Trust It or Not: Evidential Uncertainty for Feed-Forward 3D Reconstruction with Trust3R Zihao Zhu, Wenyuan Zhao, Nuo Chen, Chao Tian, @aaronfann.bsky.social tl;dr: evidential learning->closed-form Student-t predictive distribution->uncertainty for pointmaps arxiv.org/abs/2605.19539

EpiDiffVO: Geometry-Aware Epipolar Diffusion for Robust Visual Odometry Prateeth Rao tl;dr: DDPM for keypoint realignment satisfying epipolar constraints arxiv.org/abs/2605.19556

PRISM-SLAM: Probabilistic Ray-Grounded Inference for Scale-aware Metric SLAM Eunsoo Im tl;dr: DA3->SLAM; Plücker coordinates->ray distance->scale ambiguity; probabilistic soft-gating->dynamic distractors arxiv.org/abs/2605.19257

HAD: Hallucination-Aware Diffusion Priors for 3D Reconstruction Xi Liu, Weiwei Sun, Zhou Ren, Chris Broaddus, Siyu Huang, Laurent Guigues tl;dr: LVSM-based hallucination score network->pixel-wise hallucination scores->augmented views arxiv.org/abs/2605.16873

Rethinking the State Update Gate for Long-Sequence Recurrent 3D Reconstruction Kejun Ren, Lei Jin, Tianxin Huang, Lianming Xu, Li Wang tl;dr: scalar frame-level gate at inference time from features arxiv.org/abs/2605.16981

PySIFT: GPU-Resident Deterministic SIFT for Deep Learning Vision Pipelines Sivakumar K.S., Mohammad Daniyalur Rahman, Gopi Raju Matta tl;dr: in title arxiv.org/abs/2605.17869

Can These Views Be One Scene? Evaluating Multiview 3D Consistency when 3D Foundation Models Hallucinate Soumava Paul, Prakhar Kaushik, Alan Yuille tl;dr: in title arxiv.org/abs/2605.18754

SEDualVLN: A Spatially-Enhanced Dual-System for Vision-Language Navigation Jingzhi Huang, Junkai Huang, Wenxuan Song, Haoyang Yang, Hailong Huang, Haoang Li, Yi Wang tl;dr: VLM+MLLM arxiv.org/abs/2605.17249

Efficient Feature-Free Initialization for Monocular Visual-Inertial Systems Using a Feed-Forward 3D Model Yuantai Zhang, Jiaqi Yang, Huajian Zeng, Changhao Chen, Haoang Li, Liang Li, Dezhen Song, Xingxing Zuo tl;dr: VGGT helps VINS initialization arxiv.org/abs/2605.17327

3D Skew Gaussian Splatting with Any Camera Trajectory Visualization Engine Beizhen Zhao, Yifan Zhou, Gaochao Song, Ziran Yin, Hao Wang tl;dr: symmetric+skew Gaussians arxiv.org/abs/2605.18334

Learn2Splat: Extending the Horizon of Learned 3DGS Optimization Naama Pearl, @s-esposito.bsky.social, @haofeixu.bsky.social, Amit Peleg, @pgschossmann.bsky.social, Lorenzo Porzi, Peter Kontschieder, Gerard Pons-Moll, @andreasgeiger.bsky.social arxiv.org/abs/2605.15760

GHOST: Geometry-Hierarchical Online Streaming Token Eviction for Efficient 3D Reconstruction Leyang Chen, Junyi Wu, Zhiteng Li, Yulun Zhang tl;dr: depth, point, camera pose outputs-> importance signals->redundant tokens or valuable tokens arxiv.org/abs/2605.15852

IVGT: Implicit Visual Geometry Transformer for Neural Scene Representation Yuqi Wu, Tianyu Hu, Wenzhao Zheng, Yuanhui Huang, Haowen Sun, Jie Zhou, Jiwen Lu tl;dr: scene->implicit SDF field->continuous 3D queries at arbitrary locations arxiv.org/abs/2605.16258

TurboVGGT: Fast Visual Geometry Reconstruction with Adaptive Alternating Attention David Huang, Guile Wu, Chengjie Huang, Bingbing Liu, Dongfeng Bai tl;dr: adaptive sparsity selection + adaptive sparse global attention arxiv.org/abs/2605.14315

CalibAnyView: Beyond Single-View Camera Calibration in the Wild Boying Li, Cheng Zhang, Weirong Chen, @dcremers.bsky.social, Ian Reid, Hamid Rezatofighi tl;dr: new video dataset; VGGTpbased framework; for single or multi-view camera calibration arxiv.org/abs/2605.14615

3D Skew-Normal Splatting Xiangru Wu, Ke Fan, Yanwei Fu tl;dr: Azzalini Skew-Normal distribution->primitive arxiv.org/abs/2605.15010

VGGT-Ω @jianyuanwang.bsky.social, Minghao Chen, Shangzhan Zhang, @nikkar.bsky.social, Johannes Schönberger, Patrick Labatut, Piotr Bojanowski, David Novotny, Andrea Vedaldi, Christian Rupprecht arxiv.org/abs/2605.15195

Denoising-GS: Gaussian Splatting with Spatial-aware Denoising Qingyuan Zhou, Xinyi Liu, Weidong Yang, Ning Wang, Shuquan Ye, Ben Fei, Ying He, Wanli Ouyang tl;dr: 3DGS optimization->Gaussian primitive denoising arxiv.org/abs/2605.14880

4DVGGT-D: 4D Visual Geometry Transformer with Improved Dynamic Depth Estimation Ying Zang, Xuanyi Liu, Yidong Han, Deyi Ji, Chaotao Ding, Yuanqi Hu, Qi Zhu, Xuanfu Li, Jin Ma, Lingyun Sun, Tianrun Chen, Lanyun Zhu tl;dr: first pose, then depth arxiv.org/abs/2605.12027

UniFixer: A Universal Reference-Guided Fixer for Diffusion-Based View Synthesis Sihan Chen, Xiang Zhang, Yang Zhang, Tunc Aydin, Christopher Schroers tl;dr: reference pre-alignment+global structure anchoring+local detail injection arxiv.org/abs/2605.12169

GeoQuery: Geometry-Query Diffusion for Sparse-View Reconstruction Xiao Cao, Yuze Li, Youmin Zhang, Jiayu Song, Cheng Yan, Wen Li, Lixin Duan tl;dr: depth+pose->geometric correspondence field->proxy query features->window-based retrieval->diffusion arxiv.org/abs/2605.12399

WildPose: A Unified Framework for Robust Pose Estimation in the Wild Jianhao Zheng, @liyuanzzz.bsky.social, Zihan Zhu, @ir0armeni.bsky.social tl;dr: MASt3R->DROID-SLAM arxiv.org/abs/2605.12774

HarmoGS: Robust 3D Gaussian Splatting in the Wild via Conflict-Aware Gradient Harmonization Yulei Kang, Tianze Zhu, Jian-Fang Hu, Jianhuang Lai, Wei-Shi Zheng tl;dr: image-space supervision and gradient-level optimization arxiv.org/abs/2605.13073

RoSplat: Robust Feed-Forward Pixel-wise Gaussian Splatting for Varying Input Views and High-Resolution Rendering Hoang Chuong Nguyen, Renjie Wu, Jose M. Alvarez, Miaomiao Liu arxiv.org/abs/2605.13093

Z-Order Transformer for Feed-Forward Gaussian Splatting Can Wang, Lei Liu, Wei Jiang, Dong Xu tl;dr: pixel-level GS->Z-order GS arxiv.org/abs/2605.13465

Distributed Pose Graph Optimization via Continuous Riemannian Dynamics Jaeho Shin, Maani Ghaffari, Yulun Tian tl;dr: Euler-Poincaré equation->PGO; pose variables->particles subject to damping->equilibrium states-> first-order critical point of PGO arxiv.org/abs/2605.11210

HCSG: Human-Centric Semantic-Geometric Reasoning for Vision-Language Navigation Haoxuan Xu, Tianfu Li, Wenbo Chen, Yi Liu, Jin Wu, Huashuo Lei, Yunfan Lou, Lujia Wang, Hesheng Wang, Haoang Li tl;dr: geometric forecasting + semantic interpretation arxiv.org/abs/2605.13321

TinySDP: Real Time Semidefinite Optimization for Certifiable and Agile Edge Robotics Ishaan Mahajan, Jon Arrizabalaga, Andrea Grillo, Fausto Vega, James Anderson, Zachary Manchester, Brian Plancher tl;dr: semidefinite relaxations->embedded MPC arxiv.org/abs/2605.13748

BlitzGS: City-Scale Gaussian Splatting at Lightning Speed Zhongtao Wang, Huishan Au, Yilong Li, Mai Su, Haojie Jin, Yisong Chen, Meng Gai, Fei Zhu, Guoping Wang tl;dr: reduce active Gaussian workload at three levels arxiv.org/abs/2605.13794

PaceVGGT: Pre-Alternating-Attention Token Pruning for Visual Geometry Transformers Haotang Li, Zhenyu Qi, Shaohan Henry Wang, Kebin Peng, Zi Wang, Qing Guo, Sen He, Huanrui Yang tl;dr: AA-internal attention->distillation->scorer->DINO per-token importance arxiv.org/abs/2605.08371

Attention Itself Could Retrieve.RetrieveVGGT: Training-Free Long Context Streaming 3D Reconstruction via Query-Key Similarity Retrieval Zichen Zou, Xiaosong Jia, Zuxuan Wu, Yu-Gang Jiang arxiv.org/abs/2605.09644

AdaptSplat: Adapting Vision Foundation Models for Feed-Forward 3D Gaussian Splatting Mingwei Xing, Xinliang Wang, Yifeng Shi tl;dr: shallow features->direction-aware high-frequency structural priors->Transformer & DPT arxiv.org/abs/2605.10239

MAG-VLAQ: Multi-modal Aerial-Ground Query Aggregation for Cross-View Place Recognition Zhengyi Xu, Yuhang Ming, Zhihao Zhan, Hanyu Zhu, @jcivera.bsky.social, Wanzeng Kong tl;dr: DINOv2+Utonia->tokens; neural ODE-based RGB-LiDAR fusion+VLAQ->global descriptors arxiv.org/abs/2605.09418

CapVector: Learning Transferable Capability Vectors in Parametric Space for Vision-Language-Action Models Wenxuan Song, Han Zhao, Fuhao Li, Ziyang Zhou, Xi Wang, Jing Lyu, Pengxiang Ding, Yan Wang, Donglin Wang, Haoang Li tl;dr: gains from finetuning->pretrained models arxiv.org/abs/2605.10903

RoboMemArena: A Comprehensive and Challenging Robotic Memory Benchmark Huashuo Lei, Wenxuan Song, Huarui Zhang, Jieyuan Pei, Jiayi Chen, Haodong Yan, Han Zhao, Pengxiang Ding, Zhipeng Zhang, Lida Huang, Donglin Wang, Yan Wang, Haoang Li tl;dr: benchmark+dual-system VLA arxiv.org/abs/2605.10921

Representations of 3D Rotations: Mathematical Foundations and Comparative Analysis Aizierjiang Aiersilan, Haochen Liu, James Hahn tl;dr: in title arxiv.org/abs/2605.08086

SplatWeaver: Learning to Allocate Gaussian Primitives for Generalizable Novel View Synthesis Yecong Wan, Fan Li, Mingwen Shao, Wangmeng Zuo tl;dr: scene complexity->adaptively allocate Gaussian primitives arxiv.org/abs/2605.07287

Disambiguating 2D-3D Correspondences in Gaussian Splatting-based Feature Fields for Visual Localization Miso Lee, Sangeek Hyun, Yerim Jeon, Jae-Pil Heo tl;dr: decompose each Gaussian along its major axis to replace many-to-one with one-to-one corres. arxiv.org/abs/2605.07351

Mind the Gap: Geometrically Accurate Generative Reconstruction from Disjoint Views Grzegorz Wilczynski, Mikołaj Zielinski, Bartosz Świrta, Dominik Belter, Przemysław Spurek tl;dr: new task->Generative Reconstruction from Disjoint Views arxiv.org/abs/2605.07550

Sparse-to-Complete: From Sparse Image Captures to Complete 3D Scenes Yiyang Shen, Yin Yang, Kun Zhou, Tianjia Shao tl;dr: diffusion for image repair+coverage-aware camera trajectory planning+view-consistency conditioned sampling for refinement arxiv.org/abs/2605.05664

Ray-Aware Pointer Memory with Adaptive Updates for Streaming 3D Reconstruction Feifei Li, Qi Song, Chi Zhang, Rui Huang tl;dr: 3D position+ray direction+timestamp+feature embedding->memory arxiv.org/abs/2605.05749

Spark3R: Asymmetric Token Reduction Makes Fast Feed-Forward 3D Reconstruction Zecheng Tang, Jiaye Fu, Qiankun Gao, Haijie Li, Yanmin Wu, Jiaqi Zhang, Siwei Ma, Jian Zhang tl;dr: different compressions to different tokens arxiv.org/abs/2605.06270

Solving Minimal Problems Without Matrix Inversion Using FFT-Based Interpolation Haidong Wu, Snehal Bhayani, Janne Heikkilä tl;dr: selected hidden variable->resultant matrix; IFFT interpolation->determinant coefficients arxiv.org/abs/2605.06572

ULF-Loc: Unbiased Landmark Feature for Robust Visual Localization with 3D Gaussian Splatting Yingdong Gu, Shaocheng Yan, @ericzzj.bsky.social, Yuan Kou, Jianxin Luo, Pengcheng Shi, Jiayuan Li #CVPR2026 Highlight arxiv.org/abs/2605.04730

Velox: Learning Representations of 4D Geometry and Appearance Anagh Malik, Dorian Chan, Xiaoming Zhao, @davelindell.bsky.social, @onceltuzel.bsky.social, Jen-Hao Rick Chang arxiv.org/abs/2605.04527

CARD: A Multi-Modal Automotive Dataset for Dense 3D Reconstruction in Challenging Road Topography Gasser Elazab, Frank Neuhaus, Tilman Koß, Malte Splietker, Aditya Date, Michael Unterreiner, Maximilian Jansen, Olaf Hellwich tl;dr: in title arxiv.org/abs/2605.05014

Syn4D: A Multiview Synthetic 4D Dataset Zeren Jiang, @yushi-lan.bsky.social, Yihang Luo, @yfdeng.bsky.social, Zihang Lai, Edgar Sucar, Christian Rupprecht, Iro Laina, @dlarlus.bsky.social, Chuanxia Zheng, Andrea Vedaldi tl;dr: in title arxiv.org/abs/2605.05207

Optimal Uncertainty-Aware Calibration for the AX=YB Problem Yanjia Chen, Xiangfei Li, Huan Zhao, Yiyuan Hong, Guanxiao Xia, Jiexin Zhang, Han Ding tl;dr: relative uncertainty between datasets->uncertainty metric->L-HED->UAL-HED local solver arxiv.org/abs/2605.04809

UniCorrn: Unified Correspondence Transformer Across 2D and 3D Prajnan Goswami, Tianye Ding, Feng Liu, Huaizu Jiang tl;dr: one Transformer for 2D-2D/2D-3D/3D-3D matching arxiv.org/abs/2605.04044

LR-SGS: Robust LiDAR-Reflectance-Guided Salient Gaussian Splatting for Self-Driving Scene Reconstruction Ziyu Chen, Fan Zhu, Hui Zhu, Deyi Kong, Xinkai Kuang, Yujia Zhang, Chunmao Jiang arxiv.org/abs/2603.12647