DynaTok introduces a token-based framework for correspondence-free 4D reconstruction from partial point cloud sequences via latent encoding, transformer aggregation, residual decoupling, and flow-matching decoding.
Flow4R: Unifying 4D reconstruction and tracking with scene flow
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 4years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
BA-T is an iterative Transformer that implements bundle adjustment as a repeatable lightweight layer to progressively refine pose and geometry predictions in two-view 3D reconstruction while using far fewer decoder parameters than prior models.
A two-stage diversity-plus-entropy token selection framework speeds up visual geometry transformers by over 85% on 500-image scenes while preserving baseline accuracy.
Dense optical flow can be estimated accurately in one forward pass by combining DINO-v2 semantic priors and monocular depth geometric cues via global matching, reaching 2.81 EPE on Sintel Final without any refinement.
citing papers explorer
-
DynaTok: Token-Based 4D Reconstruction from Partial Point Clouds
DynaTok introduces a token-based framework for correspondence-free 4D reconstruction from partial point cloud sequences via latent encoding, transformer aggregation, residual decoupling, and flow-matching decoding.
-
BA-T: An Iterative Transformer for Two-View Bundle Adjustment
BA-T is an iterative Transformer that implements bundle adjustment as a repeatable lightweight layer to progressively refine pose and geometry predictions in two-view 3D reconstruction while using far fewer decoder parameters than prior models.
-
Good Token Hunting: A Hitchhiker's Guide to Token Selection for Visual Geometry Transformers
A two-stage diversity-plus-entropy token selection framework speeds up visual geometry transformers by over 85% on 500-image scenes while preserving baseline accuracy.
-
Rethinking Dense Optical Flow without Test-Time Scaling
Dense optical flow can be estimated accurately in one forward pass by combining DINO-v2 semantic priors and monocular depth geometric cues via global matching, reaching 2.81 EPE on Sintel Final without any refinement.