Browse State-of-the-Art › Point Cloud Pre-training
Point Cloud Pre-training
15 papers with code · 0 benchmarks · 0 datasets archive 2025-07-28
Point cloud data represents 3D shapes as a set of discrete points in 3D space. This kind of data is primarily sourced from 3D scanners, LiDAR systems, and other similar technologies. Point cloud processing has a wide range of applications, such as robotics, autonomous vehicles, and augmented/virtual reality.
Pre-training on point cloud data is similar in spirit to pre-training on images or text. By pre-training a model on a large, diverse dataset, it learns essential features of the data type, which can then be fine-tuned on a smaller, task-specific dataset. This two-step process (pre-training and fine-tuning) often results in better performance, especially when the task-specific dataset is limited in size.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
No benchmark for this task in the archive.
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
No dataset record in the archive lists this task.
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: 26 · with a code link: 15 · 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 26 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 26 of 26, 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.
-
28 May 2022 3 repositories listedBy fine-tuning on downstream tasks, Point-M2AE achieves 86.
-
21 Jul 2020 2 repositories listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples) · 2 pointer-only (licence)To this end, we select a suite of diverse datasets and tasks to measure the effect of unsupervised pre-training on a large source set of 3D scenes.
-
8 Jul 2024 1 repository listed Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified (of 8 harvested samples) · 6 pointer-only (licence)To answer this question, we first empirically validate that integrating MAE-based point cloud pre-training with the standard contrastive learning paradigm, even with meticulous design, can lead to a decrease in…
-
12 Oct 2023 1 repository listedIn this paper, we introduce a novel universal 3D pre-training framework designed to facilitate the acquisition of efficient 3D representation, thereby establishing a pathway to 3D foundational models.
-
8 Jun 2023 1 repository listedIn our work, we present Point-LGMask, a novel method to embed both local and global contexts with multi-ratio masking, which is quite effective for self-supervised feature learning of point clouds but is unfortunately…
-
1 Jun 2023 1 repository listed Syntology official (archive's flag): 4 ran · 4 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; 4 where Syntology's instrument failed) · 5 unverified (of 9 harvested samples)It is a long-term vision for Autonomous Driving (AD) community that the perception models can learn from a large-scale point cloud dataset, to obtain unified representations that can achieve promising results on…
-
15 May 2023 1 repository listedThis paper tries to address a fundamental question in point cloud self-supervised learning: what is a good signal we should leverage to learn features from point clouds without annotations?
-
PointClustering: Unsupervised Point Cloud Pre-Training Using Transformation Invariance in Clustering1 Jan 2023 1 repository listedFeature invariance under different data transformations, i. e., transformation invariance, can be regarded as a type of self-supervision for representation learning.
-
12 Dec 2022 1 repository listedBased on the property of outdoor point clouds in autonomous driving scenarios, i. e., the point clouds of distant objects are more sparse, we propose point density prediction to enable the 3D encoder to learn location…
-
27 Jul 2022 1 repository listedMasked language modeling (MLM) has become one of the most successful self-supervised pre-training task.
-
26 Jul 2022 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples)Existing approaches for unsupervised point cloud pre-training are constrained to either scene-level or point/voxel-level instance discrimination.
-
3 Apr 2022 1 repository listedWe propose to use the dynamically updated momentum encoder as the tokenizer, which is updated and outputs the dynamic supervision signal along with the training process.
-
1 Jan 2022 1 repository listedMoreover, the PC-FractalDB pre-trained model is especially effective in training with limited data.
-
1 Sep 2021 1 repository listedAlbeit simple, the pre-trained encoder can capture the key points of an unseen point cloud and surpasses the encoder trained from scratch on downstream tasks.
-
2 Oct 2020 1 repository listedWe find that even when we construct a single pre-training dataset (from ModelNet40), this pre-training method improves accuracy across different datasets and encoders, on a wide range of downstream tasks.
-
Gaussian2Scene: 3D Scene Representation Learning via Self-supervised Learning with 3D Gaussian Splatting10 Jun 2025 0 repositories listedSelf-supervised learning (SSL) for point cloud pre-training has become a cornerstone for many 3D vision tasks, enabling effective learning from large-scale unannotated data.
-
EPContrast: Effective Point-level Contrastive Learning for Large-scale Point Cloud Understanding22 Oct 2024 0 repositories listedThe acquisition of inductive bias through point-level contrastive learning holds paramount significance in point cloud pre-training.
-
A Unified Framework for Human-centric Point Cloud Video Understanding29 Mar 2024 0 repositories listedHuman-centric Point Cloud Video Understanding (PVU) is an emerging field focused on extracting and interpreting human-related features from sequences of human point clouds, further advancing downstream human-centric…
-
Point Cloud Pre-training with Diffusion Models25 Nov 2023 0 repositories listedPre-training a model and then fine-tuning it on downstream tasks has demonstrated significant success in the 2D image and NLP domains.
-
PRED: Pre-training via Semantic Rendering on LiDAR Point Clouds8 Nov 2023 0 repositories listedPre-training is crucial in 3D-related fields such as autonomous driving where point cloud annotation is costly and challenging.
-
PatchContrast: Self-Supervised Pre-training for 3D Object Detection14 Aug 2023 0 repositories listedAccurately detecting objects in the environment is a key challenge for autonomous vehicles.
-
Multi-View Representation is What You Need for Point-Cloud Pre-Training5 Jun 2023 0 repositories listedA promising direction for pre-training 3D point clouds is to leverage the massive amount of data in 2D, whereas the domain gap between 2D and 3D creates a fundamental challenge.
-
Joint-MAE: 2D-3D Joint Masked Autoencoders for 3D Point Cloud Pre-training27 Feb 2023 0 repositories listedMasked Autoencoders (MAE) have shown promising performance in self-supervised learning for both 2D and 3D computer vision.
-
Ponder: Point Cloud Pre-training via Neural Rendering31 Dec 2022 0 repositories listedWe propose a novel approach to self-supervised learning of point cloud representations by differentiable neural rendering.
-
3D Point Cloud Pre-training with Knowledge Distillation from 2D Images17 Dec 2022 0 repositories listedThe recent success of pre-trained 2D vision models is mostly attributable to learning from large-scale datasets.
-
24 Jan 2019 0 repositories listedPoint clouds provide a flexible and natural representation usable in countless applications such as robotics or self-driving cars.
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