MipSLAM: Alias-Free Gaussian Splatting SLAM
Yingzhao Li, Yan Li, Shixiong Tian, Yanjie Liu, Lijun Zhao,
tl;dr: elliptical sampling and Riemann summation-> pixel integrals; spatiotemporal signal+spectral decomposition->spectral-spatial PGO
arxiv.org/abs/2603.06989
3DGS-HPC: Distractor-free 3D Gaussian Splatting with Hybrid Patch-wise Classification
Jiahao Chen, Yipeng Qin, Ganlong Zhao, Xin Li, Wenping Wang, Guanbin Li
tl;dr: classification->local spatial consistency->robust 3DGS
arxiv.org/abs/2603.07587
FrameVGGT: Frame Evidence Rolling Memory for streaming VGGT
Zhisong Xu, Takeshi Oishi
tl;dr: not token-level compression, but block-level bounded retention
arxiv.org/abs/2603.07690
L3: Scene-agnostic Visual Localization in the Wild
Yu Zhang, Muhua Zhu, Yifei Xue, Tie Ji, Yizhen Lao
tl;dr: Ο3 helps map-free visual localization; need scale and point-only BA to achieve consistent metric scale
arxiv.org/abs/2603.07937
Speed3R: Sparse Feed-forward 3D Reconstruction Models
Weining Ren, Xiao Tan, Kai Han
tl;dr: attention only on the most informative image tokens
arxiv.org/abs/2603.08055
DynamicVGGT: Learning Dynamic Point Maps for 4D Scene Reconstruction in Autonomous Driving
Zhuolin He, Jing Li, Guanghao Li, Xiaolei Chen, Jiacheng Tang, Siyang Zhang, Zhounan Jin, Feipeng Cai, Bin Li, Jian Pu, Jia Cai, Xiangyang Xue
tl;dr: VGGT+DPM?
arxiv.org/abs/2603.08254
OVGGT: O(1) Constant-Cost Streaming Visual Geometry Transformer
Si-Yu Lu, Po-Ting Chen, Hui-Che Hsu, Sin-Ye Jhong, Wen-Huang Cheng, Yung-Yao Chen
tl;dr: FFN residual magnitude->score token; global initial/historical anchors->coordinate-critical tokens
arxiv.org/abs/2603.05959
Dark3R: Learning Structure from Motion in the Dark
Andrew Y Guo, Anagh Malik, SaiKiran Tedla, Yutong Dai, Yiqian Qin, Zach Salehe, Benjamin Attal, Sotiris Nousias, Kyros Kutulakos, David B. Lindell
tl;dr: MASt3R+distillation with noisyβclean raw image pairs
arxiv.org/abs/2603.05330
SURE: Semi-dense Uncertainty-REfined Feature Matching
Sicheng Li, Zaiwang Gu, Jie Zhang, Qing Guo, Xudong Jiang, Jun Cheng
tl;dr: uncertainty-aware LoFTR
no eval. on IMC
arxiv.org/abs/2603.04869
MoRe: Motion-aware Feed-forward 4D Reconstruction Transformer
Juntong Fang, Zequn Chen, Weiqi Zhang, Donglin Di, Xuancheng Zhang, Chengmin Yang, Yu-Shen Liu
tl;dr: attention-forcing->dynamic motion/static scene structure; grouped causal attention+BA-like token aggregation
arxiv.org/abs/2603.05078
AIM-SLAM: Dense Monocular SLAM via Adaptive and Informative Multi-View Keyframe Prioritization with Foundation Model
Jinwoo Jeon, Dong-Uk Seo, Eungchang Mason Lee, Hyun Myung
tl;dr: good keyframe selection+VGGT+MASt3R-SLAM
arxiv.org/abs/2603.05097
Omni-Manip: Beyond-FOV Large-Workspace Humanoid Manipulation with Omnidirectional 3D Perception
Pei Qu, Zheng Li, Yufei Jia, Ziyun Liu, Liang Zhu, Haoang Li, Jinni Zhou, Jun Ma
tl;dr: end-to-end LiDAR-driven visuomotor policy in large workspaces
arxiv.org/abs/2603.05355
GloSplat: Joint Pose-Appearance Optimization for Faster and More Accurate 3D Reconstruction
Tianyu Xiong, Rui Li, Linjie Li, Jiaqi Yang
tl;dr: use 3D feature tracks
arxiv.org/abs/2603.04847
DAGE: Dual-Stream Architecture for Efficient and Fine-Grained Geometry Estimation
Tuan Duc Ngo, Jiahui Huang, Seoung Wug Oh, Kevin Blackburn-Matzen, Evangelos Kalogerakis, Chuang Gan, Joon-Young Lee
tl;dr: low/high-resolution stream->fusion
arxiv.org/abs/2603.03744
NOVA3R: Non-pixel-aligned Visual Transformer for Amodal 3D Reconstruction
Weirong Chen, @chuanxiaz.bsky.social, @ganlinzhang.xyz, Andrea Vedaldi, @dcremers.bsky.social
tl;dr: TripoSG+VGGT
layout issue with tables?
arxiv.org/abs/2603.04179
Similar idea as:
bsky.app/profile/eric...
ZipMap: Linear-Time Stateful 3D Reconstruction with Test-Time Training
@haian-jin.bsky.social, Rundi Wu, Tianyuan Zhang, Ruiqi Gao, @jonbarron.bsky.social, @snavely.bsky.social, @holynski.bsky.social
tl;dr: another(?) TTT+VGGT
arxiv.org/abs/2603.04385
Overlapping Domain Decomposition for Distributed Pose Graph Optimization
Aneesa Sonawalla, Yulun Tian, Jonathan P. How
tl;dr: RBCD+overlapping domain decomposition
arxiv.org/abs/2603.03499
MERG3R: A Divide-and-Conquer Approach to Large-Scale Neural Visual Geometry
Leo Kaixuan Cheng, Abdus Shaikh, Ruofan Liang, Zhijie Wu, Yushi Guan, Nandita Vijaykumar
tl;dr: another scalable VGGT
arxiv.org/abs/2603.02351
LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory
@junyi42.bsky.social, Charles Herrmann, Junhwa Hur, Chen Sun, Ming-Hsuan Yang, Forrester Cole, Trevor Darrell, Deqing Sun
tl;dr: sliding window attention+Test-Time Training
arxiv.org/abs/2603.03269
TokenSplat: Token-aligned 3D Gaussian Splatting for Feed-forward Pose-free Reconstruction
Yihui Li, Chengxin Lv, Zichen Tang, Hongyu Yang, Di Huang
tl;dr: align semantically corresponding information across viewpoints directly in the feature space
arxiv.org/abs/2603.00697
OnlineX: Unified Online 3D Reconstruction and Understanding with Active-to-Stable State Evolution
Chong Xia, Fangfu Liu, Yule Wang, Yize Pang, Yueqi Duan
tl;dr: memory state->active local state & stable global state; active state->global state
arxiv.org/abs/2603.02134
riMESA: Consensus ADMM for Real-World Collaborative SLAM
Daniel McGann, Michael Kaess
tl;dr: MESA improvement+M-Estimation
arxiv.org/abs/2603.01178
tl;dr: Shorβs relaxation+Burer-Monteiro factorization->lifted factor graph (BM SDP relaxation)->Riemannian Staircase->LM+optimality certifier
extend SE-Sync/Shonan Rotation Averaging to factor graph
Certifiable Estimation with Factor Graphs
Zhexin Xu, Nikolas R. Sanderson, Hanna Jiamei Zhang, David M. Rosen
arxiv.org/abs/2603.01267
tl;dr: Gaussian noise->low-opacity regions; distill->auto-regressive causal model
ArtiFixer: Enhancing and Extending 3D Reconstruction with Auto-Regressive Diffusion Models
Riccardo de Lutio, @tobiasfshr.bsky.social, Yen-Yu Chang, Yuxuan Zhang, Jay Zhangjie Wu, Xuanchi Ren, Tianchang Shen, Katarina Tothova, Zan Gojcic, Haithem Turki
arxiv.org/abs/2603.00492
You still have 2 weeks to submit your paper to Image Matching Workshop at #CVPR2026
Deadline: March 16.
Topics: anything related to image matching and 3D reconstruction.
cmt3.research.microsoft.com/IMW2026
@cvprconference.bsky.social
Multiprojective Geometry of Compatible Triples of Fundamental and Essential Matrices
Timothy Duff, Viktor Korotynskiy, Anton Leykin, Tomas Pajdla
tl;dr: multidegree & multihomogeneous vanishing ideal->compatible triples for F/E matrices
read carefully later
arxiv.org/abs/2602.23450
No Calibration, No Depth, No Problem: Cross-Sensor View Synthesis with 3D Consistency
Cho-Ying Wu, Zixun Huang, Xinyu Huang, Liu Ren
tl;dr: cross-modality matching->semi-dense X-images->densification & fusion->dense X-images->self-matching->RGB-X 3DGS
arxiv.org/abs/2602.23559
