Profile avatar
ericzzj.bsky.social
PhD from CUHK. 3D vision, SLAM, SfM, Image Matching (https://github.com/ericzzj1989/Awesome-Image-Matching).
326 posts 1,168 followers 379 following
Prolific Poster
Posts 42 Comments 8

No Parameters, No Problem: 3D Gaussian Splatting without Camera Intrinsics and Extrinsics Dongbo Shi, Shen Cao, Lubin Fan, Bojian Wu, Jinhui Guo, Renjie Chen, Ligang Liu, Jieping Ye tl;dr: derive the gradients of focal length->back-propagation arxiv.org/abs/2502.19800

submitted 10 hours ago • 0 comments

RUBIK: A Structured Benchmark for Image Matching across Geometric Challenges Thibaut Loiseau, Guillaume Bourmaud tl;dr: 16.5K image pairs from nuScenes into 33 difficulty levels; three metrics-scene overlap, scale ratio, viewpoint angle; 14 methods arxiv.org/abs/2502.19955

submitted 10 hours ago • 0 comments

A2-GNN: Angle-Annular GNN for Visual Descriptor-free Camera Relocalization Yejun Zhang, Shuzhe Wang, Juho Kannala tl;dr: GoMatch with angle-annular convolution and modified outlier rejection arxiv.org/abs/2502.20036

submitted 10 hours ago • 0 comments

Efficient Gaussian Splatting for Monocular Dynamic Scene Rendering via Sparse Time-Variant Attribute Modeling Hanyang Kong, Xingyi Yang, Xinchao Wang tl;dr: separately processes time-invariant attributes, time-variant attributes, and motions arxiv.org/abs/2502.20378

submitted 10 hours ago • 0 comments

Compression in 3D Gaussian Splatting: A Survey of Methods, Trends, and Future Directions Muhammad Salman Ali, Chaoning Zhang, Marco Cagnazzo, Giuseppe Valenzise, Enzo Tartaglione, Sung-Ho Bae tl;dr: in title arxiv.org/abs/2502.19457

submitted 10 hours ago • 0 comments

Efficient and Distributed Large-Scale Point Cloud Bundle Adjustment via Majorization-Minimization Rundong Li, et al. tl;dr: upper surrogate cost->majorization-minimization decouples scan poses->linear time complexity no comparison with GlobalPointer arxiv.org/abs/2502.18801

submitted 1 day ago • 0 comments

LiDAR Registration with Visual Foundation Models Niclas Vödisch, Giovanni Cioffi, Marco Cannici, Wolfram Burgard, @davidescaramuzza.bsky.social tl;dr: DINOv2 features->point descriptors arxiv.org/abs/2502.19374

submitted 1 day ago • 0 comments

Does 3D Gaussian Splatting Need Accurate Volumetric Rendering? Adam Celarek, @grgkopanas.bsky.social, George Drettakis, Michael Wimmer, Bernhard Kerbl arxiv.org/abs/2502.19318

submitted 1 day ago • 1 comment

PromptMID: Modal Invariant Descriptors Based on Diffusion and Vision Foundation Models for Optical-SAR Image Matching Han Nie, et al. tl;dr: pre-trained VFMs+diffusion models+text prompts based on land use classification->modality-invariant descriptors arxiv.org/abs/2502.18104

submitted 2 days ago • 0 comments

S-Graphs 2.0 -- A Hierarchical-Semantic Optimization and Loop Closure for SLAM Hriday Bavle, Jose Luis Sanchez-Lopez, Muhammad Shaheer, @jcivera.bsky.social, Holger Voos tl;dr:S-Graphs+semantic+floor-based hierarchical loop closure+floor-&room-based hierarchical opt. arxiv.org/abs/2502.18044

submitted 2 days ago • 0 comments

MegaLoc: One Retrieval to Place Them All @berton-gabri.bsky.social Carlo Masone tl;dr: DINOv2-SALAD, trained on all available VPR datasets works very well. Code should at github.com/gmberton/Meg..., but not yet arxiv.org/abs/2502.17237

submitted 3 days ago • 1 comment

Dr. Splat: Directly Referring 3D Gaussian Splatting via Direct Language Embedding Registration Kim Jun-Seong, GeonU Kim, Kim Yu-Ji, Yu-Chiang Frank Wang, Jaesung Choe, Tae-Hyun Oh tl;dr: distil language knowledges into 3DGS arxiv.org/abs/2502.16652

submitted 3 days ago • 0 comments

Graph-Guided Scene Reconstruction from Images with 3D Gaussian Splatting Chong Cheng, Gaochao Song, Yiyang Yao, Qinzheng Zhou, Gangjian Zhang, Hao Wang tl;dr: select image pairs->camera pose+matching->octree initialization->camera graph->GS optimization arxiv.org/abs/2502.17377

submitted 3 days ago • 0 comments

GCC: Generative Color Constancy via Diffusing a Color Checker Chen-Wei Chang, Cheng-De Fan, Chia-Che Chang, Yi-Chen Lo, Yu-Chee Tseng, Jiun-Long Huang, Yu-Lun Liu tl;dr: pretrained stable-diffusion-2-inpainting->integrate color checker into image arxiv.org/abs/2502.17435

submitted 3 days ago • 0 comments

Improving Monocular Visual-Inertial Initialization with Structureless Visual-Inertial Bundle Adjustment Junlin Song, Antoine Richard, Miguel Olivares-Mendez tl;dr: IMU preintegration constraints+visual epipolar constraints->initial VIO states w/o 3D structure arxiv.org/abs/2502.16598

submitted 3 days ago • 0 comments

RGB-Only Gaussian Splatting SLAM for Unbounded Outdoor Scenes Sicheng Yu, Chong Cheng, Yifan Zhou, Xiaojun Yang, Hao Wang tl;dr: DUSt3R+3DGS arxiv.org/abs/2502.15633

submitted 4 days ago • 0 comments

Para-Lane: Multi-Lane Dataset Registering Parallel Scans for Benchmarking Novel View Synthesis Ziqian Ni, Sicong Du, Zhenghua Hou, Chenming Wu, Sheng Yang tl;dr: in title arxiv.org/abs/2502.15635

submitted 4 days ago • 0 comments

Hier-SLAM++: Neuro-Symbolic Semantic SLAM with a Hierarchically Categorical Gaussian Splatting Boying Li, Vuong Chi Hao, Peter J. Stuckey, Ian Reid, Hamid Rezatofighi arxiv.org/abs/2502.14931

submitted 4 days ago • 1 comment

DynamicGSG: Dynamic 3D Gaussian Scene Graphs for Environment Adaptation Luzhou Ge, Xiangyu Zhu, Zhuo Yang, Xuesong Li tl;dr: instance-level rendering+VLM semantic information->3D-2D object association->object-centric Gaussian map->LVLM->scene graphs arxiv.org/abs/2502.15309

submitted 4 days ago • 0 comments

pySLAM: An Open-Source, Modular, and Extensible Framework for SLAM Luigi Freda tl;dr: python implementation of a Visual SLAM pipeline, support monocular, stereo and RGBD cameras github.com/luigifreda/p... arxiv.org/abs/2502.11955

submitted 8 days ago • 0 comments

IM360: Textured Mesh Reconstruction for Large-scale Indoor Mapping with 360 Dongki Jung, Jaehoon Choi, Yonghan Lee, Dinesh Manocha tl;dr: spherical camera model->SfM; DebSDF; classical texture mapping->differentiable rendering->neural texture fine-tuning arxiv.org/abs/2502.12545

submitted 8 days ago • 0 comments

High-Fidelity Novel View Synthesis via Splatting-Guided Diffusion Xiang Zhang, Yang Zhang, Lukas Mehl, Markus Gross, Christopher Schroers tl;dr: pixel-splatting-guided video diffusion model; aligned synthesis+texture bridge arxiv.org/abs/2502.12752

submitted 8 days ago • 0 comments

GS-GVINS: A Tightly-integrated GNSS-Visual-Inertial Navigation System Augmented by 3D Gaussian Splatting Zelin Zhou, Saurav Uprety, Shichuang Nie, Hongzhou Yang tl;dr: GICI-LIB+3DGS arxiv.org/abs/2502.10975

submitted 8 days ago • 0 comments

FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views Shangzhan Zhang et 7 al tl;dr: CroCo->regress pose -> Dust3r-like geometry estimation -> refine as 3DGS. No IMC eval. arxiv.org/abs/2502.12138

submitted 10 days ago • 1 comment

DenseSplat: Densifying Gaussian Splatting SLAM with Neural Radiance Prior Mingrui Li, Shuhong Liu, Tianchen Deng, Hongyu Wang tl;dr: RGB-D->Instant-NGP->point sampling->initialize Gaussian primitives->GS map arxiv.org/abs/2502.09111

submitted 14 days ago • 0 comments

Latent Radiance Fields with 3D-aware 2D Representations Chaoyi Zhou, Xi Liu, Feng Luo, Siyu Huang tl;dr: correspondence-aware autoencoding->3D-aware 2D representations->latent radiance field->3D latent fields->VAE-Radiance Field arxiv.org/abs/2502.09613

submitted 14 days ago • 0 comments

LIR-LIVO: A Lightweight,Robust LiDAR/Vision/Inertial Odometry with Illumination-Resilient Deep Features Shujie Zhou, Zihao Wang, Xinye Dai, Weiwei Song, Shengfeng Gu tl;dr: FAST-LIO2+SuperPoint+LightGlue arxiv.org/abs/2502.08676

submitted 14 days ago • 0 comments

Self-Calibrating Gaussian Splatting for Large Field of View Reconstruction Youming Deng, Wenqi Xian, Guandao Yang, Leonidas Guibas, Gordon Wetzstein, Steve Marschner, Paul Debevec arxiv.org/abs/2502.09563

submitted 14 days ago • 1 comment

Flow Distillation Sampling: Regularizing 3D Gaussians with Pre-trained Matching Priors Lin-Zhuo Chen, Kangjie Liu, Youtian Lin, Siyu Zhu, Zhihao Li, Xun Cao, Yao Yao tl;dr: pre-trained optical flow model+camera sampling->geometric information->3DGS arxiv.org/abs/2502.07615

submitted 16 days ago • 0 comments

Matrix3D: Large Photogrammetry Model All-in-One Yuanxun Lu, Jingyang Zhang, Tian Fang, Jean-Daniel Nahmias, Yanghai Tsin, Long Quan, Xun Cao, Yao Yao, Shiwei Li tl;dr: DiT+mask learning; camera poses->Plücker rays; 3D structures->2.5D depth maps arxiv.org/abs/2502.07685

submitted 16 days ago • 1 comment

Accelerating Outlier-robust Rotation Estimation by Stereographic Projection Taosi Xu, Yinlong Liu, Xianbo Wang, Zhi-Xin Yang arxiv.org/abs/2502.06337

submitted 16 days ago • 1 comment

PINGS: Gaussian Splatting Meets Distance Fields within a Point-Based Implicit Neural Map Yue Pan, Xingguang Zhong, Liren Jin, Louis Wiesmann, Marija Popović, Jens Behley, Cyrill Stachniss tl;dr: PIN-SLAM+Scaffold-GS->LiDAR-visual SLAM arxiv.org/abs/2502.05752

submitted 16 days ago • 0 comments

MeshSplats: Mesh-Based Rendering with Gaussian Splatting Initialization Rafał Tobiasz, Grzegorz Wilczyński, Marcin Mazur, Sławomir Tadeja, Przemysław Spurek tl;dr: flat Gaussians->disjoint meshes->ray tracing->mesh-based representation arxiv.org/abs/2502.07754

submitted 16 days ago • 0 comments

PoI: Pixel of Interest for Novel View Synthesis Assisted Scene Coordinate Regression Feifei Li, Qi Song, Chi Zhang, Hui Shuai, Rui Huang tl;dr: 3D-to-2D projection error->filtering; SCR with sparse inputs arxiv.org/abs/2502.04843

submitted 18 days ago • 0 comments

AuraFusion360: Augmented Unseen Region Alignment for Reference-based 360° Unbounded Scene Inpainting Chung-Ho Wu, Yang-Jung Chen, Ying-Huan Chen, Jie-Ying Lee, Bo-Hsu Ke, Chun-Wei Tuan Mu, Yi-Chuan Huang, Chin-Yang Lin, @cmhungsteve.bsky.social, Yen-Yu Lin, Yu-Lun Liu

submitted 18 days ago • 1 comment

Joint State and Noise Covariance Estimation Kasra Khosoussi, Iman Shames tl;dr: analytical expressions for (conditionally) optimal noise covariance matrix under various structural constraints on the true covariance matrix arxiv.org/abs/2502.04584

submitted 18 days ago • 0 comments

Building Rome with Convex Optimization Haoyu Han, Heng Yang tl;dr: 2D keypoints+pretrained depth->scaled BA->QCQP->empirically tight convex SDR->Burer-Monteiro factorization+CUDA-based trust-region Riemannian optimizer arxiv.org/abs/2502.04640

submitted 18 days ago • 0 comments

High-Speed Dynamic 3D Imaging with Sensor Fusion Splatting Zihao Zou, Ziyuan Qu, Xi Peng, Vivek Boominathan, Adithya Pediredla, Praneeth Chakravarthula tl;dr: RGB+depth+event cameras & deformable 3DGS arxiv.org/abs/2502.04630

submitted 18 days ago • 0 comments

SC-OmniGS: Self-Calibrating Omnidirectional Gaussian Splatting Huajian Huang, Yingshu Chen, Longwei Li, Hui Cheng, Tristan Braud, Yajie Zhao, Sai-Kit Yeung tl;dr: pose-free OmniGS arxiv.org/abs/2502.04734

submitted 18 days ago • 0 comments

Fillerbuster: Multi-View Scene Completion for Casual Captures @ethanjohnweber.bsky.social, Norman Müller, Yash Kant, Vasu Agrawal, Michael Zollhöfer, Angjoo Kanazawa, @cr333.bsky.social arxiv.org/abs/2502.05175

submitted 18 days ago • 1 comment

sshELF: Single-Shot Hierarchical Extrapolation of Latent Features for 3D Reconstruction from Sparse-Views Eyvaz Najafli, @mariusm.bsky.social, Sebastian Bernhard, Thomas Brox, @andreasgeiger.bsky.social arxiv.org/abs/2502.04318

submitted 21 days ago • 1 comment

SiLVR: Scalable Lidar-Visual Radiance Field Reconstruction with Uncertainty Quantification @taoyifu.bsky.social, @mauricefallon.bsky.social tl;dr: Nerfacto+lidar; perturbation field in BayesRays->epistemic uncertainty; graph partitioning->per-image visibility->submapping arxiv.org/abs/2502.02657

submitted 22 days ago • 0 comments