Cover Image

Good Token Hunting: A Hitchhiker's Guide to Token Selection for Visual Geometry Transformers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zheng, Shuhong, Oechsle, Michael, Sandström, Erik, Rakotosaona, Marie-Julie, Tombari, Federico, Gilitschenski, Igor
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Graphics Machine Learning Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Track, Inpaint, Resplat: Subject-driven 3D and 4D Generation with Progressive Texture Infilling
by: Zheng, Shuhong, et al.
Published: (2025)

RadSplat: Radiance Field-Informed Gaussian Splatting for Robust Real-Time Rendering with 900+ FPS
by: Niemeyer, Michael, et al.
Published: (2024)

3D-LATTE: Latent Space 3D Editing from Textual Instructions
by: Parelli, Maria, et al.
Published: (2025)

TokenLight: Precise Lighting Control in Images using Attribute Tokens
by: Chaturvedi, Sumit, et al.
Published: (2026)

Squeezing Capacity from Multimodal Large Language Models for Subject-driven Generation
by: Zheng, Shuhong, et al.
Published: (2026)

CTRL-D: Controllable Dynamic 3D Scene Editing with Personalized 2D Diffusion
by: He, Kai, et al.
Published: (2024)

LiftNav: Path Planning via Semantic Lifting in TSDF-Guided Gaussian Splatting
by: Schieber, Hannah, et al.
Published: (2026)

PaMoSplat: Part-Aware Motion-Guided Gaussian Splatting for Dynamic Scene Reconstruction
by: Deng, Yinan, et al.
Published: (2026)

CRISP: Contact-Guided Real2Sim from Monocular Video with Planar Scene Primitives
by: Wang, Zihan, et al.
Published: (2025)

Tokenizing Buildings: A Transformer for Layout Synthesis
by: de Guevara, Manuel Ladron, et al.
Published: (2025)

3DGS-ReLoc: 3D Gaussian Splatting for Map Representation and Visual ReLocalization
by: Jiang, Peng, et al.
Published: (2024)

Incorporating dense metric depth into neural 3D representations for view synthesis and relighting
by: Chaudhury, Arkadeep Narayan, et al.
Published: (2024)

TwinAligner: Visual-Dynamic Alignment Empowers Physics-aware Real2Sim2Real for Robotic Manipulation
by: Fan, Hongwei, et al.
Published: (2025)

DisMech: A Discrete Differential Geometry-based Physical Simulator for Soft Robots and Structures
by: Choi, Andrew, et al.
Published: (2023)

ReBot: Scaling Robot Learning with Real-to-Sim-to-Real Robotic Video Synthesis
by: Fang, Yu, et al.
Published: (2025)

VibraVerse: A Large-Scale Geometry-Acoustics Alignment Dataset for Physically-Consistent Multimodal Learning
by: Pang, Bo, et al.
Published: (2025)

Articraft: An Agentic System for Scalable Articulated 3D Asset Generation
by: Zhou, Matt, et al.
Published: (2026)

LuxDiT: Lighting Estimation with Video Diffusion Transformer
by: Liang, Ruofan, et al.
Published: (2025)

Scaling Transformer-Based Novel View Synthesis Models with Token Disentanglement and Synthetic Data
by: Nair, Nithin Gopalakrishnan, et al.
Published: (2025)

Fire as a Service: Augmenting Robot Simulators with Thermally and Visually Accurate Fire Dynamics
by: Wagner, Anton R., et al.
Published: (2026)

Kimodo: Scaling Controllable Human Motion Generation
by: Rempe, Davis, et al.
Published: (2026)

SimULi: Real-Time LiDAR and Camera Simulation with Unscented Transforms
by: Turki, Haithem, et al.
Published: (2025)

Spherical-GOF: Geometry-Aware Panoramic Gaussian Opacity Fields for 3D Scene Reconstruction
by: Yang, Zhe, et al.
Published: (2026)

PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observations
by: Zheng, Yang, et al.
Published: (2024)

Scaling Mesh Generation via Compressive Tokenization
by: Weng, Haohan, et al.
Published: (2024)

RP-SLAM: Real-time Photorealistic SLAM with Efficient 3D Gaussian Splatting
by: Bai, Lizhi, et al.
Published: (2024)

Diff2DGS: Reliable Reconstruction of Occluded Surgical Scenes via 2D Gaussian Splatting
by: Song, Tianyi, et al.
Published: (2026)

UniPhys: Unified Planner and Controller with Diffusion for Flexible Physics-Based Character Control
by: Wu, Yan, et al.
Published: (2025)

Motion Synthesis with Sparse and Flexible Keyjoint Control
by: Hwang, Inwoo, et al.
Published: (2025)

PINGS: Gaussian Splatting Meets Distance Fields within a Point-Based Implicit Neural Map
by: Pan, Yue, et al.
Published: (2025)

SynAgent: Generalizable Cooperative Humanoid Manipulation via Solo-to-Cooperative Agent Synergy
by: Yao, Wei, et al.
Published: (2026)

SimEndoGS: Efficient Data-driven Scene Simulation using Robotic Surgery Videos via Physics-embedded 3D Gaussians
by: Yang, Zhenya, et al.
Published: (2024)

SMPLOlympics: Sports Environments for Physically Simulated Humanoids
by: Luo, Zhengyi, et al.
Published: (2024)

SurfFill: Completion of LiDAR Point Clouds via Gaussian Surfel Splatting
by: Strobel, Svenja, et al.
Published: (2025)

PointSLAM++: Robust Dense Neural Gaussian Point Cloud-based SLAM
by: Wang, Xu, et al.
Published: (2026)

Real2Edit2Real: Generating Robotic Demonstrations via a 3D Control Interface
by: Zhao, Yujie, et al.
Published: (2025)

LGSDF: Continual Global Learning of Signed Distance Fields Aided by Local Updating
by: Yue, Yufeng, et al.
Published: (2024)

MotionWavelet: Human Motion Prediction via Wavelet Manifold Learning
by: Feng, Yuming, et al.
Published: (2024)

Ponimator: Unfolding Interactive Pose for Versatile Human-human Interaction Animation
by: Liu, Shaowei, et al.
Published: (2025)

A Unified Masked Autoencoder with Patchified Skeletons for Motion Synthesis
by: Mascaro, Esteve Valls, et al.
Published: (2023)