{"total":12,"items":[{"citing_arxiv_id":"2606.22481","ref_index":162,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Lighting-Consistent Object Transfer Across Radiance Fields","primary_cat":"cs.GR","submitted_at":"2026-06-21T12:50:07+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Diffusion-based per-view harmonization for lighting-consistent object transfer between 3DGS scenes, using heterogeneous training data and final 3D consolidation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.21368","ref_index":20,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Graph-of-Differences: Anatomy-Structured Difference Alignment for Medical Image Re-Identification","primary_cat":"cs.CV","submitted_at":"2026-06-19T12:18:12+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"GoD uses anatomy graphs and difference alignment to improve medical image re-identification accuracy and auditability, with +7.1 pp Rank-1 gains on fundus and +3.1 pp on CXR.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.27662","ref_index":8,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"How the Optimizer Shapes Learned Solutions in Equivariant Neural Networks","primary_cat":"cs.LG","submitted_at":"2026-05-26T20:25:44+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Muon optimizer improves performance over Adam in equivariant networks on ModelNet40 and produces solutions with larger Hessian curvature, more regular loss surfaces, and higher stable/effective ranks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.24013","ref_index":53,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"UniField: RBF-Guided Electron Density Fusion for Enhanced Molecular Representations","primary_cat":"physics.chem-ph","submitted_at":"2026-05-20T03:00:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"UniField fuses discrete atomic graphs with continuous electron density fields via RBF guidance in an SE(3)-equivariant multimodal model, reporting new SOTA results on QM9-ED, QMugs-ED, and ED5-OE benchmarks with gains up to 37%.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.17131","ref_index":107,"ref_count":2,"confidence":0.88,"is_internal_anchor":false,"paper_title":"A Survey on Deep Learning Architectures for Point Cloud Classification and Segmentation","primary_cat":"cs.CV","submitted_at":"2026-05-16T19:37:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":1.0,"formal_verification":"none","one_line_summary":"A survey that categorizes deep learning models for point cloud tasks by backbone architecture, evaluates benchmark performance, and outlines challenges and future research directions.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"downstream tasks (see Figure 14). Manuscript submitted to ACM A Systematic Survey on Deep Learning Architectures for Point Cloud Classification and Segmentation 19 3.5 Others Notable Architectures Several other notable methods have introduced novel architectures demonstrating competitive performance in point cloud understanding tasks. For instance,RCNet[ 107] presents a permutation invariant method to capture spatial structure by subdividing the point clouds and then sorting them. Each subdivision of point cloud is then processed by a Recurrent Neural Network (RNN) [23, 38]. The resulting features are fed into a regular 2D CNN for global feature extraction. Another RNN-based model isPoint2Sequence[ 56]."},{"citing_arxiv_id":"2605.14393","ref_index":110,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Analogical Trajectory Transfer","primary_cat":"cs.CV","submitted_at":"2026-05-14T05:14:59+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A method transfers trajectories across 3D scenes by clustering objects, predicting hierarchical smooth maps from foundation model features, assembling them combinatorially, and refining for coherence.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09216","ref_index":56,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Continuum Robot Modeling with Action Conditioned Flow Matching","primary_cat":"cs.RO","submitted_at":"2026-05-09T23:22:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A conditional point-cloud flow matching model maps motor actuation to 3D geometry of tendon-driven continuum robots and outperforms prior self-modeling methods on simulated and real 2- and 3-module hardware.","context_count":1,"top_context_role":"baseline","top_context_polarity":"baseline","context_text":"hardware is instantiated as 2- and 3-module real robots, while our MuJoCo simulation environments include 2-, 3- , and 5-module TDCR variants. Across simulated and real hardware settings, we compare against representative point based and view based deformable object and robot self mod- eling methods, including Visual Self Modeling (VSM) [7], conditional continuous normalizing flows (PointFlow) [56], NeRF inspired self simulation (FFKSM) [20], and articulated 3D Gaussian splatting [19]. Our experiments show that action conditioned flow matching achieves lower geometric error in steady state shape prediction, including more complex multi module settings and a simulated payload conditioned setting. In summary, our main contributions are: •A lightweight, configurable 3D printed TDCR platform"},{"citing_arxiv_id":"2605.07590","ref_index":29,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Beyond Defenses: Manifold-Aligned Regularization for Intrinsic 3D Point Cloud Robustness","primary_cat":"cs.CV","submitted_at":"2026-05-08T11:02:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"MAPR improves adversarial robustness in 3D point cloud networks by aligning latent predictions with intrinsic manifold geometry via curvature/diffusion features and a consistency loss.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.02098","ref_index":30,"ref_count":2,"confidence":0.88,"is_internal_anchor":false,"paper_title":"From Spherical to Gaussian: A Comparative Analysis of Point Cloud Cropping Strategies in Large-Scale 3D Environments","primary_cat":"cs.CV","submitted_at":"2026-05-03T23:36:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Gaussian and related cropping strategies for point cloud subclouds improve 3D neural network performance over spherical cropping on large outdoor scenes.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"and Pattern Recognition (CVPR), IEEE, Seattle, WA, USA, 2020, pp. 11105-11114. doi:10.1109/CVPR42600.2020.01112. URLhttps://ieeexplore.ieee.org/ document/9156466/ [29] L. Landrieu, M. Simonovsky, Large-scale Point CloudSemanticSegmentationwithSuperpoint Graphs, arXiv:1711.09869 [cs] (Mar. 2018). doi:10.48550/arXiv.1711.09869. URLhttp://arxiv.org/abs/1711.09869 [30] Y. Wang, Y. Sun, Z. Liu, S. E. Sarma, M. M. Bronstein, J. M. Solomon, Dynamic Graph CNN for Learning on Point Clouds, ACM Transactions on Graphics 38 (5) (2019) 1-12. doi:10.1145/3326362. URLhttps://dl.acm.org/doi/10.1145/ 3326362 [31] H. Lei, N. Akhtar, A. Mian, SegGCN: Efficient 3D Point Cloud Segmentation With Fuzzy Spherical Kernel, in: 2020 IEEE/CVF Conference on Computer Vision"},{"citing_arxiv_id":"2603.19684","ref_index":18,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"TSegAgent: Zero-Shot Tooth Segmentation via Geometry-Aware Vision-Language Agents","primary_cat":"cs.CV","submitted_at":"2026-03-20T06:32:16+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2507.19205","ref_index":45,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Physics-Informed Graph Neural Networks for Transverse Momentum Estimation in CMS Trigger Systems","primary_cat":"cs.LG","submitted_at":"2025-07-25T12:19:57+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Physics-informed GNNs with four detector-aware graph constructions and a custom message passing layer achieve MAE 0.8525 for pT estimation on CMS trigger data with over 55% fewer parameters than baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2411.07799","ref_index":55,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Horticultural Temporal Fruit Monitoring via 3D Instance Segmentation and Re-Identification using Colored Point Clouds","primary_cat":"cs.CV","submitted_at":"2024-11-12T13:53:22+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A 3D instance segmentation and attention-based re-identification pipeline for tracking fruits over time in colored point clouds, evaluated on strawberry and apple orchard data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}