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.
By Seonghwan Park, Min-Gyu Park
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.
By Dominik Lindner, Johann Schmidt, Tom Siegl, Martin Becker, Sebastian Stober
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...
By Ronghao Zhang, Shuaicheng Niu, Qi Deng, Yanjie Dong, Jian Chen, Runhao Zeng
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.
By Wei Zhang, Yihang Wu, Songhua Li, Qi Wang
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.
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.
By Zixiang Ai, Zhenyu Cui, Yufei Guo, Wenwen Qiang, Lei Chen, Jiwen Lu, Jiahuan Zhou
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...
By Linhao Wang, Dongjin Huang
SATOR is a source‑free, backpropagation‑free framework for test‑time adaptation of 3D point cloud models. It eliminates the need for predefined purge‑size candidates by computing token abnormality scores from attention and geometric graphs, then using an Otsu‑based threshold to partition tokens into retained and pruned sets. A keep‑ratio‑calibrated routing step selects the pruned prediction only when its entropy, adjusted by the keep ratio, is lower than that of the original prediction, achieving state‑of‑the‑art accuracy on three 3D corruption benchmarks.
By Inseok Kong, Geunyoung Jung, Jiyoung Jung
Position Anchor Tuning (PAT) is a parameter‑efficient fine‑tuning method for pre‑trained point cloud transformers that improves inference efficiency. PAT reduces the computational cost of multi‑head attention and feed‑forward networks by using token aggregation‑expansion pairs: a token aggregation module (TAM) selects representative tokens based on 3D position anchors, and a token expansion module (TEM) propagates the learned representations back to the full token set. Combined with base‑sharing low‑rank adaptation (BSLoRA) for the TAMs, PAT achieves performance comparable to state‑of‑the‑art methods while requiring fewer trainable parameters and lower computational overhead.
By Zheng Liu, Xin Gao, Jinchao Zhu, Gao Huang
arXiv:2604.13287v2 Announce Type: replace
Abstract: Weight pruning is a common technique for compressing large neural networks. We focus on the challenging post-training one-shot setting, where a pre...
By Gabriel Afriat, Xiang Meng, Shibal Ibrahim, Hussein Hazimeh, Rahul Mazumder
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...
By Abteen Arab, Guile Wu, Chengjie Huang, Dongfeng Bai
SpaceCache is a training‑free feature cache that reuses intermediate features from point‑cloud transformers across consecutive frames, allowing tokens of previously seen regions to skip transformer blocks and only compute new tokens. The method limits cache entry age and evicts low‑confidence entries to maintain reliability, and it operates once per encoder stage at negligible cost. Experiments on outdoor and indoor datasets (nuScenes, Waymo, ScanNet) with Utonia and LitePT‑B backbones show up to 1.65× speedup with less than 1‑point mIoU loss, outperforming token‑merging approaches.
By Dongheon Yang, Beomseok Kang, Jae-Joon Kim