Imagen de Portada

GHOST: Geometry-Hierarchical Online Streaming Token Eviction for Efficient 3D Reconstruction

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Chen, Leyang, Wu, Junyi, Li, Zhiteng, Zhang, Yulun
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

QuantCache: Adaptive Importance-Guided Quantization with Hierarchical Latent and Layer Caching for Video Generation
por: Wu, Junyi, et al.
Publicado: (2025)

FlashEdit: Decoupling Speed, Structure, and Semantics for Precise Image Editing
por: Wu, Junyi, et al.
Publicado: (2025)

Evict3R: Training-Free Token Eviction for Memory-Bounded Streaming Visual Geometry Transformers
por: Mahdi, Soroush, et al.
Publicado: (2025)

DVD-Quant: Data-free Video Diffusion Transformers Quantization
por: Li, Zhiteng, et al.
Publicado: (2025)

BinaryHPE: 3D Human Pose and Shape Estimation via Binarization
por: Li, Zhiteng, et al.
Publicado: (2023)

WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool
por: Li, Zizun, et al.
Publicado: (2025)

HiT-SR: Hierarchical Transformer for Efficient Image Super-Resolution
por: Zhang, Xiang, et al.
Publicado: (2024)

FlashClear: Ultra-Fast Image Content Removal via Efficient Step Distillation and Feature Caching
por: Tang, Yixin, et al.
Publicado: (2026)

VEQ: Modality-Adaptive Quantization for MoE Vision-Language Models
por: Qin, Guangshuo, et al.
Publicado: (2026)

StreamSplat: Towards Online Dynamic 3D Reconstruction from Uncalibrated Video Streams
por: Wu, Zike, et al.
Publicado: (2025)

HorizonStream: Long-Horizon Attention for Streaming 3D Reconstruction
por: Cheng, Chong, et al.
Publicado: (2026)

DreamCraft3D++: Efficient Hierarchical 3D Generation with Multi-Plane Reconstruction Model
por: Sun, Jingxiang, et al.
Publicado: (2024)

StreamGS: Online Generalizable Gaussian Splatting Reconstruction for Unposed Image Streams
por: LI, Yang, et al.
Publicado: (2025)

EGG-Fusion: Efficient 3D Reconstruction with Geometry-aware Gaussian Surfel on the Fly
por: Pan, Xiaokun, et al.
Publicado: (2025)

DensifyBeforehand: LiDAR-assisted Content-aware Densification for Efficient and Quality 3D Gaussian Splatting
por: Patt, Phurtivilai, et al.
Publicado: (2025)

BiMaCoSR: Binary One-Step Diffusion Model Leveraging Flexible Matrix Compression for Real Super-Resolution
por: Liu, Kai, et al.
Publicado: (2025)

CondiQuant: Condition Number Based Low-Bit Quantization for Image Super-Resolution
por: Liu, Kai, et al.
Publicado: (2025)

Accelerating Streaming Video Large Language Models via Hierarchical Token Compression
por: Wang, Yiyu, et al.
Publicado: (2025)

Prior-guided Hierarchical Harmonization Network for Efficient Image Dehazing
por: Su, Xiongfei, et al.
Publicado: (2025)

Online3R: Online Learning for Consistent Sequential Reconstruction Based on Geometry Foundation Model
por: Zhou, Shunkai, et al.
Publicado: (2026)

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos
por: Yao, Linli, et al.
Publicado: (2025)

TokenSeg: Efficient 3D Medical Image Segmentation via Hierarchical Visual Token Compression
por: Zeng, Sen, et al.
Publicado: (2026)

Geometric Context Transformer for Streaming 3D Reconstruction
por: Chen, Lin-Zhuo, et al.
Publicado: (2026)

4DGCPro: Efficient Hierarchical 4D Gaussian Compression for Progressive Volumetric Video Streaming
por: Zheng, Zihan, et al.
Publicado: (2025)

HRGS: Hierarchical Gaussian Splatting for Memory-Efficient High-Resolution 3D Reconstruction
por: Li, Changbai, et al.
Publicado: (2025)

Towards Unified 3D Hair Reconstruction from Single-View Portraits
por: Zheng, Yujian, et al.
Publicado: (2024)

HCC-3D: Hierarchical Compensatory Compression for 98% 3D Token Reduction in Vision-Language Models
por: Zhang, Liheng, et al.
Publicado: (2025)

Spark3R: Asymmetric Token Reduction Makes Fast Feed-Forward 3D Reconstruction
por: Tang, Zecheng, et al.
Publicado: (2026)

Ray-Aware Pointer Memory with Adaptive Updates for Streaming 3D Reconstruction
por: Li, Feifei, et al.
Publicado: (2026)

LONG3R: Long Sequence Streaming 3D Reconstruction
por: Chen, Zhuoguang, et al.
Publicado: (2025)

StreamingTOM: Streaming Token Compression for Efficient Video Understanding
por: Chen, Xueyi, et al.
Publicado: (2025)

DenoiseGS: Gaussian Reconstruction Model for Burst Denoising
por: Cheng, Yongsen, et al.
Publicado: (2025)

StreamingAssistant: Efficient Visual Token Pruning for Accelerating Online Video Understanding
por: Jin, Xinqi, et al.
Publicado: (2025)

IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction
por: Li, Hao, et al.
Publicado: (2025)

UAVFF3D: A Geometry-Aware Benchmark for Feed-Forward UAV 3D Reconstruction
por: Yang, Xiang, et al.
Publicado: (2026)

Spherical Geometry Diffusion: Generating High-quality 3D Face Geometry via Sphere-anchored Representations
por: Zhang, Junyi, et al.
Publicado: (2026)

Geometry-Guided 3D Visual Token Pruning for Video-Language Models
por: Li, Han, et al.
Publicado: (2026)

S2GS: Streaming Semantic Gaussian Splatting for Online Scene Understanding and Reconstruction
por: Zhang, Renhe, et al.
Publicado: (2026)

InfVSR: Toward Consistency-Driven Streaming Generative Video Super-Resolution
por: Zhang, Ziqing, et al.
Publicado: (2025)

TokenSplat: Token-aligned 3D Gaussian Splatting for Feed-forward Pose-free Reconstruction
por: Li, Yihui, et al.
Publicado: (2026)