UniPR-3D: Towards Universal Visual Place Recognition with Visual Geometry Grounded Transformer Tianchen Deng, Xun Chen, Ziming Li, Hongming Shen, Danwei Wang, @jcivera.bsky.social, Hesheng Wang arxiv.org/abs/2512.21078

EcoSplat: Efficiency-controllable Feed-forward 3D Gaussian Splatting from Multi-view Images Jongmin Park, Minh-Quan Viet Bui, Juan Luis Gonzalez Bello, Jaeho Moon, Jihyong Oh, Munchurl Kim tl;dr: importance-aware primitive ranking arxiv.org/abs/2512.18692

Trifocal Tensor and Relative Pose Estimation with Known Vertical Direction Tao Li, Zhenbao Yu, Banglei Guan, Jianli Han, Weimin Lv, Friedrich Fraundorfer tl;dr: 3-view with known vertical directions->4 or 3 correspondences->closed-form or minimal solver arxiv.org/abs/2512.19110

WorldWarp: Propagating 3D Geometry with Asynchronous Video Diffusion Hanyang Kong, Xingyi Yang, Xiaoxu Zheng, Xinchao Wang tl;dr: SpatioTemporal Diffusion model trained with bidirectional non-causal attention arxiv.org/abs/2512.19678

RANSAC Scoring Functions: Analysis and Reality Check A. Shekhovtsov tl;dr: in title arxiv.org/abs/2512.19850

UMAMI: Unifying Masked Autoregressive Models and Deterministic Rendering for View Synthesis Thanh-Tung Le, Tuan Pham, Tung Nguyen, Deying Kong, Xiaohui Xie, @stephanmandt.bsky.social arxiv.org/abs/2512.20107

SirenPose: Dynamic Scene Reconstruction via Geometric Supervision Kaitong Cai, Jensen Zhang, Jing Yang, Keze Wang tl;dr: periodic activation characteristics of SIREN + geometric priors from pre-annotated keypoint dataset->new loss arxiv.org/abs/2512.20531

Globally Optimal Solution to the Generalized Relative Pose Estimation Problem using Affine Correspondences Zhenbao Yu, Banglei Guan, Shunkun Liang, Zibin Liu, Yang Shang, Qifeng Yu arxiv.org/abs/2512.17188

G3Splat: Geometrically Consistent Generalizable Gaussian Splatting Mehdi Hosseinzadeh, Shin-Fang Chng, Yi Xu, Simon Lucey, Ian Reid, Ravi Garg tl;dr: why priors matter for pose-free generalizable GS? arxiv.org/abs/2512.17547

Aion: Towards Hierarchical 4D Scene Graphs with Temporal Flow Dynamics Iacopo Catalano, Eduardo Montijano, @jcivera.bsky.social, Julio A. Placed, Jorge Pena-Queralta tl;dr: temporal flow dynamics->hierarchical 3DSG arxiv.org/abs/2512.11903

4D Primitive-Mâché: Glueing Primitives for Persistent 4D Scene Reconstruction @makezur.bsky.social, @marwantaher.bsky.social, @ajdavison.bsky.social arxiv.org/abs/2512.16564

Off The Grid: Detection of Primitives for Feed-Forward 3D Gaussian Splatting @arthurmoreau.bsky.social, Richard Shaw, @michaal94.bsky.social, Jisu Shin, Thomas Tanay, Zhensong Zhang, Songcen Xu, Eduardo Pérez-Pellitero arxiv.org/abs/2512.15508

ACE-SLAM: Scene Coordinate Regression for Neural Implicit Real-Time SLAM Ignacio Alzugaray, @marwantaher.bsky.social, @ajdavison.bsky.social tl;dr: in title; ACE+SLAM arxiv.org/abs/2512.14032

Broadening View Synthesis of Dynamic Scenes from Constrained Monocular Videos Le Jiang, Shaotong Zhu, Yedi Luo, Shayda Moezzi, Sarah Ostadabbas tl;dr: GS->3D prior->pseudo-novel view supervision; new dataset arxiv.org/abs/2512.14406

Fast 2DGS: Efficient Image Representation with Deep Gaussian Prior Hao Wang, Ashish Bastola, Chaoyi Zhou, Wenhui Zhu, Xiwen Chen, Xuanzhao Dong, Siyu Huang, Abolfazl Razi tl;dr: iterative bootstrapping loop->initialization arxiv.org/abs/2512.12774

DePT3R: Joint Dense Point Tracking and 3D Reconstruction of Dynamic Scenes in a Single Forward Pass Vivek Alumootil, Tuan-Anh Vu, M. Khalid Jawed tl;dr: frame-to-query->motion field->map points from observation time to query time arxiv.org/abs/2512.13122

Charge: A Comprehensive Novel View Synthesis Benchmark and Dataset to Bind Them All @michaal94.bsky.social, @thomas-tanay.bsky.social, @arthurmoreau.bsky.social, Zhensong Zhang, @eduperezp.bsky.social tl;dr: in title arxiv.org/abs/2512.13639

LASER: Layer-wise Scale Alignment for Training-Free Streaming 4D Reconstruction Tianye Ding, Yiming Xie, Yiqing Liang, Moitreya Chatterjee, Pedro Miraldo, Huaizu Jiang arxiv.org/abs/2512.13680

Prior-Enhanced Gaussian Splatting for Dynamic Scene Reconstruction from Casual Video Meng-Li Shih, Ying-Huan Chen, Yu-Lun Liu, Brian Curless tl;dr: dynamic-object masks+refining video depth+2-D tracks; scaffold-projection loss+virtual-view depth loss arxiv.org/abs/2512.11356

On Geometric Understanding and Learned Data Priors in VGGT Jelena Bratulić, Sudhanshu Mittal, Thomas Brox, Christian Rupprecht tl;dr: in title arxiv.org/abs/2512.11508

Moment-Based 3D Gaussian Splatting: Resolving Volumetric Occlusion with Order-Independent Transmittance Jan U. Müller, Robin Tim Landsgesell, Leif Van Holland, Patrick Stotko, Reinhard Klein arxiv.org/abs/2512.11800

E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training Qitao Zhao, Hao Tan, @qianqianwang.bsky.social, Sai Bi, Kai Zhang, Kalyan Sunkavalli, Shubham Tulsiani, Hanwen Jiang tl;dr: upgrade RayZer arxiv.org/abs/2512.10950

Any4D: Unified Feed-Forward Metric 4D Reconstruction Jay Karhade, @nikv9.bsky.social, Yuchen Zhang, Tanisha Gupta, @akashsharma02.bsky.social, @smash0190.bsky.social, Deva Ramanan tl;dr: upgrade MapAnything to 4D arxiv.org/abs/2512.10935

D2GSLAM: 4D Dynamic Gaussian Splatting SLAM Siting Zhu, Yuxiang Huang, Wenhua Wu, Chaokang Jiang, Yongbo Chen, I-Ming Chen, Hesheng Wang tl;dr: geometricprompt dynamic separation + static 3DGS & dynamic 4DGS + motion consistency loss arxiv.org/abs/2512.09411

TrackingWorld: World-centric Monocular 3D Tracking of Almost All Pixels Jiahao Lu, Weitao Xiong, Jiacheng Deng, Peng Li, Tianyu Huang, @frankzydou.bsky.social, Cheng Lin, Sai-Kit Yeung, Yuan Liu arxiv.org/abs/2512.08358

On-the-fly Large-scale 3D Reconstruction from Multi-Camera Rigs Yijia Guo, Tong Hu, Zhiwei Li, Liwen Hu, Keming Qian, Xitong Lin, Shengbo Chen, Tiejun Huang, Lei Ma tl;dr: in title arxiv.org/abs/2512.08498

Efficiently Reconstructing Dynamic Scenes One D4RT at a Time arxiv.org/abs/2512.08924

Sparse Variable Projection in Robotic Perception: Exploiting Separable Structure for Efficient Nonlinear Optimization @alanpapalia.bsky.social, Nikolas Sanderson, Haoyu Han, Heng Yang, Hanumant Singh, Michael Everett arxiv.org/abs/2512.07969

Selfi: Self Improving Reconstruction Engine via 3D Geometric Feature Alignment Youming Deng, @songyoupeng.bsky.social, @junyi42.bsky.social, Kathryn Heal, Tiancheng Sun, John Flynn, Steve Marschner, Lucy Chai arxiv.org/abs/2512.08930

MuSASplat: Efficient Sparse-View 3D Gaussian Splats via Lightweight Multi-Scale Adaptation Muyu Xu, Fangneng Zhan, Xiaoqin Zhang, Ling Shao, Shijian Lu tl;dr: multi-scale depth-wise convolutions->transformer; batch-wise encoding and decoding arxiv.org/abs/2512.07165

Dynamic Visual SLAM using a General 3D Prior Xingguang Zhong, Liren Jin, Marija Popović, Jens Behley, Cyrill Stachniss tl;dr: π3+moving object segmentation->depth+motion probability, then with uncertainty-aware BA->SLAM arxiv.org/abs/2512.06868

SyncTrack4D: Cross-Video Motion Alignment and Video Synchronization for Multi-Video 4D Gaussian Splatting Yonghan Lee, Tsung-Wei Huang, Shiv Gehlot, Jaehoon Choi, Guan-Ming Su, Dinesh Manocha arxiv.org/abs/2512.04315

RobustSplat++: Decoupling Densification, Dynamics, and Illumination for In-the-Wild 3DGS Chuanyu Fu, Guanying Chen, Yuqi Zhang, Kunbin Yao, Yuan Xiong, Chuan Huang, Shuguang Cui, Yasuyuki Matsushita, Xiaochun Cao arxiv.org/abs/2512.04815

LiteVGGT: Boosting Vanilla VGGT via Geometry-aware Cached Token Merging Zhijian Shu, Cheng Lin, Tao Xie, Wei Yin, Ben Li, Zhiyuan Pu, Weize Li, Yao Yao, Xun Cao, Xiaoyang Guo, Xiao-Xiao Long arxiv.org/abs/2512.04939

UTrice: Unifying Primitives in Differentiable Ray Tracing and Rasterization via Triangles for Particle-Based 3D Scenes Changhe Liu, Ehsan Javanmardi, Naren Bao, @highvis.supply, Manabu Tsukada tl;dr: treat triangles as primitives without proxy geometry arxiv.org/abs/2512.04421

Emergent Outlier View Rejection in Visual Geometry Grounded Transformers Jisang Han, Sunghwan Hong, Jaewoo Jung, Wooseok Jang, Honggyu An, @qianqianwang.bsky.social, Seungryong Kim, Chen Feng tl;dr: threshold internal attention and feature signals arxiv.org/abs/2512.04012

Flux4D: Flow-based Unsupervised 4D Reconstruction Jingkang Wang, Henry Che, Yun Chen, Ze Yang, @lilygoli.bsky.social, Sivabalan Manivasagam, Raquel Urtasun tl;dr: photometric losses and simple static-preference prior arxiv.org/abs/2512.03210

MUT3R: Motion-aware Updating Transformer for Dynamic 3D Reconstruction Guole Shen, Tianchen Deng, Xingrui Qin, Nailin Wang, Jianyu Wang, Yanbo Wang, Yongtao Chen, Hesheng Wang, Jingchuan Wang tl;dr: attention-derived motion cue->early decoder layers arxiv.org/abs/2512.03939

What Is The Best 3D Scene Representation for Robotics? From Geometric to Foundation Models Tianchen Deng, Yue Pan, Shenghai Yuan, Dong Li, Chen Wang, Mingrui Li, Long Chen, Lihua Xie, Danwei Wang, Jingchuan Wang, @jcivera.bsky.social, Hesheng Wang, Weidong Chen arxiv.org/abs/2512.03422

Radiance Meshes for Volumetric Reconstruction Alexander Mai, Trevor Hedstrom, @grgkopanas.bsky.social, Janne Kontkanen, Falko Kuester, @jonbarron.bsky.social tl;dr: Delaunay tetrahedralization->constant density and linear color radian->radiance mesh->radiance field arxiv.org/abs/2512.04076

TALO: Pushing 3D Vision Foundation Models Towards Globally Consistent Online Reconstruction Fengyi Zhang, Tianjun Zhang, Kasra Khosoussi, Zheng Zhang, Zi Huang, Yadan Luo arxiv.org/abs/2512.02341

AVGGT: Rethinking Global Attention for Accelerating VGGT Xianbing Sun, Zhikai Zhu, Zhengyu Lou, Bo Yang, Jinyang Tang, Liqing Zhang, He Wang, Jianfu Zhang tl;dr: early global attention layers->frame attention; grid-based K/V subsampling another scalable VGGT arxiv.org/abs/2512.02541

EGGS: Exchangeable 2D/3D Gaussian Splatting for Geometry-Appearance Balanced Novel View Synthesis Yancheng Zhang, Guangyu Sun, Chen Chen tl;dr: 2DGS+3DGS rasterization; erank->switch between 2D and 3D types for Gaussian arxiv.org/abs/2512.02932

VIGS-SLAM: Visual Inertial Gaussian Splatting SLAM Zihan Zhu, Wei Zhang, Norbert Haala, @marcpollefeys.bsky.social, @danielbarath.bsky.social tl;dr: in title arxiv.org/abs/2512.02293

EGG-Fusion: Efficient 3D Reconstruction with Geometry-aware Gaussian Surfel on the Fly Xiaokun Pan, Zhenzhe Li, Zhichao Ye, Hongjia Zhai, Guofeng Zhang tl;dr: Gaussian surfel-based; surfel fusion+information filter arxiv.org/abs/2512.01296

FlashVGGT: Efficient and Scalable Visual Geometry Transformers with Compressed Descriptor Attention Zipeng Wang, @danxuhk.bsky.social tl;dr: frame->compression->descriptor tokens; global attention->cross-attention between image and descriptor tokens another scalable VGGT arxiv.org/abs/2512.01540

Fin3R: Fine-tuning Feed-forward 3D Reconstruction Models via Monocular Knowledge Distillation Weining Ren, Hongjun Wang, Xiao Tan, Kai Han tl;dr: free decoder & re-normalization LoRA adapter->encoder & monocular teacher+unlabeled dataset->distill model arxiv.org/abs/2511.22429

Emergent Extreme-View Geometry in 3D Foundation Models Yiwen Zhang, @jtung.bsky.social, @ruojin.bsky.social, David Fouhey, Hadar Averbuch-Elor tl;dr: freeze decoder heads & tune biases of selected backbone layers & minimize rotation loss arxiv.org/abs/2511.22686

Robust 3DGS-based SLAM via Adaptive Kernel Smoothing Shouhe Zhang, Dayong Ren, Sensen Song, Wenjie Li, Piaopiao Yu, Yurong Qian tl;dr: controlled blur->rendered image->resilient to parameter noise arxiv.org/abs/2511.23221

DiskChunGS: Large-Scale 3D Gaussian SLAM Through Chunk-Based Memory Management Casimir Feldmann, Maximum Wilder-Smith, Vaishakh Patil, Michael Oechsle, @miniemeyer.bsky.social, Keisuke Tateno, Marco Hutter arxiv.org/abs/2511.23030