🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Faster than Fast: Accelerating Oriented FAST Feature Detection on Low-end Embedded GPUs Qiong Chang, Xinyuan Chen, Xiang Li, Weimin Wang, Jun Miyazaki tl;dr: binary encoding->FAST detection; semi-separable Sobel operator->Harris detection; shared memory arxiv.org/abs/2506.07164

UNO: Unified Self-Supervised Monocular Odometry for Platform-Agnostic Deployment Wentao Zhao, et al. tl;dr: MoE-based multiple decoders->distinct motion patterns; differentiable Gumbel-Softmax sampling->inter-frame associations; sliding-window BA arxiv.org/abs/2506.07013

Gaussian Mapping for Evolving Scenes Vladimir Yugay, Thies Kersten, Luca Carlone, Theo Gevers, Martin Oswald, Lukas Schmid tl;dr: semantic consistency->3DGS->environment changes; covisibility-bsed keyframe management->mask stale areas arxiv.org/abs/2506.06909

GS4: Generalizable Sparse Splatting Semantic SLAM Mingqi Jiang, Chanho Kim, Ziwen Chen, Fuxin Li tl;dr: ODIN-based GS prediction->3D Gaussians w/ semantics->Gaussian refinement; 1-iteration test-time optimization arxiv.org/abs/2506.06517

Princeton365: A Diverse Dataset with Accurate Camera Pose Karhan Kayan, Stamatis Alexandropoulos, Rishabh Jain, Yiming Zuo, Erich Liang, Jia Deng tl;dr: dataset with gt camera pose and 6 DoF camera motion; new optical-flow based metric arxiv.org/abs/2506.09035

StreamSplat: Towards Online Dynamic 3D Reconstruction from Uncalibrated Video Streams Zike Wu, Qi Yan, Xuanyu Yi, Lele Wang, Renjie Liao tl;dr: probabilistic sampling->static encoder for 3DGS position prediction; bidirectional deformation field+adaptive Gaussian fusion->dynamic

SceneSplat++: A Large Dataset and Comprehensive Benchmark for Language Gaussian Splatting Mengjiao Ma, Qi Ma, Yue Li, Jiahuan Cheng, Runyi Yang (杨润一), Bin Ren, Nikola Popovic, Mingqiang Wei, Nicu Sebe, Luc Van Gool, Theo Gevers, Martin Oswald, Danda Pani Paudel tl;dr: in title

TraGraph-GS: Trajectory Graph-based Gaussian Splatting for Arbitrary Large-Scale Scene Rendering Xiaohan Zhang, Sitong Wang, et al. tl;dr: images as vertices & feature matches as edge->image connectivity graph->graph segmentation->spatial partition arxiv.org/abs/2506.08704

DGS-LRM: Real-Time Deformable 3D Gaussian Reconstruction From Monocular Videos Chieh Hubert Lin (Job Hunting For 2025), Zhaoyang Lv, Songyin Wu, Zhen Xu, Thu Nguyen-Phuoc, Hung-Yu Tseng, Julian Straub, Numair Khan, Lei Xiao, Ming-Hsuan Yang, Carl Yuheng Ren, Richard Newcombe, Zhao Dong, Zhengqin Li

UniForward: Unified 3D Scene and Semantic Field Reconstruction via Feed-Forward Gaussian Splatting from Only Sparse-View Images Qijian Tian, Xin Tan, Jingyu Gong, Yuan Xie, Lizhuang Ma tl;dr:dual-branch decoupled decoder->scene geometry+appearance and semantic; loss-guided view

RationalVLA: A Rational Vision-Language-Action Model with Dual System Wenxuan Song, Jiayi Chen, Wenxue Li, Xu He, Han Zhao, Pengxiang Ding Shiyan Su, Feilong Tang, Xuelian Cheng, Donglin Wang, Zongyuan Ge, Xinhu Zheng, Zhe Liu, Hesheng Wang, Yunhui Liu, Haoang Li tl;dr: dataset

LRSLAM: Low-rank Representation of Signed Distance Fields in Dense Visual SLAM System Hongbeen Park, Minjeong Park, Giljoo Nam, Jinkyu Kim tl;dr: tri-planes->Six-axis decomposition->six axis-aligned feature tensors->O(n) arxiv.org/abs/2506.10567

HeMoRa: Unsupervised Heuristic Consensus Sampling for Robust Point Cloud Registration Shaocheng Yan, Yiming Wang, Kaiyan Zhao, Pengcheng Shi, Zhenjun Zhao, Yongjun Zhang, Jiayuan Li tl;dr: A learnable sampling probability distribution for matches in robust estimation, no

Heading to #CVPR2025 today? Don’t miss our poster presentation! 🗓️ Fri, June 13 🕤 10:30 AM – 12:30 PM CDT 📍 Poster Session 1, Exhibit Hall D – Poster #111 Join us! #CVPR2025

Presenting today at #CVPR poster 81. Code is available at github.com/nianticlabs/mv… Want to try it on an iPhone video? On Android? On any other sequence you have? We got you covered. Check the repo.

We'll be resenting our #CVPR2025 Best Paper Award Candidate GlobustVP today! 🎤 Oral Session 4C: 3D Computer Vision 🗓️ Sat, June 14 (Today) 🕐 1:15 PM – 1:30 PM CDT 📍 Davidson Ballroom 🖼️ Poster Session 4 🗓️ Sat, June 14 (Today) 🕔 5:00 PM – 7:00 PM CDT 📍 Exhibit Hall D –

Anti-Aliased 2D Gaussian Splatting Mae Younes, Adnane Boukhayma tl;dr: Mip-Splatting->2DGS; world space flat smoothing kernel +object space Mip filter arxiv.org/abs/2506.11252

Linearly Solving Robust Rotation Estimation Yinlong Liu, Tianyu Huang, Zhi-Xin Yang tl;dr: rotation estimation problem->intersection between quaternion circles on the unit sphere surface in 4-dimensional space arxiv.org/abs/2506.11547