🎉 Thrilled to share our CVPR 2025 Award Candidate & Oral paper: 🔹 GlobustVP Convex Relaxation for Robust Vanishing Point Estimation in Manhattan World 🚀 A globally optimal & outlier-robust method for vanishing point (VP) estimation 🧱 Global optimality 💥 Tolerates up to

WildfireX-SLAM: A Large-scale Low-altitude RGB-D Dataset for Wildfire SLAM and Beyond Zhicong Sun, Jacqueline Lo, Jinxing Hu tl;dr: synthetic dataset https://t.co/XFwq6sUCir

CHECK OUT TODAY'S AI STORY- AI Cybersecurity Stocks to Watch and the Race for $234 billion Market by 2032 AI, more than any other technology, has empowered both sides of an industry, from the criminals and bad actors to the companies leading the cybersecurity battle. There is a

Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Denoising Diffusion Process Jiayi Chen, Wenxuan Song, Pengxiang Ding, Ziyang Zhou, Han Zhao, Feilong Tang, Donglin Wang, Haoang Li tl;dr: multiple modalities->single synchronous denoising trajectory

JOGS: Joint Optimization of Pose Estimation and 3D Gaussian Splatting Yuxuan Li, Tao Wang, Xianben Yang tl;dr: Lucas-Kanade 3D optical flow+reprojection errors->poses; standard differentiable rendering3DGS parameters https://t.co/0Nn4mdpzlG

PointSt3R: Point Tracking through 3D Grounded Correspondence Rhodri Guerrier, @AdamWHarley, @dimadamen tl;dr: fine-tune MASt3R with point matching loss and visibility head to handle dynamic scenes https://t.co/SqzPBNykY5

The Impact and Outlook of 3D Gaussian Splatting @Snosixtytwo tl;dr: in title https://t.co/pUdSgPN4SG

STG-Avatar: Animatable Human Avatars via Spacetime Gaussian Guangan Jiang, Tianzi Zhang, @Doong__Li, @zhenjun_zhao, Haoang Li, Mingrui Li, Hongyu Wang tl;dr: 3DGS-based framework for high-fidelity animatable human avatar reconstruction https://t.co/khIdwDcRVo

Epipolar Geometry Improves Video Generation Models @OKupyn, Fabian Manhardt, @fedassa, Christian Rupprecht tl;dr: Wan->diverse videos->Sampson epipolar error->relative reward signals->Flow-DPO->video generation rankings->3D-consistent videos https://t.co/u7bGcpFLwx

PlanarGS: High-Fidelity Indoor 3D Gaussian Splatting Guided by Vision-Language Planar Priors Xirui Jin, Renbiao Jin, @BoyingLi_LBY, @luckytsou, Wenxian Yu tl;dr: depth & normal priors from DUSt3R+semantic planar priors from Grounded SAM & geometric cues & cross-view fusion

Kineo: Calibration-Free Metric Motion Capture From Sparse RGB Cameras @charlesjvt, Pierre Raimbaud, Guillaume Lavoué tl;dr: confidence-driven reliable correspondences+graph-based global optimization https://t.co/Nv3kpod2at

AtlasGS: Atlanta-world Guided Surface Reconstruction with Implicit Structured Gaussians Xiyu Zhang, Chong Bao, Yipeng Chen, Hongjia Zhai, Yitong Dong, Hujun Bao, @ZhaopengCui, Guofeng Zhang tl;dr: implicit-structured+semantic+Atlanta-world guided planar regularized GS

RoGER-SLAM: A Robust Gaussian Splatting SLAM System for Noisy and Low-light Environment Resilience Huilin Yin, Zhaolin Yang, Linchuan Zhang, Gerhard Rigoll, @joebeatzhoven tl;dr: 3DGS rendering->low-pass filtering->fusion+adaptive tracking+CLIP-based enhancement

TWC-SLAM: Multi-Agent Cooperative SLAM with Text Semantics and WiFi Features Integration for Similar Indoor Environments Chunyu Li, Shoubin Chen, @Doong__Li, Weixing Xue, Qingquan Li tl;dr: text semantics & WiFi features->multi-agent cooperative SLAM https://t.co/Rmw7gxoFNF

PLANA3R: Zero-shot Metric Planar 3D Reconstruction via Feed-Forward Planar Splatting @liu_changkun, Bin Tan, Zeran Ke, Shangzhan Zhang, Jiachen Liu, Ming Qian, @NanXue7, Yujun Shen, Tristan Braud tl;dr: ViT-base; depth and normal->supervision; PlanarSplatting->rendered depth

Advances in 4D Representation: Geometry, Motion, and Interaction Mingrui Zhao, @Dumb_Thug, Kai Wang, @anvorain, Guangda Ji, Peter Chun, @arash_mham, @richardzhangsfu tl;dr: in title https://t.co/76BsKEXdlh

PoseCrafter: Extreme Pose Estimation with Hybrid Video Synthesis Qing Mao, Tianxin Huang, Yu Zhu, Jinqiu Sun, Yanning Zhang, @gimhee_lee tl;dr: DynamiCrafter+ViewCrafter->intermediate frames->ORB+RANSAC->top k frames https://t.co/55ZVRY2kFP

LightGlueStick: a Fast and Robust Glue for Joint Point-Line Matching Aidyn Ubingazhibov, Rémi Pautrat, @IagoSuarez0, @B1ueber2y, @mapo1, @visionviktor tl;dr: LightGlue+GlueStick+line message https://t.co/rMHFMuMV1i

GSPlane: Concise and Accurate Planar Reconstruction via Structured Representation Ruitong Gan, Junran Peng, Yang Liu, Chuanchen Luo, Qing Li, Zhaoxiang Zhang tl;dr: normals from Metric3D v2+planar regions from SAM->planar Gaussians https://t.co/iLcCBsGnjv

Initialize to Generalize: A Stronger Initialization Pipeline for Sparse-View 3DGS Feng Zhou, Wenkai Guo, Pu Cao, Zhicheng Zhang, Jianqin Yin tl;dr: initialization matters in sparse-view 3DGS https://t.co/QtkZXWmWud

PAGE-4D: Disentangled Pose and Geometry Estimation for 4D Perception Kaichen Zhou, Yuhan Wang, Grace Chen, Xinhai Chang, Gaspard Beaudouin, @fnzhan0507, Paul Pu Liang, Mengyu Wang tl;dr: dynamic VGGT https://t.co/NK7LEkKkr9

VAR-SLAM: Visual Adaptive and Robust SLAM for Dynamic Environments João Carlos Virgolino Soares, Gabriel Fischer Abati, Claudio Semini tl;dr: semantics->known dynamic objects; adaptive robust kernels->unknown dynamic objects https://t.co/DE0OoQpgBm