GaussianFlow SLAM: Monocular Gaussian Splatting SLAM Guided by GaussianFlow
Dong-Uk Seo, Jinwoo Jeon, Eungchang Mason Lee, Hyun Myung
tl;dr: optical flow supervision with closed-form analytic gradients in 3DGS kernel
arxiv.org/abs/2604.15612
Neural Gabor Splatting: Enhanced Gaussian Splatting with Neural Gabor for High-frequency Surface Reconstruction
Haato Watanabe, Nobuyuki Umetani
tl;dr: augment Gaussian primitive with MLP->color variations within a single primitive
arxiv.org/abs/2604.15941
Code is out!
We are releasing code for the GNC experiments (point cloud registration & triangulation) and more tasks coming soon!
🔗 Code: github.com/maijiayao1/NPC
🎬 Video: youtu.be/7rjERHpgEYw
📑 Slides: iclr.cc/media/iclr-2...
🪧 Poster: iclr.cc/media/Poster...
Cross-Attentive Multiview Fusion of Vision-Language Embeddings
@tberriel.bsky.social, @martin-r-oswald.bsky.social, @jcivera.bsky.social
tl;dr: multiple viewpoints->vision-language descriptors->multi-view transformer->unified per-3D-instance embedding
arxiv.org/abs/2604.12551
StreamCacheVGGT: Streaming Visual Geometry Transformers with Robust Scoring and Hybrid Cache Compression
Xuanyi Liu, Deyi Ji, Chunan Yu, Qi Zhu, Xuanfu Li, Jin Ma, Tianrun Chen, Lanyun Zhu
tl;dr: in title; another scalable VGGT
arxiv.org/abs/2604.15237
TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens
Jiawei Ren, Michal Jan Tyszkiewicz, Jiahui Huang, Zan Gojcic
tl;dr: regress 3D Gaussian mean coordinates with self-supervised rendering loss->encoder-decoder
arxiv.org/abs/2604.15239
tl;dr: all input views->a fixed number of latent scene tokens->decoder->explicit 3D Gaussians
GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens
Roni Itkin, Noam Issachar, Yehonatan Keypur, @xingyu-chen.bsky.social, @apchen.bsky.social, Sagie Benaim
arxiv.org/abs/2604.15284
tl;dr: spacing prior->scale alignment; epipolar-guided intrinsics&pose correction; anchor-based global mapping
Keep It CALM: Toward Calibration-Free Kilometer-Level SLAM with Visual Geometry Foundation Models via an Assistant Eye
Tianjun Zhang, Fengyi Zhang, Tianchen Deng, Lin Zhang, Hesheng Wang
arxiv.org/abs/2604.14795
Hybrid Latents - Geometry-Appearance-Aware Surfel Splatting
Neel Kelkar, Simon Niedermayr, Klaus Engel, Rüdiger Westermann
tl;dr: 2D surfel carries a base feature signal that replaces the coarse levels of the hash-grid; bounded Beta kernels
arxiv.org/abs/2604.14928
Efficient closed-form approaches for pose estimation using Sylvester forms
Jana Vráblíková, Ezio Malis, Laurent Busé
tl;dr: Sylvester forms->resultant-based method in degrees 7 and 8
arxiv.org/abs/2604.14747
DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesis
Cheng-You Lu, Yi-Shan Hung, Wei-Ling Chi, Hao-Ping Wang, Charlie Li-Ting Tsai, Yu-Cheng Chang, Yu-Lun Liu, Thomas Do, Chin-Teng Lin
tl;dr: in title
arxiv.org/abs/2604.13416
SceneGlue: Scene-Aware Transformer for Feature Matching without Scene-Level Annotation
Songlin Du, Xiaoyong Lu, Yaping Yan, Guobao Xiao, Xiaobo Lu, Takeshi Ikenaga
tl;dr: self- and cross-attentions in parallel; feature classification->visible/invisible
arxiv.org/abs/2604.13941
Free Geometry: Refining 3D Reconstruction from Longer Versions of Itself
Yuhang Dai, Xingyi Yang
tl;dr: full-view prediction->supervisor for masked-view predictions
arxiv.org/abs/2604.14048
tl;dr: streaming state->anchor+local pose-reference window+trajectory memory
Geometric Context Transformer for Streaming 3D Reconstruction
Lin-Zhuo Chen, Jian Gao, Yihang Chen, Ka Leong Cheng, Yipengjing Sun, Liangxiao Hu, Nan Xue, Xing Zhu, Yujun Shen, Yao Yao, Yinghao Xu
arxiv.org/abs/2604.14141
Robust Energy-Aware Routing for Air-Ground Cooperative Multi-UAV Delivery in Wind-Uncertain Environments
Tianshun Li, Hongliang Lu, Yanggang Sheng, Zhongzhen Wang, Haoang Li, Xinhu Zheng
tl;dr: online risk-sensitive planning for truck-UAV delivery
arxiv.org/abs/2604.13441
@weijiewang.bsky.social, Qihang Cao, Sensen Gao, @donydchen.bsky.social, @haofeixu.bsky.social, @wenjingbian.bsky.social, @songyoupeng.bsky.social, Tat-Jen Cham, @chuanxiaz.bsky.social, @andreasgeiger.bsky.social, Jianfei Cai, Jia-Wang Bian, Bohan Zhuang
Author's thread:
bsky.app/profile/weij...
Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective
tl;dr: new survey
arxiv.org/abs/2604.14025
PDF-GS: Progressive Distractor Filtering for Robust 3D Gaussian Splatting
Kangmin Seo, MinKyu Lee, Tae-Young Kim, ByeongCheol Lee, JoonSeoung An, Jae-Pil Heo
tl;dr: use 3DGSself-filtering and amplify it through iterative discrepancy-guided refinement
arxiv.org/abs/2604.12580
GGD-SLAM: Monocular 3DGS SLAM Powered by Generalizable Motion Model for Dynamic Environments
Yi Liu, Haoxuan Xu, Hongbo Duan, Keyu Fan, Zhengyang Zhang, Peiyu Zhuang, Pengting Luo, Houde Liu
tl;dr: in title
arxiv.org/abs/2604.12837
tl;dr: dynamic-static decoupling requires principled uncertainty modeling across multiple abstraction levels
Robust 4D Visual Geometry Transformer with Uncertainty-Aware Priors
Ying Zang, Yidong Han, Chaotao Ding, Yuanqi Hu, Deyi Ji, Qi Zhu, Xuanfu Li, Jin Ma, Lingyun Sun, Tianrun Chen, Lanyun Zhu
arxiv.org/abs/2604.09366
AsymLoc: Towards Asymmetric Feature Matching for Efficient Visual Localization
Mohammad Omama, @berton-gabri.bsky.social, Eric Foxlin, Yelin Kim
tl;dr: detector confidence+descriptor similarity->alignment objective with geometric matching loss
arxiv.org/abs/2604.09445
Are Pretrained Image Matchers Good Enough for SAR-Optical Satellite Registration?
Isaac Corley, Alex Stoken, @berton-gabri.bsky.social
tl;dr: benchmark for optical–SAR registration
arxiv.org/abs/2604.10217
SyncFix: Fixing 3D Reconstructions via Multi-View Synchronization
Deming Li, Abhay Yadav, Cheng Peng, Rama Chellappa, @anandbhattad.bsky.social
tl;dr: joint conditional over multiple views to enforce consistency during denoising
arxiv.org/abs/2604.11797
tl;dr: feed-forward gating->geometric utility score->new frame value
Accelerating Transformer-Based Monocular SLAM via Geometric Utility Scoring
Xinmiao Xiong, Bangya Liu, Hao Wang, Dayou Li, Nuo Chen, Andrew Feng, Mingyu Ding, Suman Banerjee, Yang Zhou, @aaronfann.bsky.social
arxiv.org/abs/2604.08718
MonoEM-GS: Monocular Expectation-Maximization Gaussian Splatting SLAM
Evgenii Kruzhkov, @sven-behnke.bsky.social
tl;dr: not fully understood
arxiv.org/abs/2604.10593