Image de couverture de livre

TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Ren, Jiawei, Tyszkiewicz, Michal Jan, Huang, Jiahui, Gojcic, Zan
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Pixel-GS: Density Control with Pixel-aware Gradient for 3D Gaussian Splatting
par: Zhang, Zheng, et autres
Publié: (2024)

Déjà View: Looping Transformers for Multi-View 3D Reconstruction
par: Burzio, Alessandro, et autres
Publié: (2026)

Composable Visual Tokenizers with Generator-Free Diagnostics of Learnability
par: Zhao, Bingchen, et autres
Publié: (2026)

TokenSplat: Token-aligned 3D Gaussian Splatting for Feed-forward Pose-free Reconstruction
par: Li, Yihui, et autres
Publié: (2026)

TokenMotion: Motion-Guided Vision Transformer for Video Camouflaged Object Detection Via Learnable Token Selection
par: Yu, Zifan, et autres
Publié: (2023)

3DGUT: Enabling Distorted Cameras and Secondary Rays in Gaussian Splatting
par: Wu, Qi, et autres
Publié: (2024)

Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation
par: Bahmani, Sherwin, et autres
Publié: (2025)

Geometry-Guided 3D Visual Token Pruning for Video-Language Models
par: Li, Han, et autres
Publié: (2026)

Lyra 2.0: Explorable Generative 3D Worlds
par: Shen, Tianchang, et autres
Publié: (2026)

FreGS: 3D Gaussian Splatting with Progressive Frequency Regularization
par: Zhang, Jiahui, et autres
Publié: (2024)

GaussianToken: An Effective Image Tokenizer with 2D Gaussian Splatting
par: Dong, Jiajun, et autres
Publié: (2025)

2D Gaussians Meet Visual Tokenizer
par: Shi, Yiang, et autres
Publié: (2025)

3D Gaussian Ray Tracing: Fast Tracing of Particle Scenes
par: Moenne-Loccoz, Nicolas, et autres
Publié: (2024)

Efficient Visual Transformer by Learnable Token Merging
par: Wang, Yancheng, et autres
Publié: (2024)

From Pixels to Tokens: Revisiting Object Hallucinations in Large Vision-Language Models
par: Shang, Yuying, et autres
Publié: (2024)

Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models
par: Wu, Jay Zhangjie, et autres
Publié: (2025)

VGG-T$^3$: Offline Feed-Forward 3D Reconstruction at Scale
par: Elflein, Sven, et autres
Publié: (2026)

PixelPrune: Pixel-Level Adaptive Visual Token Reduction via Predictive Coding
par: Wang, Nan, et autres
Publié: (2026)

PCR-GS: COLMAP-Free 3D Gaussian Splatting via Pose Co-Regularizations
par: Wei, Yu, et autres
Publié: (2025)

Aligning Text, Images, and 3D Structure Token-by-Token
par: Sahoo, Aadarsh, et autres
Publié: (2025)

HybridGS: Decoupling Transients and Statics with 2D and 3D Gaussian Splatting
par: Lin, Jingyu, et autres
Publié: (2024)

CoR-GS: Sparse-View 3D Gaussian Splatting via Co-Regularization
par: Zhang, Jiawei, et autres
Publié: (2024)

SWinGS: Sliding Windows for Dynamic 3D Gaussian Splatting
par: Shaw, Richard, et autres
Publié: (2023)

DeferredGS: Decoupled and Editable Gaussian Splatting with Deferred Shading
par: Wu, Tong, et autres
Publié: (2024)

DeRA: Decoupled Representation Alignment for Video Tokenization
par: Guo, Pengbo, et autres
Publié: (2025)

DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models
par: Yao, Linli, et autres
Publié: (2024)

Learnable Motion-Focused Tokenization for Effective and Efficient Video Unsupervised Domain Adaptation
par: Liu, Tzu Ling, et autres
Publié: (2026)

SparseGS-W: Sparse-View 3D Gaussian Splatting in the Wild with Generative Priors
par: Li, Yiqing, et autres
Publié: (2025)

Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videos
par: Liang, Hanxue, et autres
Publié: (2024)

ReorgGS: Equivalent Distribution Reorganization for 3D Gaussian Splatting
par: Wang, Luchao, et autres
Publié: (2026)

Grounded 3D-LLM with Referent Tokens
par: Chen, Yilun, et autres
Publié: (2024)

Versatile Video Tokenization with Generative 2D Gaussian Splatting
par: Chen, Zhenghao, et autres
Publié: (2025)

PPISP: Physically-Plausible Compensation and Control of Photometric Variations in Radiance Field Reconstruction
par: Deutsch, Isaac, et autres
Publié: (2026)

3DGS$^2$-TR: Scalable Second-Order Trust-Region Method for 3D Gaussian Splatting
par: Hsiao, Roger, et autres
Publié: (2026)

SAM-Guided Masked Token Prediction for 3D Scene Understanding
par: Chen, Zhimin, et autres
Publié: (2024)

Self-Supervised and Generalizable Tokenization for CLIP-Based 3D Understanding
par: Mei, Guofeng, et autres
Publié: (2025)

Can3Tok: Canonical 3D Tokenization and Latent Modeling of Scene-Level 3D Gaussians
par: Gao, Quankai, et autres
Publié: (2025)

VisionSelector: End-to-End Learnable Visual Token Compression for Efficient Multimodal LLMs
par: Zhu, Jiaying, et autres
Publié: (2025)

EntropyGS: An Efficient Entropy Coding on 3D Gaussian Splatting
par: Huang, Yuning, et autres
Publié: (2025)

UniFlow: A Unified Pixel Flow Tokenizer for Visual Understanding and Generation
par: Yue, Zhengrong, et autres
Publié: (2025)