Imagen de Portada

Mem3R: Streaming 3D Reconstruction with Hybrid Memory via Test-Time Training

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Liu, Changkun, Yang, Jiezhi, Li, Zeman, Deng, Yuan, Guo, Jiancong, Ballan, Luca
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

Test3R: Learning to Reconstruct 3D at Test Time
por: Yuan, Yuheng, et al.
Publicado: (2025)

PreF3R: Pose-Free Feed-Forward 3D Gaussian Splatting from Variable-length Image Sequence
por: Chen, Zequn, et al.
Publicado: (2024)

TTT3R: 3D Reconstruction as Test-Time Training
por: Chen, Xingyu, et al.
Publicado: (2025)

Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction
por: Xie, Tao, et al.
Publicado: (2026)

SSR: A Training-Free Approach for Streaming 3D Reconstruction
por: Deng, Hui, et al.
Publicado: (2026)

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

3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning
por: Yang, Yuncong, et al.
Publicado: (2024)

PLANA3R: Zero-shot Metric Planar 3D Reconstruction via Feed-Forward Planar Splatting
por: Liu, Changkun, et al.
Publicado: (2025)

UniQueR: Unified Query-based Feedforward 3D Reconstruction
por: Peng, Chensheng, et al.
Publicado: (2026)

PAS3R: Pose-Adaptive Streaming 3D Reconstruction for Long Video Sequences
por: Xu, Lanbo, et al.
Publicado: (2026)

TTSA3R: Training-Free Temporal-Spatial Adaptive Persistent State for Streaming 3D Reconstruction
por: Zheng, Zhijie, et al.
Publicado: (2026)

StreamMem: Query-Agnostic KV Cache Memory for Streaming Video Understanding
por: Yang, Yanlai, et al.
Publicado: (2025)

FreshMem: Brain-Inspired Frequency-Space Hybrid Memory for Streaming Video Understanding
por: Li, Kangcong, et al.
Publicado: (2026)

ParkingTwin: Training-Free Streaming 3D Reconstruction for Parking-Lot Digital Twins
por: Liu, Xinhao, et al.
Publicado: (2026)

Mem4D: Decoupling Static and Dynamic Memory for Dynamic Scene Reconstruction
por: Cai, Xudong, et al.
Publicado: (2025)

Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer Memory
por: Wu, Yuqi, et al.
Publicado: (2025)

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

tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction
por: Wang, Chen, et al.
Publicado: (2026)

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

Benchmarking Layout-Guided Diffusion Models through Unified Semantic-Spatial Evaluation in Closed and Open Settings
por: Parolari, Luca, et al.
Publicado: (2026)

MosaicMem: Hybrid Spatial Memory for Controllable Video World Models
por: Yu, Wei, et al.
Publicado: (2026)

FluxMem: Adaptive Hierarchical Memory for Streaming Video Understanding
por: Xie, Yiweng, et al.
Publicado: (2026)

Learning 3D Reconstruction with Priors in Test Time
por: Zhou, Lei, et al.
Publicado: (2026)

Stream3D: Sequential Multi-View 3D Generation via Evidential Memory
por: Zhou, Kaichen, et al.
Publicado: (2026)

ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training
por: Jin, Haian, et al.
Publicado: (2026)

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

Remembering by Reconstructing: Domain Incremental Learning With Test-Time Training on Video Streams
por: Swinnen, Jonathan, et al.
Publicado: (2026)

MemRoPE: Training-Free Infinite Video Generation via Evolving Memory Tokens
por: Kim, Youngrae, et al.
Publicado: (2026)

$R^3$: 3D Reconstruction via Relative Regression
por: Xu, Congrong, et al.
Publicado: (2026)

H3R: Hybrid Multi-view Correspondence for Generalizable 3D Reconstruction
por: Jia, Heng, et al.
Publicado: (2025)

Test-Time Training on Video Streams
por: Wang, Renhao, et al.
Publicado: (2023)

3D Reconstruction with Spatial Memory
por: Wang, Hengyi, et al.
Publicado: (2024)

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

7Bench: a Comprehensive Benchmark for Layout-guided Text-to-image Models
por: Izzo, Elena, et al.
Publicado: (2025)

Towards Polyp Counting In Full-Procedure Colonoscopy Videos
por: Parolari, Luca, et al.
Publicado: (2025)

MemGS: Memory-Efficient Gaussian Splatting for Real-Time SLAM
por: Bai, Yinlong, et al.
Publicado: (2025)

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

CARFF: Conditional Auto-encoded Radiance Field for 3D Scene Forecasting
por: Yang, Jiezhi, et al.
Publicado: (2024)

R3D-AD: Reconstruction via Diffusion for 3D Anomaly Detection
por: Zhou, Zheyuan, et al.
Publicado: (2024)

IT$^3$: Idempotent Test-Time Training
por: Durasov, Nikita, et al.
Publicado: (2024)