Zhenjun Zhao

🚀 New paper led by Zhisong and Fan F²SLAM Turning Feed-Forward Geometry into Persistent Factors for SLAM 📉 Uncalibrated Replica ATE 0.002 m vs 0.030 m for the best feed-forward baseline 📄 arxiv.org/abs/2610.05207 💻 github.com/ZhisongXu/F2SLAM (code upon acceptance) 1/5

Foundation4D: Towards a unified perception and reconstruction model for autonomous vehicles NVIDIA tl;dr: in title arxiv.org/abs/2610.30340

SplatLab: Autonomous Scientific Discovery for 3DGS Research Seemandhar Jain, Manmohan Chandraker tl;dr: autonomous research system->submission-ready 3DGS manuscripts arxiv.org/abs/2610.30468

WovenAnchor Matcher: Specialized Intra- and Inter-Image Context Modeling for Feature Matching Zhiyang Li, Ruijiang Jin, Thibaut Klenke, Yusuke Sekikawa, Nakamasa Inoue tl;dr: separate intra-image and inter-image aggregation into two proposed modules arxiv.org/abs/2610.30799

Stream4D: Streaming 4D Reconstruction with Training-free Motion Decoupling via Causal KV-Cache Attention Wei Zhang, Ying Feng, Mengtong Wu, Shiqiang Gong, Huaqi Zhang, Qi Zhang tl;dr: causal attention encodes rich temporal motion cues within KV cache arxiv.org/abs/2610.31320

MVLoMa: Multi-View Local Feature Matching with Any Geometry Foundation Model Xinyang Lu, Shengzhe Wei, Sheng Tang, Weiqi Zhang, Juntong Fang, Zesong Li tl;dr: multi-view version of LoMa arxiv.org/abs/2610.31321

HiP3R: Hierarchical Pose Graphs for Long-Horizon 3D Reconstruction Zunnan Xu, Shangchen Zhou, Yihang Luo, Chen Change Loy tl;dr: chunk-level + frame-level SE(3) arxiv.org/abs/2610.31635

OmniRay: Camera-Agnostic Monocular 3D Reconstruction with Composite Ray Fields Namitha Guruprasad, Abhay Yadav, Cheng Peng, Rama Chellappa, @anandbhattad.bsky.social tl;dr: no intrinsics or camera-type input arxiv.org/abs/2610.31645

DLOSAC: Joint Spatial-Geometric Image Estimation via Delaunay-Guided Local Optimization RANSAC Yu Liu, Meiqi Zhou, Zipei Fan, Guanyuan Feng, Xuan Song tl;dr: candidate inliers->Delaunay triangulation->spatial distribution and geometric consistency losses->weighting->WLS arxiv.org/abs/2610.21215

Anchor3DGS: Feed-Forward 3D Gaussian Splatting with Compact Anchor-Based Representation Sheng Ye, Jiangke Lin, Fudong Wang, Yi Yuan, Zhen-Hui Dong, Yong-Jin Liu tl;dr: replace the pixel-aligned paradigm with a compact anchor-based representation arxiv.org/abs/2610.21634

Towards Reconstructing Geographically Diverse Architecture with 3D Foundation Models Nicky Kriplani, Yiwen Zhang, Angelina Wang, Hadar Averbuch-Elor tl;dr: geographically 3D scene benchmark arxiv.org/abs/2610.22514

LonGaussian: Tracking Foundation Priors for Long-Context Feedforward Gaussian Reconstruction Zhoufeng Xie, Guanjun Wu, Shuai Zhang, Xinggang Wang, Wenyu Liu tl;dr: LoGeR’s chunk-wise hybrid memory + track-guided consolidation + artifact filtering arxiv.org/abs/2610.23250

FineSplat: Fine Patches, Local Groups, Detailed Splats Hyebin Kim, Hwasik Jeong, Joonhyuk Park, Gyeongjin Kang, Jungwoo Kim, Younghyun Kim, Eunbyung Park tl;dr: fine-grained image patches->feed-forward 3DGS arxiv.org/abs/2610.25011

ReDT: Resolution-Decoupled Visual Geometry Transformer Abteen Arab, Guile Wu, Dongfeng Bai tl;dr: resolution-aware visual geometry transformer arxiv.org/abs/2610.25517

Causal Spatiotemporal State Evolution for Monocular 4D Reconstruction Qiaowei Miao, Yijing Guo, Lipei Zhang, Qifeng Cheng, Yuru Xiao, Ziqian Ni, Sheng Yang tl;dr: directionally ordered spatiotemporal state evolution->monocular 4D visual geometry arxiv.org/abs/2610.27594

KoalaGS: Complexity-Aware Continuous Level of Detail for Gaussian Splatting Radu Beche, Raoul de Charette tl;dr: reconstruction error->spatial prior for allocating capacity and selecting primitives arxiv.org/abs/2610.28615

BlazeVGGT: 13x Faster VGGT at 2,000 Frames via Camera Token without Training Shujun Yao, Junhui Lin, Congying Han, Tiande Guo, Ziwen Liu, Bonan Li tl;dr: use evolving camera-token relations to select complementary views for KV sparsification arxiv.org/abs/2610.29454

Remember, Revisit, Revise: Scaffold Memory for Long-Horizon 3D Geometry Soumick Sarker, Mengmi Zhang tl;dr: associate where an observer is with what it observes arxiv.org/abs/2610.19674

InfiniSplat v2: Analyzing and Improving Feed-Forward 3DGS from Any Views Yongzhen Hu, Hao Yu, Jiawei Wang, Xianming Zeng, Jianyun Xu, Xingliang Liu, Ruizhen Hu, Xiaowei Zhou, Hujun Bao, Sida Peng tl;dr: freeze geometry&learn Gaussian attributes arxiv.org/abs/2610.20341

BAT3R: Robust Online 3D Reconstruction with Bayesian Adaptive State Updates Lijian Li, Yuanpeng He, Yudian Zheng, Chung-ju Huang, Linyu Li, Dongming Jin, Wenpin Jiao, Zhi Jin, Chi-Man Pun tl;dr: Bayesian adaptation for uncertainty-aware state updating arxiv.org/abs/2610.16330

Towards Complementary Keypoint Detection via Mixture of Detectors Xiaoyong Lu, Guobao Xiao, Dong Liang, Songlin Du tl;dr: distill six detectors into multiple heads->router with reward-guided supervision selects most suitable detectors arxiv.org/abs/2610.16762

UniMetric: Universal Metric Scale Recovery for Visual Geometry Foundation Models Lei Yang, Yuner Zhang, Ziyang Liu, Ziying Song, Kai WU, Yiyang Gao, Jiangtao Su, Yiming Li tl;dr: uncertain object-size priors from VLM + GFM reconstruction->scale arxiv.org/abs/2610.16945

FLoTS-SLAM: Optical Flow-Derived Uncertainty for Monocular Dynamic SLAM with Two-Stage Optimization Haorui Du, Lipu Zhou tl;dr: optical flow and camera motion induced flow->residual->uncertainty; depth fix & poses est.->joint refinement of poses and depth arxiv.org/abs/2610.23496

TartanMatch: Towards Universal Dense Correspondence Across Modalities Hyeokjoon Kwon, Jiting Cai, Ruogu Li, Kritan Bhandari, Geethika Hemkumar, Parv Maheshwari, @yuhengqiu.bsky.social, Yuchen Zhang, @smash0190.bsky.social, Wenshan Wang tl;dr: multi-modal UFM arxiv.org/abs/2610.14513

Graph3R: Unifying View Graph Initialization with Feed-Forward Reconstruction Jingwen Yu, Hengli Wang, Jianhao Jiao, Zhonghang Liu, Ping Tan, Hong Zhang tl;dr: π3->verification head->pairwise covisibility->view graph->graph-conditioned reconstruction arxiv.org/abs/2610.16272

Global Optimality of Pose Graph Optimization Shuan Ding, Ruishuang Chen, Mengfan Cao, Zaiyue Yang tl;dr: global optimality of PGO from its own problem structure arxiv.org/abs/2610.14655

FoundationVIO: Enforcing Metric Scale in Feed-forward Visual-Inertial Odometry Jin Rhee, Yuhao Zhang, @fdellaert.bsky.social, @mauricefallon.bsky.social tl;dr: IMU measurements + GFM predictions->factor graph arxiv.org/abs/2610.14951

RootSLAM: Square Root Bundle Adjustment for Visual-Inertial SLAM Tomás Santucci, Mateo de Mayo, @dcremers.bsky.social, Taihú Pire tl;dr: square-root bundle adjustment->Basalt arxiv.org/abs/2610.15157

Physical SLAM: Physics-aware Simultaneous Localisation and Mapping Guangming Wang, Zhishuo Liu, Haibing Wu, Wanli Ma, Yixiong Jing, Olaf Wysocki, Brian Sheil tl;dr: dynamic object Gaussian field driven by spring-mass physical model arxiv.org/abs/2610.17260

All-St3R SLAM: Real-time RGB Dynamic SLAM with Pixel-wise Motion Masking Yewon Kim, Paul Hongsuck Seo, Sang Chul Ahn tl;dr: DUSt3R + All-Tracker arxiv.org/abs/2610.16143

Line-Augmented cuVSLAM: Robust Visual Odometry in Low-Texture Environments Dara Molloy, Terry Wu, Wonju Lee, Abhilash Nand Kumar, David Adley, Conor Ferguson, Hesam Rabeti tl;dr: PL-VINS->cuVSLAM arxiv.org/abs/2610.20958

CF-Splat: Closed-Form Triangle Splatting with Mesh Priors Yixin Fang, Liang Zhao tl;dr: mesh geometry&calibrated cameras->rendered pixel colors are linear with respect to per-vertex SH coefficients->multi-view appearance estimation->global LLS problem arxiv.org/abs/2610.22108

Zebra3D: Efficient Hybrid Foundation Models For Scalable 3D Reconstruction Utkarsh Saxena, Ruijing Yang, Mehdi Rezagholizadeh, Akash Haridas, Vikram Appia, @ebarsoum.bsky.social tl;dr: linear-centered attention->tolerant stages; tile-sparse attention->sensitive stages arxiv.org/abs/2610.12727

CompactSplat: Spatially Adaptive Gaussian Distribution for Feedforward Scene Reconstruction Bing He, Jingnan Gao, Yunuo Chen, Zhengxue Cheng, Rong Xie, Li Song, Wenjun Zhang tl;dr: Gaussians allocation according to image texture arxiv.org/abs/2610.13177

Efficient Confidence-Aware Densification for 3DGS Manuel Hofer, Thomas Köhler, Felix Windisch, Bernhard Kerbl, Markus Steinberger, Lukas Radl tl;dr: large screen-space gradients->new primitives->weighted learned confidence->relocate->contribute least arxiv.org/abs/2610.13541