Cover Image

TTSA3R: Training-Free Temporal-Spatial Adaptive Persistent State for Streaming 3D Reconstruction

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zheng, Zhijie, Xiang, Xinhao, Zhang, Jiawei
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

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

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

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

Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence
by: Gao, Yuanyuan, et al.
Published: (2026)

Mem3R: Streaming 3D Reconstruction with Hybrid Memory via Test-Time Training
by: Liu, Changkun, et al.
Published: (2026)

VS3R: Robust Full-frame Video Stabilization via Deep 3D Reconstruction
by: Zhu, Muhua, et al.
Published: (2026)

FILT3R: Latent State Adaptive Kalman Filter for Streaming 3D Reconstruction
by: Jin, Seonghyun, et al.
Published: (2026)

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

Towards Open-Vocabulary Multimodal 3D Object Detection with Attributes
by: Xiang, Xinhao, et al.
Published: (2025)

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

PIS3R: Very Large Parallax Image Stitching via Deep 3D Reconstruction
by: Zhu, Muhua, et al.
Published: (2025)

Are AI-Generated Driving Videos Ready for Autonomous Driving? A Diagnostic Evaluation Framework
by: Xiang, Xinhao, et al.
Published: (2025)

EffiPerception: an Efficient Framework for Various Perception Tasks
by: Xiang, Xinhao, et al.
Published: (2024)

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

LASER: Layer-wise Scale Alignment for Training-Free Streaming 4D Reconstruction
by: Ding, Tianye, et al.
Published: (2025)

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

StreamSTGS: Streaming Spatial and Temporal Gaussian Grids for Real-Time Free-Viewpoint Video
by: Ke, Zhihui, et al.
Published: (2025)

3DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videos
by: Sun, Jiakai, et al.
Published: (2024)

Disambiguating Monocular Reconstruction of 3D Clothed Human with Spatial-Temporal Transformer
by: Deng, Yong, et al.
Published: (2024)

OCH3R: Object-Centric Holistic 3D Reconstruction
by: Du, Yi, et al.
Published: (2026)

DetAny4D: Detect Anything 4D Temporally in a Streaming RGB Video
by: Hou, Jiawei, et al.
Published: (2025)

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

TIMI: Training-Free Image-to-3D Multi-Instance Generation with Spatial Fidelity
by: Cai, Xiao, et al.
Published: (2026)

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

Continuous 3D Perception Model with Persistent State
by: Wang, Qianqian, et al.
Published: (2025)

Styl3R: Instant 3D Stylized Reconstruction for Arbitrary Scenes and Styles
by: Wang, Peng, et al.
Published: (2025)

End-to-End Spatial-Temporal Transformer for Real-time 4D HOI Reconstruction
by: Zhang, Haoyu, et al.
Published: (2026)

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

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

TalkingGaussian: Structure-Persistent 3D Talking Head Synthesis via Gaussian Splatting
by: Li, Jiahe, et al.
Published: (2024)

Ov3R: Open-Vocabulary Semantic 3D Reconstruction from RGB Videos
by: Gong, Ziren, et al.
Published: (2025)

Training-free Video Temporal Grounding using Large-scale Pre-trained Models
by: Zheng, Minghang, et al.
Published: (2024)

ACT-R: Adaptive Camera Trajectories for Single View 3D Reconstruction
by: Wang, Yizhi, et al.
Published: (2025)

VCBench: A Streaming Counting Benchmark for Spatial-Temporal State Maintenance in Long Videos
by: Liu, Pengyiang, et al.
Published: (2026)

Attention Itself Could Retrieve.RetrieveVGGT: Training-Free Long Context Streaming 3D Reconstruction via Query-Key Similarity Retrieval
by: Zou, Zichen, et al.
Published: (2026)

StreamForest: Efficient Online Video Understanding with Persistent Event Memory
by: Zeng, Xiangyu, et al.
Published: (2025)

NOVA3R: Non-pixel-aligned Visual Transformer for Amodal 3D Reconstruction
by: Chen, Weirong, et al.
Published: (2026)

SwinSF: Image Reconstruction from Spatial-Temporal Spike Streams
by: Jiang, Liangyan, et al.
Published: (2024)

Temporally-consistent 3D Reconstruction of Birds
by: Hägerlind, Johannes, et al.
Published: (2024)