Image de couverture de livre

SToRe3D: Sparse Token Relevance in ViTs for Efficient Multi-View 3D Object Detection

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Papais, Sandro, Feng, Lezhou, Cossette, Charles, Ge, Lingting
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition Robotics
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

SWTrack: Multiple Hypothesis Sliding Window 3D Multi-Object Tracking
par: Papais, Sandro, et autres
Publié: (2024)

ForeSight: Multi-View Streaming Joint Object Detection and Trajectory Forecasting
par: Papais, Sandro, et autres
Publié: (2025)

DuoSpaceNet: Leveraging Both Bird's-Eye-View and Perspective View Representations for 3D Object Detection
par: Huang, Zhe, et autres
Publié: (2024)

Adapting Pretrained ViTs with Convolution Injector for Visuo-Motor Control
par: Hwang, Dongyoon, et autres
Publié: (2024)

Revisiting Token Compression for Accelerating ViT-based Sparse Multi-View 3D Object Detectors
par: Ji, Mingqian, et autres
Publié: (2026)

DVPE: Divided View Position Embedding for Multi-View 3D Object Detection
par: Wang, Jiasen, et autres
Publié: (2024)

STRAP-ViT: Segregated Tokens with Randomized -- Transformations for Defense against Adversarial Patches in ViTs
par: Chattopadhyay, Nandish, et autres
Publié: (2026)

MDHA: Multi-Scale Deformable Transformer with Hybrid Anchors for Multi-View 3D Object Detection
par: Adeline, Michelle, et autres
Publié: (2024)

Provable Sparse Inversion and Token Relabel Enhanced One-shot Federated Learning with ViTs
par: Shen, Li, et autres
Publié: (2026)

Gaussian-Sum Filter for Range-based 3D Relative Pose Estimation in the Presence of Ambiguities
par: Ahmed, Syed S., et autres
Publié: (2024)

Token Cropr: Faster ViTs for Quite a Few Tasks
par: Bergner, Benjamin, et autres
Publié: (2024)

SToRM: Supervised Token Reduction for Multi-modal LLMs toward efficient end-to-end autonomous driving
par: Kim, Seo Hyun, et autres
Publié: (2026)

Refining Datapath for Microscaling ViTs
par: Xiao, Can, et autres
Publié: (2025)

Purrturbed but Stable: Human-Cat Invariant Representations Across CNNs, ViTs and Self-Supervised ViTs
par: Shah, Arya, et autres
Publié: (2025)

2D-3D Pose Tracking with Multi-View Constraints
par: Yu, Huai, et autres
Publié: (2023)

TransForSeg: A Multitask Stereo ViT for Joint Stereo Segmentation and 3D Force Estimation in Catheterization
par: Fekri, Pedram, et autres
Publié: (2025)

HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videos
par: Banerjee, Prithviraj, et autres
Publié: (2024)

Toward General Object-level Mapping from Sparse Views with 3D Diffusion Priors
par: Liao, Ziwei, et autres
Publié: (2024)

CoIn3D: Revisiting Configuration-Invariant Multi-Camera 3D Object Detection
par: Kuang, Zhaonian, et autres
Publié: (2026)

DreamUp3D: Object-Centric Generative Models for Single-View 3D Scene Understanding and Real-to-Sim Transfer
par: Wu, Yizhe, et autres
Publié: (2024)

Sparse3DTrack: Monocular 3D Object Tracking Using Sparse Supervision
par: Gosala, Nikhil, et autres
Publié: (2026)

Label-Efficient 3D Object Detection For Road-Side Units
par: Dao, Minh-Quan, et autres
Publié: (2024)

Unsupervised Object Localization in the Era of Self-Supervised ViTs: A Survey
par: Siméoni, Oriane, et autres
Publié: (2023)

VAT: Vision Action Transformer by Unlocking Full Representation of ViT
par: Li, Wenhao, et autres
Publié: (2025)

Object-Scene-Camera Decomposition and Recomposition for Data-Efficient Monocular 3D Object Detection
par: Kuang, Zhaonian, et autres
Publié: (2026)

3D Multi-Object Tracking with Semi-Supervised GRU-Kalman Filter
par: Wang, Xiaoxiang, et autres
Publié: (2024)

Multi-Object Tracking based on Imaging Radar 3D Object Detection
par: Palmer, Patrick, et autres
Publié: (2024)

I&S-ViT: An Inclusive & Stable Method for Pushing the Limit of Post-Training ViTs Quantization
par: Zhong, Yunshan, et autres
Publié: (2023)

CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTs
par: Ramachandran, Akshat, et autres
Publié: (2024)

Scene-Graph ViT: End-to-End Open-Vocabulary Visual Relationship Detection
par: Salzmann, Tim, et autres
Publié: (2024)

A Multi-View 3D Telepresence System for XR Robot Teleoperation
par: Dincer, Enes Ulas, et autres
Publié: (2026)

UADA3D: Unsupervised Adversarial Domain Adaptation for 3D Object Detection with Sparse LiDAR and Large Domain Gaps
par: Wozniak, Maciej K, et autres
Publié: (2024)

Perspective-Invariant 3D Object Detection
par: Liang, Ao, et autres
Publié: (2025)

MAP-NBV: Multi-agent Prediction-guided Next-Best-View Planning for Active 3D Object Reconstruction
par: Dhami, Harnaik, et autres
Publié: (2023)

SparseGrasp: Robotic Grasping via 3D Semantic Gaussian Splatting from Sparse Multi-View RGB Images
par: Yu, Junqiu, et autres
Publié: (2024)

Object Instance Retrieval in Assistive Robotics: Leveraging Fine-Tuned SimSiam with Multi-View Images Based on 3D Semantic Map
par: Sakaguchi, Taichi, et autres
Publié: (2024)

RL-Based Coverage Path Planning for Deformable Objects on 3D Surfaces
par: Zhang, Yuhang, et autres
Publié: (2026)

Reconstruction by Generation: 3D Multi-Object Scene Reconstruction from Sparse Observations
par: Zadaianchuk, Andrii, et autres
Publié: (2026)

Cross-Cluster Shifting for Efficient and Effective 3D Object Detection in Autonomous Driving
par: Chen, Zhili, et autres
Publié: (2024)

DATR: Diffusion-based 3D Apple Tree Reconstruction Framework with Sparse-View
par: Qiu, Tian, et autres
Publié: (2025)