Cover Image

Towards Foundation Models for 3D Scene Understanding: Instance-Aware Self-Supervised Learning for Point Clouds

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yang, Bin, Abdelsamad, Mohamed, Zhang, Miao, Condurache, Alexandru Paul
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Collaborative Learning for Semi-Supervised LiDAR Semantic Segmentation
by: Yang, Bin, et al.
Published: (2026)

Unsupervised Point Cloud Registration with Self-Distillation
by: Löwens, Christian, et al.
Published: (2024)

FLARES: Fast and Accurate LiDAR Multi-Range Semantic Segmentation
by: Yang, Bin, et al.
Published: (2025)

DOS: Distilling Observable Softmaps of Zipfian Prototypes for Self-Supervised Point Representation
by: Abdelsamad, Mohamed, et al.
Published: (2025)

Multi-Scale Neighborhood Occupancy Masked Autoencoder for Self-Supervised Learning in LiDAR Point Clouds
by: Abdelsamad, Mohamed, et al.
Published: (2025)

Learning Instance-Aware Correspondences for Robust Multi-Instance Point Cloud Registration in Cluttered Scenes
by: Yu, Zhiyuan, et al.
Published: (2024)

LaneCPP: Continuous 3D Lane Detection using Physical Priors
by: Pittner, Maximilian, et al.
Published: (2024)

SparseLaneSTP: Leveraging Spatio-Temporal Priors with Sparse Transformers for 3D Lane Detection
by: Pittner, Maximilian, et al.
Published: (2026)

FA-KPConv: Introducing Euclidean Symmetries to KPConv via Frame Averaging
by: Alawieh, Ali, et al.
Published: (2025)

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks
by: Berisha, Uranik, et al.
Published: (2025)

Masked Scene Modeling: Narrowing the Gap Between Supervised and Self-Supervised Learning in 3D Scene Understanding
by: Hermosilla, Pedro, et al.
Published: (2025)

Pre-training with 3D Synthetic Data: Learning 3D Point Cloud Instance Segmentation from 3D Synthetic Scenes
by: Otsuka, Daichi, et al.
Published: (2025)

Weakly-Supervised Learning for Tree Instances Segmentation in Airborne Lidar Point Clouds
by: Destouches, Swann Emilien Céleste, et al.
Published: (2025)

Data-Free Dynamic Compression of CNNs for Tractable Efficiency
by: Meiner, Lukas, et al.
Published: (2023)

PROM: Prioritize Reduction of Multiplications Over Lower Bit-Widths for Efficient CNNs
by: Meiner, Lukas, et al.
Published: (2025)

Variance-Based Pruning for Accelerating and Compressing Trained Networks
by: Berisha, Uranik, et al.
Published: (2025)

Inst3D-LMM: Instance-Aware 3D Scene Understanding with Multi-modal Instruction Tuning
by: Yu, Hanxun, et al.
Published: (2025)

Point Cloud Mixture-of-Domain-Experts Model for 3D Self-supervised Learning
by: Zha, Yaohua, et al.
Published: (2024)

Relation3D: Enhancing Relation Modeling for Point Cloud Instance Segmentation
by: Lu, Jiahao, et al.
Published: (2025)

Understanding Dynamic Scenes in Ego Centric 4D Point Clouds
by: Huang, Junsheng, et al.
Published: (2025)

InstaScene: Towards Complete 3D Instance Decomposition and Reconstruction from Cluttered Scenes
by: Yang, Zesong, et al.
Published: (2025)

3DRS: MLLMs Need 3D-Aware Representation Supervision for Scene Understanding
by: Huang, Xiaohu, et al.
Published: (2025)

To Supervise or Not to Supervise: Understanding and Addressing the Key Challenges of Point Cloud Transfer Learning
by: Hadgi, Souhail, et al.
Published: (2024)

Learning to Efficiently Adapt Foundation Models for Self-Supervised Endoscopic 3D Scene Reconstruction from Any Cameras
by: Cui, Beilei, et al.
Published: (2025)

Point2Vec for Self-Supervised Representation Learning on Point Clouds
by: Knaebel, Karim, et al.
Published: (2023)

PseudoMapTrainer: Learning Online Mapping without HD Maps
by: Löwens, Christian, et al.
Published: (2025)

Improved Block Merging for 3D Point Cloud Instance Segmentation
by: Denis, Leon, et al.
Published: (2024)

Integrating SAM Supervision for 3D Weakly Supervised Point Cloud Segmentation
by: You, Lechun, et al.
Published: (2025)

Harnessing Text-to-Image Diffusion Models for Point Cloud Self-Supervised Learning
by: Chen, Yiyang, et al.
Published: (2025)

Bringing Masked Autoencoders Explicit Contrastive Properties for Point Cloud Self-Supervised Learning
by: Ren, Bin, et al.
Published: (2024)

Instance-free Text to Point Cloud Localization with Relative Position Awareness
by: Wang, Lichao, et al.
Published: (2024)

2D-3D Interlaced Transformer for Point Cloud Segmentation with Scene-Level Supervision
by: Yang, Cheng-Kun, et al.
Published: (2023)

PI3DETR: Parametric Instance Detection of 3D Point Cloud Edges With a Geometry-Aware 3DETR
by: Oberweger, Fabio F., et al.
Published: (2025)

Foundational Models for 3D Point Clouds: A Survey and Outlook
by: Thengane, Vishal, et al.
Published: (2025)

MM-Point: Multi-View Information-Enhanced Multi-Modal Self-Supervised 3D Point Cloud Understanding
by: Yu, Hai-Tao, et al.
Published: (2024)

Self-Supervised Implicit Attention Priors for Point Cloud Reconstruction
by: Fogarty, Kyle, et al.
Published: (2025)

3D Focusing-and-Matching Network for Multi-Instance Point Cloud Registration
by: Zhang, Liyuan, et al.
Published: (2024)

GS-PT: Exploiting 3D Gaussian Splatting for Comprehensive Point Cloud Understanding via Self-supervised Learning
by: Liu, Keyi, et al.
Published: (2024)

Uni4D: A Unified Self-Supervised Learning Framework for Point Cloud Videos
by: Zuo, Zhi, et al.
Published: (2025)

Toward Scalable, Flexible Scene Flow for Point Clouds
by: Vedder, Kyle
Published: (2025)