BAT3R: Robust Online 3D Reconstruction with Bayesian Adaptive State Updates
cs.CV, cs.AI
Submitted: 2026-10-12
Updated: 2026-10-12
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Titans: Learning to Memorize at Test Time
- TTT3R: 3D Reconstruction as Test-Time Training
- Stuffed Mamba: Oversized States Lead to the Inability to Forget
- Human3R: Everyone Everywhere All at Once
- Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
- Learning without training: The implicit dynamics of in-context learning
- Repeat After Me: Transformers are Better than State Space Models at Copying
- ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training
- DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
- Longhorn: State Space Models are Amortized Online Learners
- FastVGGT: Training-Free Acceleration of Visual Geometry Transformer
- Learning to (Learn at Test Time): RNNs with Expressive Hidden States
- Test-time regression: a unifying framework for designing sequence models with associative memory
- $\pi^3$: Permutation-Equivariant Visual Geometry Learning
- Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer Memory
- ConfCtrl: Enabling Precise Camera Control in Video Diffusion via Confidence-Aware Interpolation
- Gated Delta Networks: Improving Mamba2 with Delta Rule
- Test3R: Learning to Reconstruct 3D at Test Time
- Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey
- MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models