera Stereo Images3 Jun 2019 0 repositories listed
-
ClusterNet: Deep Hierarchical Cluster Network With Rigorously Rotation-Invariant Representation for Point Cloud Analysis1 Jun 2019 0 repositories listed
-
Deep Multi-View Learning using Neuron-Wise Correlation-Maximizing Regularizers25 Apr 2019 0 repositories listed
-
Volumetric Convolution: Automatic Representation Learning in Unit Ball3 Jan 2019 0 repositories listed
-
Deep RBFNet: Point Cloud Feature Learning using Radial Basis Functions11 Dec 2018 0 repositories listed
-
Multi-View Harmonized Bilinear Network for 3D Object Recognition1 Jun 2018 0 repositories listed
-
Performance Evaluation of 3D Correspondence Grouping Algorithms6 Apr 2018 0 repositories listed
-
Rotational Subgroup Voting and Pose Clustering for Robust 3D Object Recognition7 Sep 2017 0 repositories listed
-
Signature of Geometric Centroids for 3D Local Shape Description and Partial Shape Matching26 Dec 2016 0 repositories listed
-
Hierarchical Object Representation for Open-Ended Object Category Learning and Recognition1 Dec 2016 0 repositories listed
-
FusionNet: 3D Object Classification Using Multiple Data Representations19 Jul 2016 0 repositories listed
-
12 Apr 2016 0 repositories listed
-
Efficient Global Point Cloud Alignment using Bayesian Nonparametric Mixtures15 Mar 2016 0 repositories listed
-
Analysis by Synthesis: 3D Object Recognition by Object Reconstruction1 Jun 2014 0 repositories listed
-
Dual coordinate solvers for large-scale structural SVMs6 Dec 2013 0 repositories listed
-
Integration of 3D Object Recognition and Planning for Robotic Manipulation: A Preliminary Report29 Jul 2013 0 repositories listed
-
Matching objects across the textured-smooth continuum14 Jun 2013 0 repositories listed
-
Efficient 2D-to-3D Correspondence Filtering for Scalable 3D Object Recognition1 Jun 2013 0 repositories listed
-
SLAM++: Simultaneous Localisation and Mapping at the Level of Objects1 Jun 2013 0 repositories listed
-
Rotational Projection Statistics for 3D Local Surface Description and Object Recognition11 Apr 2013 0 repositories listed
-
3D Object Recognition with Deep Belief Nets1 Dec 2009 0 repositories listed
Syntology lines on 4 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections