The paper introduces CanDO, a test‑time canonicalization technique that restores performance of score‑only black‑box point cloud models when faced with pose shifts. CanDO searches for an input transformation that maximizes model confidence using derivative‑free optimization, requiring only forward queries. Experiments show that it recovers 76% of the oracle gap for azimuthal misorientation and 51% for arbitrary SO(3) rotations in object part segmentation tasks.
Point cloud models are increasingly deployed through score-only black-box interfaces. Under this access model, test-time rotations outside the training distribution can substantially degrade performan...
arXiv:2606. 24178v1 Announce Type: cross Abstract: Pretrained vision models often misclassify inputs that are rotated, scaled, or sheared, even though these affine transformations leave the object class unchanged.
arXiv:2608. 15260v1 Announce Type: cross Abstract: Maintaining global geometric consistency is a central challenge in long-sequence 3D reconstruction, with scale drift being the most critical failure mode.
arXiv:2603.14254v2 Announce Type: replace Abstract: Test-time adaptation (TTA) aims to improve model robustness under distribution shifts by adapting to unlabeled test data, but most existing methods...
GAPrompt++ is a multi-granular geometry-aware prompting method designed to adapt pre-trained 3D vision models to downstream tasks efficiently. It introduces a Point Shift Prompter for multi-scale geometric feature extraction, a Keypoint Prompter for local geometric saliency, and a Prompt Propagation mechanism to embed these cues throughout the model hierarchy. Experiments demonstrate that GAPrompt++ outperforms other prompting-based PEFT methods and even surpasses full fine-tuning while using less than 2% trainable parameters, and the authors provide two new challenging benchmarks for future research.
arXiv:2610.27418v1 Announce Type: new Abstract: 3D point clouds generation requires capturing both part-level layout and surface detail while preserving permutation equivariance. Existing latent gene...
Vision Foundation Models (VFMs) have significantly advanced dense feature matching, yet severe in-plane rotation remains a critical challenge. Existing solutions face a fundamental dilemma: data-driven methods require inefficient parameter scaling to implicitly learn rotations, whereas strictly equivariant networks lack the semantic capacity of modern VFMs.
arXiv:2606. 31585v1 Announce Type: cross Abstract: The remarkable scalability of Transformers has expanded their application to 3D computer vision, where camera-aware positional encoding is crucial for providing spatial cues in multi-view geometry.
arXiv:2609.23733v1 Announce Type: new Abstract: Feed-forward visual geometry models such as the Visual Geometry Grounded Transformer (VGGT) have recently enabled direct 3D reconstruction from multi-v...
NovaSplat is a model‑free pipeline for 6D object pose estimation that builds a 3D Gaussian Splatting (3DGS) model from a short smartphone video during onboarding. The 3DGS model serves both as a template for detection and coarse pose estimation and as a differentiable backbone for pose refinement, which optimizes pose using photometric and geometric losses under a continuous rotation parametrization. The method outperforms all model‑based methods on a household‑object benchmark and all model‑free competitors on a challenging industrial benchmark, while a faster variant, NovaSplat‑Lite, achieves comparable accuracy with a 3.1× speedup.
Scal3R is a new method for online 3D reconstruction that addresses the failure of traditional models on long videos by decoupling per‑frame depth from global pose estimation. It reformulates reconstruction as a multi‑reference relative pose query, using lightweight learnable tokens (~1% of parameters) injected into a frozen backbone via asymmetric attention to query poses relative to multiple past keyframes. An online pose‑graph optimization with loop closure further suppresses drift, achieving convergence in 8 hours on a single GPU and reducing average absolute trajectory error by over 60% on KITTI while setting state‑of‑the‑art results on several benchmark datasets.
The paper introduces Self-Geometry, a plug‑and‑play test‑time adaptation framework that enforces explicit multi‑view geometric constraints on Vision Foundation Models (VFMs) using 2D pixel correspondences as pseudo ground truth. It combines Geometric Disentanglement Optimization—mixing Multi‑View and Epipolar Consistency losses with Gradient Disentanglement—to avoid gradient conflicts, a Frame Angular‑Neighbor sampler based on SO(3) geodesic distances to select informative views, and a Lightweight TTA module that adapts VFMs via LoRA. Experiments on six VFMs and four benchmarks (7Scenes, ETH3D, ScanNet++, HiRoom) show consistent improvements in pose and geometry estimation.