Zhenjun Zhao@zhenjun_zhao

Postdoc @unizar | PhD @CUHKofficial | 3D vision, SLAM, Image matching (github.com/ericzzj1989/Aweso…)

 Zaragoza
ericzzj1989.github.io/
Joined September 2022
🚀 Thrilled to share our survey paper: Advances in Global Solvers for 3D Vision The FIRST systematic survey unifying global optimization for 3D vision, covering 400+ papers across 60+ years (1960–2025) 3 paradigms × 10 tasks × global solutions 📄 Paper: arxiv.org/abs/2602.14662 💻 Paper List & Tutorial Code : github.com/ericzzj1989/Aweso… 1/7
2
17
72
15,882
General Neural Gauge Fields Fangneng Zhan, @LingjieLiu1 , @AdamKortylewski , Christian Theobalt tl;dr: jointly end-to-end learn gauge transformation and neural fields arxiv.org/pdf/2305.03462.pdf
1
5
20
15,555
🎉 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 70% outliers ⚡ No learning, fast runtime 📄 Paper: arxiv.org/abs/2505.04788 💻 Code: github.com/WU-CVGL/GlobustVP 1/
5
51
371
41,604
GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting Chi Yan, Delin Qu, Dong Wang, Dan Xu, Zhigang Wang, Bin Zhao, Xuelong Li tl;dr: 3D Gaussian meets SLAM arxiv.org/pdf/2311.11700.pdf
1
47
241
25,949
BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects Bowen Wen, et al. tl;dr: object-level SLAM, online pose graph optimization + Neural Object Field #CVPR2023 arxiv.org/pdf/2303.14158.pdf
2
46
215
211,314
Compact 3D Gaussian Representation for Radiance Field Joo Chan Lee, Daniel Rho, Xiangyu Sun, Jong Hwan Ko, Eunbyung Park tl;dr: volume-based masking reduces the number of Gaussians; grid-based neural field->view-dependent colors arxiv.org/pdf/2311.13681.pdf
2
34
226
30,091
Blendify -- Python rendering framework for Blender @guzov_vladimir, @ptrvilya, @GerardPonsMoll1 tl;dr: high-level API for creating and rendering scenes with Blender github.com/ptrvilya/blendify arxiv.org/pdf/2410.17858
3
27
199
9,639
4D Gaussian Splatting for Real-Time Dynamic Scene Rendering Guanjun Wu, Taoran Yi, Jiemin Fang, Lingxi Xie, Xiaopeng Zhang, Wei Wei, Wenyu Liu, Qi Tian, Xinggang Wang tl;dr: deformation field->Gaussian motions+shape deformations arxiv.org/pdf/2310.08528.pdf
29
183
15,538
Learning with 3D rotations, a hitchhiker's guide to SO(3) A. René Geist, Jonas Frey, Mikel Zobro, Anna Levina, Georg Martius tl;dr: how to select suitable SO(3) for nn regression? SO(N)->Lipschitz continuity of the function->representation space arxiv.org/pdf/2404.11735.pdf
4
30
175
33,223
3D Representation Methods: A Survey Zhengren Wang tl;dr: in title arxiv.org/pdf/2410.06475
1
31
177
9,733
3D Reconstruction with Spatial Memory @Hengyi1999, @LourdesAgapito tl;dr: DUSt3R+memory encoder->pointmaps in a global coordinate system; previous predicted pointmap->memory encoder->memory key&value+memory query from target decoder ->reference decoder arxiv.org/pdf/2408.16061
2
27
168
10,973
NeRFs: The Search for the Best 3D Representation Ravi Ramamoorthi tl;dr: review of NeRF author of NeRF arxiv.org/pdf/2308.02751.pdf
37
168
25,543
3D Gaussian as a New Vision Era: A Survey Ben Fei, Jingyi Xu, Rui Zhang, Qingyuan Zhou, Weidong Yang, Ying He tl;dr: 3D Gaussian Splatting survey arxiv.org/pdf/2402.07181.pdf
1
45
171
11,070
Cameras as Rays: Pose Estimation via Ray Diffusion Jason Y. Zhang, Amy Lin, Moneish Kumar, Tzu-Hsuan Yang, @RamananDeva, @shubhtuls tl;dr: predict a separate ray passing through each patch in each input image->least-square->camera extrinsics&intrinsics arxiv.org/pdf/2402.14817.pdf
3
33
166
10,342
How NeRFs and 3D Gaussian Splatting are Reshaping SLAM: a Survey @fabiotosi92, Youmin Zhang, Ziren Gong, Erik Sandström, @s_matt, @Martin_R_Oswald, @mattpoggi tl;dr: SLAM in radiance fields arxiv.org/pdf/2402.13255.pdf
1
35
166
10,388
A Survey on 3D Gaussian Splatting Guikun Chen, Wenguan Wang tl;dr: in title arxiv.org/pdf/2401.03890.pdf
1
25
161
10,386
MESA: Matching Everything by Segmenting Anything Yesheng Zhang, Xu Zhao tl;dr: SAM->multi-relational graph->AMRF and ABN->energy minimization->Graph Cut->area matching->point matching arxiv.org/pdf/2401.16741.pdf
2
28
152
15,837
Dropping the D: RGB-D SLAM Without the Depth Sensor Mert Kiray, Alican Karaomer, @BusamBenjamin tl;dr: DAv2+YOLOv11+Key.Net+ORB->static/dynamic processing->ORB-SLAM3 arxiv.org/abs/2510.06216
2
13
154
13,023
Depth Anything V2 Lihe Yang, Bingyi Kang, Zilong Huang, Zhen Zhao, Xiaogang Xu, Jiashi Feng, @HengshuangZhao tl;dr: use synthetic images to train teacher; unlabeled real images->trained teacher->pseudo-labeled real images->student models arxiv.org/pdf/2406.09414
2
20
150
8,115
Cameras as Relative Positional Encoding @ruilong_li, @brenthyi, @JunchenLiu77, @hangg70, @YiMaTweets, @akanazawa tl;dr: study absolute raymap and relative SE(3) encoding; viewing frustums->intrinsics and extrinsics->transformer’s self-attention arxiv.org/abs/2507.10496
2
25
148
7,419
MASt3R-Fusion: Integrating Feed-Forward Visual Model with IMU, GNSS for High-Functionality SLAM Yuxuan Zhou, Xingxing Li, Shengyu Li, Zhuohao Yan, Chunxi Xia, Shaoquan Feng tl;dr: MASt3R-SLAM+IMU+GNSS arxiv.org/abs/2509.20757
2
25
147
6,386
Segment Anything Model is a Good Teacher for Local Feature Learning Jingqian Wu, Rongtao Xu, Zach Wood-Doughty, Changwei Wang tl;dr: SAM->semantic relationship/grouping+edge map->distill->local feature browse.arxiv.org/pdf/2309.16…
2
37
142
13,097
VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequences Kai Deng, Zexin Ti, Jiawei Xu, Jian Yang, Jin Xie tl;dr: sequence->overlapping chunks->alignment and loop closure with confidence kind of same with large-scale GS ORB-SLAM2 is still powerful arxiv.org/abs/2507.16443
1
19
145
18,397
MCMC: Bridging Rendering, Optimization and Generative AI Gurprit Singh, @wenzeljakob tl;dr: in title arxiv.org/abs/2510.09078
24
143
8,598
Notes on Kalman Filter (KF, EKF, ESKF, IEKF, IESKF) Gyubeom Edward Im tl;dr: in title arxiv.org/pdf/2406.06427
3
34
140
9,689
DepthSplat: Connecting Gaussian Splatting and Depth @haofeixu, @songyoupeng, @FangjinhuaWang, @hermannsblum, @majti89, @AutoVisionGroup, @mapo1 tl;dr: MVSplat+Depth Anything->GS+depth estimation arxiv.org/pdf/2410.13862
2
14
136
6,999
Viser: Imperative, Web-based 3D Visualization in Python @brenthyi, @ChungMinKim, @justkerrding, Gina Wu, Rebecca Feng, Anthony Zhang, @jonaskulhanek, @redstone_hong, @YiMaTweets, Matthew Tancik, @akanazawa tl;dr: in title arxiv.org/abs/2507.22885
22
143
6,682
SLAM-Former: Putting SLAM into One Transformer Yijun Yuan, Zhuoguang Chen, Kenan Li, Weibang Wang, @zhaohang0124 tl;dr: e frontend and the backend promote each other with transformer arxiv.org/abs/2509.16909
2
19
136
6,393
Diffusion Models in 3D Vision: A Survey Zhen Wang, Dongyuan Li, @JiangRenhe tl;dr: in title arxiv.org/pdf/2410.04738
37
135
6,528
Visual Odometry with Transformers @vyuga3d, @kienduynguyen94, @theogevers, @cgmsnoek, @Martin_R_Oswald tl;dr: DUSt3R encoder->image token embeddings (+camera embeddings)->time/space attention decoder->rotation+translation arxiv.org/abs/2510.03348
21
134
5,448
Grounding Image Matching in 3D with MASt3R @Vinc3nt_Leroy, Yohann Cabon, @JeromeRevaud tl;dr: DUSt3R+new head with dense local features output+InfoNCE loss; in 3D space; high-resolution (coarse-to-fine matching+fast reciprocal matching) arxiv.org/pdf/2406.09756
3
21
133
10,108
MEt3R: Measuring Multi-View Consistency in Generated Images Mohammad Asim, Christopher Wewer, @wimmer_th, Bernt Schiele, @janericlenssen tl;dr: DUSt3R-based method to measure multi-view consistency of generated views without given camera poses arxiv.org/abs/2501.06336
16
130
4,564
3D Gaussian Splatting: Survey, Technologies, Challenges, and Opportunities Yanqi Bao, Tianyu Ding, Jing Huo, Yaoli Liu, Yuxin Li, Wenbin Li, Yang Gao, Jiebo Luo tl;dr: in title github.com/qqqqqqy0227/aweso… arxiv.org/pdf/2407.17418
21
129
5,728
360ORB-SLAM: A Visual SLAM System for Panoramic Images with Depth Completion Network Yichen Chen, et al. tl;dr: panoramic image->features->panoramic triangulation->depth completion network->dense panoramic depth map arxiv.org/pdf/2401.10560.pdf
20
125
37,883
GaussianShader: 3D Gaussian Splatting with Shading Functions for Reflective Surfaces Yingwenqi Jiang, et al. tl;dr: simplified shading function->rendering equation; shortest axis directions of 3D Gaussians->normal estimation arxiv.org/pdf/2311.17977.pdf
18
128
8,966
A New Split Algorithm for 3D Gaussian Splatting Qiyuan Feng, Gengchen Cao, Haoxiang Chen, Tai-Jiang Mu, Ralph R. Martin, Shi-Min Hu tl;dr: an 𝑁-dimensional Gaussian->two independent 𝑁-dimensional Gaussians->closed-form solution arxiv.org/pdf/2403.09143.pdf
1
18
124
5,881
NeRF in Robotics: A Survey Guangming Wang, Lei Pan, @songyoupeng, Shaohui Liu, Chenfeng Xu, Yanzi Miao, Wei Zhan, Masayoshi Tomizuka, @mapo1, Hesheng Wang tl;dr: in title arxiv.org/pdf/2405.01333
1
28
126
9,490
LightGlue: Local Feature Matching at Light Speed @PhilippCSE, @pesarlin, @mapo1 tl;dr: exit mechanism+point prune between each layer in SuperGlue->adaptive stopping mechanism->fast inference of SuperGlue github.com/cvg/LightGlue arxiv.org/pdf/2306.13643.pdf
2
22
123
23,100
GaussianObject: Just Taking Four Images to Get A High-Quality 3D Object with Gaussian Splatting Chen Yang, Sikuang Li, et al. tl;dr: represent and render 3D object with Gaussian splatting, that achieves high rendering quality with only 4 input images arxiv.org/pdf/2402.10259.pdf
1
21
128
8,998
NARUTO: Neural Active Reconstruction from Uncertain Target Observations Ziyue Feng, Huangying Zhan, Zheng Chen, Qingan Yan, Xiangyu Xu, Changjiang Cai, Bing Li, Qilun Zhu, Yi Xu tl;dr: reconstruction->uncertainty learning->multi-resolution hash-grid arxiv.org/pdf/2402.18771.pdf
3
27
125
11,493
MATCHA:Towards Matching Anything @FeiXue94, @s_elflein, @lealtaixe, @QunjieZhou tl;dr: diffusion model->semantic+geometric features->transformer-based fusion->enhanced diffusion features->w/ DINOv2->unified feature->geometric/semantic/temporal matching arxiv.org/abs/2501.14945
1
29
123
7,651
EC3R-SLAM: Efficient and Consistent Monocular Dense SLAM with Feed-Forward 3D Reconstruction Lingxiang Hu, Naima Ait Oufroukh, Fabien Bonardi, Raymond Ghandour tl;dr: XFeat for tracking; VGGT for mapping arxiv.org/abs/2510.02080
20
125
5,150
4D Gaussian Splatting: Towards Efficient Novel View Synthesis for Dynamic Scenes Yuanxing Duan, Fangyin Wei, Qiyu Dai, Yuhang He, Wenzheng Chen, Baoquan Chen tl;dr: 4D spatial-temporal Gaussian ellipsoids sliced with different time queries->3D dynamics arxiv.org/pdf/2402.03307.pdf
25
118
17,535
D^2USt3R: Enhancing 3D Reconstruction with 4D Pointmaps for Dynamic Scenes Jisang Han, Honggyu An, Jaewoo Jung, Takuya Narihira, Junyoung Seo, Kazumi Fukuda, Chaehyun Kim, Sunghwan Hong, Yuki Mitsufuji, Seungryong Kim tl;dr: DUSt3R with 4D pointmaps arxiv.org/abs/2504.06264
15
118
5,305
NeRF-Supervised Deep Stereo Fabio Tosi, Alessio Tonioni, Daniele De Gregorio, Matteo Poggi tl;dr: neural rendering+user-collected images->stereo training data; rendered stereo triplets+depth maps->occlusions and enhance fine details #CVPR2023 arxiv.org/pdf/2303.17603.pdf
2
21
109
12,055
SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering Antoine Guédon, Vincent Lepetit tl;dr: gaussians->surface of the mesh arxiv.org/pdf/2311.12775.pdf
13
115
13,638
RTGS: Enabling Real-Time Gaussian Splatting on Mobile Devices Using Efficiency-Guided Pruning and Foveated Rendering Weikai Lin, Yu Feng, @yzhu88 tl;dr: different points contribute differently; Foveated Rendering->PBNR arxiv.org/pdf/2407.00435
1
15
113
4,945
FastVGGT: Training-Free Acceleration of Visual Geometry Transformer You Shen, Zhipeng Zhang, Yansong Qu, Liujuan Cao tl;dr: token merging->VGGT without dense global attention arxiv.org/abs/2509.02560
1
27
114
5,825
AnyLoc: Towards Universal Visual Place Recognition Nikhil Keetha, Avneesh Mishra, Jay Karhade, Krishna Murthy Jatavallabhula, Sebastian Scherer, Madhava Krishna, Sourav Garg tl;dr: foundation model features+unsupervised feature aggregation arxiv.org/pdf/2308.00688.pdf
2
33
108
11,489
From NeRFs to Gaussian Splats, and Back Siming He, Zach Osman, Pratik Chaudhari tl;dr: NeRF+GS arxiv.org/pdf/2405.09717
2
24
110
6,443
Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass @jed_yang, @iamsashasax, Kevin J. Liang, @HenaffMikael, Hao Tang, @AngCao3, Joyce Chai, @_kainoa_, Matt Feiszli tl;dr: multi-view version of DUSt3R; over 1000 images arxiv.org/abs/2501.13928
3
17
109
4,269
GARField: Group Anything with Radiance Fields Chung Min Kim, Mingxuan Wu, Justin Kerr, Ken Goldberg, Matthew Tancik, @akanazawa tl;dr: hierarchical grouping in 3D by training a scale-conditioned affinity field from multi-level masks arxiv.org/pdf/2401.09419.pdf
16
111
7,519
MUSt3R: Multi-view Network for Stereo 3D Reconstruction Yohann Cabon, Lucas Stoffl, Leonid Antsfeld, @kgcs96, Boris Chidlovskii, @JeromeRevaud, @Vinc3nt_Leroy tl;dr: make DUSt3R symmetric and iterative+multi-layer memory mechanism->multi-view DUSt3R arxiv.org/abs/2503.01661
1
10
109
5,021
Learning Unified Representation of 3D Gaussian Splatting Yuelin Xin, Yuheng Liu, Xiaohui Xie, Xinke Li tl;dr: Gaussian primitive->continuous field defined on iso-probability surface->submanifold field; variational autoencoder+optimal transport-based Manifold Distance metric arxiv.org/abs/2509.22917
2
15
109
6,435
CuSfM: CUDA-Accelerated Structure-from-Motion Jingrui Yu, Jun Liu, Kefei Ren, @Joydeepb_robots, Rurui Ye, Keqiang Wu, Chirag Majithia, Di Zeng tl;dr: in title; ALIKED+LightGlue arxiv.org/abs/2510.15271
2
21
110
24,770
GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting Yiwen Chen, Zilong Chen, Chi Zhang, Feng Wang, Xiaofeng Yang, Yikai Wang, Zhongang Cai, Lei Yang, Huaping Liu, Guosheng Lin tl;dr: Gaussian semantic tracing->editing control arxiv.org/pdf/2311.14521.pdf
22
104
9,368
SpatialTracker: Tracking Any 2D Pixels in 3D Space Yuxi Xiao, Qianqian Wang, Shangzhan Zhang, Nan Xue, @pengsida, Yujun Shen, @XiaoweiZhou5 tl;dr: frame->triplane encoder->triplane feature maps->transformer+ARAP constraint->3D trajectories arxiv.org/pdf/2404.04319.pdf
2
18
103
7,569
The Importance of Coordinate Frames in Dynamic SLAM Jesse Morris, Yiduo Wang, Viorela Ila tl;dr: world/object-centric formulation in factor-graph-based Dynamic SLAM framework (use GTSAM) Really interesting! arxiv.org/pdf/2312.04031.pdf
1
23
102
7,854
Self-supervised Learning of Neural Implicit Feature Fields for Camera Pose Refinement Maxime Pietrantoni, Gabriela Csurka, @martinhu, @SattlerTorsten tl;dr: jointly learn NeRF (geometry)+3D dense feature field+2D feature extractor arxiv.org/pdf/2406.08463
1
10
105
5,399
gsplat: An Open-Source Library for Gaussian Splatting @vickie_ye_, @ruilong_li, Justin Kerr, @_maturk, Brent Yi, @pan_zhuoyang, @oseiskar, Jianbo Ye, Jeffrey Hu, Matthew Tancik, @akanazawa tl;dr: in title docs.gsplat.studio/ github.com/nerfstudio-projec… arxiv.org/pdf/2409.06765
1
15
101
7,264
Back on Track: Bundle Adjustment for Dynamic Scene Reconstruction @wrchen530, @zhang_ganlin, @felixwimbauer, Rui Wang, @neekans, Andrea Vedaldi, Daniel Cremers tl;dr: learning-based 3D point tracker decouples camera and object-based motion arxiv.org/abs/2504.14516
20
105
4,716
Mono3R: Exploiting Monocular Cues for Geometric 3D Reconstruction Wenyu Li, Sidun Liu, Peng Qiao, Yong Dou tl;dr: DUSt3R+MoGe+global Sim(3) alignment+monocular priors with monocular priors arxiv.org/abs/2504.13419
2
12
101
5,199
Breaking the Frame: Image Retrieval by Visual Overlap Prediction @weitong8591, @PhilippCSE, @matas_jiri, @majti89 arxiv.org/pdf/2406.16204
3
26
101
15,248
Neural Radiance Fields (NeRFs): A Review and Some Recent Developments Mohamed Debbagh tl;dr: review the original NeRF framework arxiv.org/pdf/2305.00375.pdf
1
26
99
7,159
RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes @fangli_kevin, @HaoZhang623, Narendra Ahuja tl;dr: no additional GT supervision arxiv.org/abs/2509.15123
9
99
4,864
Anything-3D: Towards Single-view Anything Reconstruction in the Wild Qiuhong Shen, Xingyi Yang, Xinchao Wang tl;dr: BLIP+SAM+stable diffusion github.com/Anything-of-anyth… arxiv.org/pdf/2304.10261.pdf
2
24
101
8,628
RANSAC Back to SOTA: A Two-stage Consensus Filtering for Real-time 3D Registration Pengcheng Shi, et al. tl;dr: length constraints->one-point RANSAC; angular consistency->two-point RANSAC; three-point RANSAC+IRLS after one-point and two-point RANSAC arxiv.org/pdf/2410.15682
2
21
101
5,578
Can Generative Video Models Help Pose Estimation? @ruojin8, @jasonyzhang2, @philipphenzler, @zhengqi_li, @Jimantha, @rmbrualla arxiv.org/abs/2412.16155
1
12
102
7,349
Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and Reconstruction Hansheng Chen, Jiatao Gu, Anpei Chen, Wei Tian, Zhuowen Tu, Lingjie Liu, Hao Su tl;dr: single-stage training jointly learns NeRF reconstruction and diffusion model arxiv.org/pdf/2304.06714.pdf
2
25
98
11,016
COLMAP-Free 3D Gaussian Splatting Yang Fu, Sifei Liu, Amey Kulkarni, Jan Kautz, Alexei A. Efros, @xiaolonw tl;dr: local 3D Gaussians->each image->relative pose; global 3D Gaussians->expansion of the 3D Gaussians->whole scene arxiv.org/pdf/2312.07504.pdf
1
17
94
8,690
nvTorchCam: An Open-source Library for Camera-Agnostic Differentiable Geometric Vision @daniel_lichy, Hang Su, Abhishek Badki, @jankautz, @0razio tl;dr: in title github.com/NVlabs/nvTorchCam arxiv.org/pdf/2410.12074
3
17
98
5,641
Deep Learning for Visual Localization and Mapping: A Survey Changhao Chen, Bing Wang, Chris Xiaoxuan Lu, Niki Trigoni, Andrew Markham tl;dr: a comprehensive survey, and propose a taxonomy for the localization and mapping methods using deep learning arxiv.org/pdf/2308.14039.pdf
1
29
99
8,998
VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold Dominic Maggio, @hyungtae_lim, @lucacarlone1 tl;dr: VGGT->multiple submaps->projective ambiguity->submap alignment->factor graph optimization on the SL(4) manifold (Special Linear, 4 × 4 homography matrix) arxiv.org/abs/2505.12549
2
21
96
6,485
GaussianPro: 3D Gaussian Splatting with Progressive Propagation Kai Cheng, @xxlong0, Kaizhi Yang, Yao Yao, Wei Yin, Yuexin Ma, Wenping Wang, Xuejin Chen tl;dr: depth and normal+classical patch matching->new Gaussians arxiv.org/pdf/2402.14650.pdf
1
13
96
6,495
FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descent @omcamsmith, @DavidCharatan, @_atewari, @vincesitzmann tl;dr: min of LS objective->optical flow (depth&intrinsics&poses) & correspondences (optical flow&point tracking) arxiv.org/pdf/2404.15259.pdf
2
17
96
6,989
Relightable 3D Gaussian: Real-time Point Cloud Relighting with BRDF Decomposition and Ray Tracing Jian Gao, Chun Gu, et al. tl;dr: material & lighting decomposition for 3DGS; bounding volume hierarchy->point-based ray-tracing arxiv.org/pdf/2311.16043.pdf
19
93
6,391
SupeRANSAC: One RANSAC to Rule Them All @majti89 tl;dr: why RANSAC work well for different vision problems? ->answer->implementation details and problem-specific optimizations arxiv.org/abs/2506.04803
1
16
98
4,834
Hier-SLAM++: Neuro-Symbolic Semantic SLAM with a Hierarchically Categorical Gaussian Splatting @BoyingLi_LBY, Vuong Chi Hao, Peter J. Stuckey, Ian Reid, @HamidRezatofigh arxiv.org/abs/2502.14931
1
10
96
4,761
1-Lipschitz Neural Distance Fields Guillaume Coiffier, Louis Bethune tl;dr: 1-Lipschitz neural network+hinge-Kantorovitch-Rubinstein loss arxiv.org/pdf/2407.09505
1
19
101
5,938
FastMap: Revisiting Dense and Scalable Structure from Motion Jiahao Li, @__whc__, @mzubairirshad, @vslevic, Matthew R. Walter, Vitor Campagnolo Guizilini, @gregshakh tl;dr: replace BA with epipolar error+IRLS; fully PyTorch implementation arxiv.org/abs/2505.04612
1
21
95
7,228
3DGS-LM: Faster Gaussian-Splatting Optimization with Levenberg-Marquardt @LukasHollein, @BozicAljaz, @MZollhoefer , @MattNiessner tl;dr: replace ADAM with LM; 3DGS rasterizer+custom CUDA kernels+caching data structure->Jacobian-vector products->PCG arxiv.org/pdf/2409.12892
3
16
96
5,312
CAT3D: Create Anything in 3D with Multi-View Diffusion Models @RuiqiGao, @holynski_, @philipphenzler, Arthur Brussee, @rmbrualla, @_pratul_, @jon_barron, @poolio arxiv.org/pdf/2405.10314
4
21
97
8,576
VGGT: Visual Geometry Grounded Transformer @jianyuan_wang, @MinghaoChen23, @n_karaev, Andrea Vedaldi, Christian Rupprecht, @davnov134 tl;dr: image->DINO->image tokens (w/ camera tokens)->frame-wise&global self attention->camera&DPT head->3D attributes arxiv.org/abs/2503.11651
1
13
96
3,830
Shape of Motion: 4D Reconstruction from a Single Video @QianqianWang5, @vickie_ye_, @hangg70, @jacobaustin132, @zhengqi_li, @akanazawa tl;dr: 3D Gaussians motion->shared SE(3) motion bases; monodepth+2D track arxiv.org/pdf/2407.13764
2
14
96
5,663
MILo: Mesh-In-the-Loop Gaussian Splatting for Detailed and Efficient Surface Reconstruction @antoine_guedon, Diego Gomez, Nissim Maruani, Bingchen Gong, @GDrettakis, Maks Ovsjanikov tl;dr: generate a mesh at every training iteration from a set of points entangled with the Gaussians, Gaussian Pivots arxiv.org/abs/2506.24096
1
13
95
5,434
VastGaussian: Vast 3D Gaussians for Large Scene Reconstruction Jiaqi Lin, Zhihao Li, Xiao Tang, Jianzhuang Liu, Shiyong Liu, Jiayue Liu, Yangdi Lu, Xiaofei Wu, Songcen Xu, Youliang Yan, Wenming Yang tl;dr: large scene->partitioning->multiple cells arxiv.org/pdf/2402.17427.pdf
14
98
6,593
OmniGlue: Generalizable Feature Matching with Foundation Model Guidance @hanwenjiang1, Arjun Karpur, Bingyi Cao, @qixing_huang, @andrefaraujo tl;dr: DINOv2->SG/LoFTR; DINOv2->similarities between keypoints->intra&inter-image graphs->self&cross-attention arxiv.org/pdf/2405.12979
4
18
97
7,509
Flexible Techniques for Differentiable Rendering with 3D Gaussians Leonid Keselman, Martial Hebert tl;dr: 3D Gaussians->Fuzzy Metaballs->shape reconstruction arxiv.org/pdf/2308.14737.pdf
1
18
95
8,011
GigaSLAM: Large-Scale Monocular SLAM with Hierachical Gaussian Splats Kai Deng, Jian Yang, @ShenlongWang, Jin Xie tl;dr: hierarchical sparse voxel representation+LoD rendering arxiv.org/abs/2503.08071
1
17
92
4,421
Revisit Anything: Visual Place Recognition via Image Segment Retrieval Kartik Garg, Sai Shubodh Puligilla, Shishir Kolathaya, Madhava Krishna, @sourav_garg_ tl;dr: encoding and searching for image segments instead of the whole images arxiv.org/pdf/2409.18049
4
16
93
7,149
Nuvo: Neural UV Mapping for Unruly 3D Representations @_pratul_, Stephan J. Garbin, @dorverbin, @jon_barron, @BenMildenhall tl;dr: neural field->UV mapping; sample visible points that affect the scene’s appearance arxiv.org/pdf/2312.05283.pdf
18
92
8,002
Sora Generates Videos with Stunning Geometrical Consistency Xuanyi Li, Daquan Zhou, Chenxu Zhang, Shaodong Wei, Qibin Hou, Ming-Ming Cheng tl;dr: perspective of 3D reconstruction->design metrics->quality of the generated videos arxiv.org/pdf/2402.17403.pdf
3
17
94
8,333
Explicit Neural Surfaces: Learning Continuous Geometry With Deformation Fields Thomas Walker, Octave Mariotti, Amir Vaxman, Hakan Bilen tl;dr: sampling meshes->deformation fields->differentiable rasterization->neural deferred shader->predicted image arxiv.org/pdf/2306.02956.pdf
1
15
90
9,882
DMESA: Densely Matching Everything by Segmenting Anything Yesheng Zhang, Xu Zhao tl;dr: journal version of MESA; dense counterpart; patch matching->Gaussian Mixture Model+Expectation Maximization->dense matching distributions->efficiency improvement arxiv.org/pdf/2408.00279
Zhenjun Zhao@zhenjun_zhao
31 Jan 2024
MESA: Matching Everything by Segmenting Anything Yesheng Zhang, Xu Zhao tl;dr: SAM->multi-relational graph->AMRF and ABN->energy minimization->Graph Cut->area matching->point matching arxiv.org/pdf/2401.16741.pdf
2
20
95
6,105
Notes on Various Errors and Jacobian Derivations for SLAM Gyubeom Edward Im tl;dr: in title arxiv.org/pdf/2406.06422
1
14
93
6,737
Continuous 3D Perception Model with Persistent State @QianqianWang5, Yifei Zhang, @holynski_, Alexei A. Efros, @akanazawa tl;dr: DUSt3R+visual tokens from input image via ViT encoder+current/past tokens interaction via ViT decoders; dynamic&unobserved arxiv.org/abs/2501.12387
18
93
4,582
Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction Ziyi Yang, Xinyu Gao, Wen Zhou, Shaohui Jiao, Yuqing Zhang, Xiaogang Jin tl;dr: deformable 3D Gaussians Splatting method->explicit 3D Gaussians->monocular dynamic scenes arxiv.org/pdf/2309.13101.pdf
1
16
92
18,108
2D3D-MATR: 2D-3D Matching Transformer for Detection-free Registration between Images and Point Clouds Minhao Li, Zheng Qin, Zhirui Gao, Renjiao Yi, Chengyang Zhu, Kai Xu tl;dr: 2D-3D matching version of LoFTR arxiv.org/pdf/2308.05667.pdf
1
25
91
5,612
Neural Mesh Fusion: Unsupervised 3D Planar Surface Understanding Farhad G. Zanjani, Hong Cai, Yinhao Zhu, Leyla Mirvakhabova, Fatih Porikli tl;dr: deform surface triangle mesh and generate an embedding for unsupervised 3D planar segmentation arxiv.org/pdf/2402.16739.pdf
11
91
4,796
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
14
92
5,620
Segment Any 3D Gaussians Jiazhong Cen, Jiemin Fang, Chen Yang, Lingxi Xie, Xiaopeng Zhang, Wei Shen, Qi Tian tl;dr: SAM meets 3DGS arxiv.org/pdf/2312.00860.pdf
19
91
7,008