arXiv_daily.json

{"GAN": {}, "NeRF": {"2411.10504": "|**2024-11-15**|**USP-Gaussian: Unifying Spike-based Image Reconstruction, Pose Correction and Gaussian Splatting**|Kang Chen et.al.|[2411.10504v1](http://arxiv.org/abs/2411.10504v1)|**[link](https://github.com/chenkang455/usp-gaussian)**|\n", "2411.08279": "|**2024-11-13**|**MBA-SLAM: Motion Blur Aware Dense Visual SLAM with Radiance Fields Representation**|Peng Wang et.al.|[2411.08279v1](http://arxiv.org/abs/2411.08279v1)|**[link](https://github.com/wu-cvgl/mba-slam)**|\n", "2411.08037": "|**2024-11-12**|**Material Transforms from Disentangled NeRF Representations**|Ivan Lopes et.al.|[2411.08037v1](http://arxiv.org/abs/2411.08037v1)|**[link](https://github.com/astra-vision/brdftransform)**|\n", "2411.03637": "|**2024-11-06**|**Structure Consistent Gaussian Splatting with Matching Prior for Few-shot Novel View Synthesis**|Rui Peng et.al.|[2411.03637v1](http://arxiv.org/abs/2411.03637v1)|**[link](https://github.com/prstrive/scgaussian)**|\n", "2411.01725": "|**2024-11-04**|**A Probabilistic Formulation of LiDAR Mapping with Neural Radiance Fields**|Matthew McDermott et.al.|[2411.01725v1](http://arxiv.org/abs/2411.01725v1)|**[link](https://github.com/mcdermatt/plink)**|\n", "2410.20220": "|**2024-10-26**|**Neural Fields in Robotics: A Survey**|Muhammad Zubair Irshad et.al.|[2410.20220v1](http://arxiv.org/abs/2410.20220v1)|**[link](https://github.com/zubair-irshad/Awesome-Implicit-NeRF-Robotics)**|\n", "2410.19483": "|**2024-10-25**|**Content-Aware Radiance Fields: Aligning Model Complexity with Scene Intricacy Through Learned Bitwidth Quantization**|Weihang Liu et.al.|[2410.19483v1](http://arxiv.org/abs/2410.19483v1)|**[link](https://github.com/weihangliu2024/content_aware_nerf)**|\n", "2410.18355": "|**2024-10-24**|**Real-time 3D-aware Portrait Video Relighting**|Ziqi Cai et.al.|[2410.18355v1](http://arxiv.org/abs/2410.18355v1)|**[link](https://github.com/GhostCai/PortraitRelighting)**|\n", "2410.17741": "|**2024-10-23**|**Efficient Neural Implicit Representation for 3D Human Reconstruction**|Zexu Huang et.al.|[2410.17741v1](http://arxiv.org/abs/2410.17741v1)|**[link](https://github.com/HZXu-526/Human-Avatar)**|\n", "2410.16995": "|**2024-10-22**|**E-3DGS: Gaussian Splatting with Exposure and Motion Events**|Xiaoting Yin et.al.|[2410.16995v1](http://arxiv.org/abs/2410.16995v1)|**[link](https://github.com/masterhow/e-3dgs)**|\n", "2410.18137": "|**2024-10-22**|**Advancing Super-Resolution in Neural Radiance Fields via Variational Diffusion Strategies**|Shrey Vishen et.al.|[2410.18137v1](http://arxiv.org/abs/2410.18137v1)|**[link](https://github.com/shreyvish5678/advancing-super-resolution-in-neural-radiance-fields-via-variational-diffusion-strategies)**|\n", "2410.11228": "|**2024-10-15**|**TEOcc: Radar-camera Multi-modal Occupancy Prediction via Temporal Enhancement**|Zhiwei Lin et.al.|[2410.11228v1](http://arxiv.org/abs/2410.11228v1)|**[link](https://github.com/vdigpku/teocc)**|\n", "2410.11080": "|**2024-10-14**|**Few-shot Novel View Synthesis using Depth Aware 3D Gaussian Splatting**|Raja Kumar et.al.|[2410.11080v1](http://arxiv.org/abs/2410.11080v1)|**[link](https://github.com/raja-kumar/depth-aware-3dgs)**|\n"}, "Visual Localization": {"2411.08279": "|**2024-11-13**|**MBA-SLAM: Motion Blur Aware Dense Visual SLAM with Radiance Fields Representation**|Peng Wang et.al.|[2411.08279v1](http://arxiv.org/abs/2411.08279v1)|**[link](https://github.com/wu-cvgl/mba-slam)**|\n", "2410.19341": "|**2024-10-25**|**Context-Based Visual-Language Place Recognition**|Soojin Woo et.al.|[2410.19341v1](http://arxiv.org/abs/2410.19341v1)|**[link](https://github.com/woo-soojin/context-based-vlpr)**|\n", "2410.12269": "|**2024-10-16**|**LoD-Loc: Aerial Visual Localization using LoD 3D Map with Neural Wireframe Alignment**|Juelin Zhu et.al.|[2410.12269v1](http://arxiv.org/abs/2410.12269v1)|**[link](https://github.com/VictorZoo/LoD-Loc)**|\n", "2410.11187": "|**2024-10-31**|**Multiview Scene Graph**|Juexiao Zhang et.al.|[2410.11187v2](http://arxiv.org/abs/2410.11187v2)|**[link](https://github.com/ai4ce/MSG)**|\n", "2410.09533": "|**2024-10-12**|**Leveraging Semantic Cues from Foundation Vision Models for Enhanced Local Feature Correspondence**|Felipe Cadar et.al.|[2410.09533v1](http://arxiv.org/abs/2410.09533v1)|**[link](https://github.com/verlab/DescriptorReasoning_ACCV_2024)**|\n", "2410.08935": "|**2024-10-11**|**Voxel-SLAM: A Complete, Accurate, and Versatile LiDAR-Inertial SLAM System**|Zheng Liu et.al.|[2410.08935v1](http://arxiv.org/abs/2410.08935v1)|**[link](https://github.com/hku-mars/Voxel-SLAM)**|\n", "2409.19293": "|**2024-09-28**|**VLAD-BuFF: Burst-aware Fast Feature Aggregation for Visual Place Recognition**|Ahmad Khaliq et.al.|[2409.19293v1](http://arxiv.org/abs/2409.19293v1)|**[link](https://github.com/ahmedest61/vlad-buff)**|\n", "2409.18049": "|**2024-09-26**|**Revisit Anything: Visual Place Recognition via Image Segment Retrieval**|Kartik Garg et.al.|[2409.18049v1](http://arxiv.org/abs/2409.18049v1)|**[link](https://github.com/anyloc/revisit-anything)**|\n", "2409.16502": "|**2024-09-24**|**GSplatLoc: Grounding Keypoint Descriptors into 3D Gaussian Splatting for Improved Visual Localization**|Gennady Sidorov et.al.|[2409.16502v1](http://arxiv.org/abs/2409.16502v1)|**[link](https://github.com/haksorus/gsplatloc)**|\n", "2409.12002": "|**2024-09-18**|**Towards Global Localization using Multi-Modal Object-Instance Re-Identification**|Aneesh Chavan et.al.|[2409.12002v1](http://arxiv.org/abs/2409.12002v1)|**[link](https://github.com/instance-based-loc/instance-based-loc)**|\n", "2409.06704": "|**2024-10-17**|**GeoCalib: Learning Single-image Calibration with Geometric Optimization**|Alexander Veicht et.al.|[2409.06704v2](http://arxiv.org/abs/2409.06704v2)|**[link](https://github.com/cvg/geocalib)**|\n", "2409.06471": "|**2024-09-10**|**Weakly-supervised Camera Localization by Ground-to-satellite Image Registration**|Yujiao Shi et.al.|[2409.06471v1](http://arxiv.org/abs/2409.06471v1)|**[link](https://github.com/yujiaoshi/g2sweakly)**|\n", "2408.16754": "|**2024-08-29**|**A compact neuromorphic system for ultra energy-efficient, on-device robot localization**|Adam D. Hines et.al.|[2408.16754v1](http://arxiv.org/abs/2408.16754v1)|**[link](https://github.com/AdamDHines/LENS)**|\n", "2408.12037": "|**2024-08-21**|**FUSELOC: Fusing Global and Local Descriptors to Disambiguate 2D-3D Matching in Visual Localization**|Son Tung Nguyen et.al.|[2408.12037v1](http://arxiv.org/abs/2408.12037v1)|**[link](https://github.com/sontung/descriptor-disambiguation)**|\n", "2408.01841": "|**2024-08-09**|**BEVPlace++: Fast, Robust, and Lightweight LiDAR Global Localization for Unmanned Ground Vehicles**|Lun Luo et.al.|[2408.01841v2](http://arxiv.org/abs/2408.01841v2)|**[link](https://github.com/zjuluolun/bevplace)**|\n"}, "Image Matching": {"2411.09484": "|**2024-11-15**|**Image Matching Filtering and Refinement by Planes and Beyond**|Fabio Bellavia et.al.|[2411.09484v2](http://arxiv.org/abs/2411.09484v2)|**[link](https://github.com/fb82/miho)**|\n", "2411.07430": "|**2024-11-11**|**XPoint: A Self-Supervised Visual-State-Space based Architecture for Multispectral Image Registration**|Ismail Can Yagmur et.al.|[2411.07430v1](http://arxiv.org/abs/2411.07430v1)|**[link](https://github.com/canyagmur/xpoint)**|\n", "2409.16925": "|**2024-09-25**|**Game4Loc: A UAV Geo-Localization Benchmark from Game Data**|Yuxiang Ji et.al.|[2409.16925v1](http://arxiv.org/abs/2409.16925v1)|**[link](https://github.com/Yux1angJi/GTA-UAV)**|\n", "2409.06471": "|**2024-09-10**|**Weakly-supervised Camera Localization by Ground-to-satellite Image Registration**|Yujiao Shi et.al.|[2409.06471v1](http://arxiv.org/abs/2409.06471v1)|**[link](https://github.com/yujiaoshi/g2sweakly)**|\n", "2409.03032": "|**2024-09-20**|**A General Albedo Recovery Approach for Aerial Photogrammetric Images through Inverse Rendering**|Shuang Song et.al.|[2409.03032v2](http://arxiv.org/abs/2409.03032v2)|**[link](https://github.com/gdaosu/albedo_aerial_photogrammetry)**|\n", "2408.16445": "|**2024-09-15**|**Mismatched: Evaluating the Limits of Image Matching Approaches and Benchmarks**|Sierra Bonilla et.al.|[2408.16445v2](http://arxiv.org/abs/2408.16445v2)|**[link](https://github.com/surgical-vision/colmap-match-converter)**|\n", "2408.14186": "|**2024-08-26**|**Affine steerers for structured keypoint description**|Georg B\u00f6kman et.al.|[2408.14186v1](http://arxiv.org/abs/2408.14186v1)|**[link](https://github.com/georg-bn/affine-steerers)**|\n", "2408.02079": "|**2024-09-14**|**Improving Neural Surface Reconstruction with Feature Priors from Multi-View Image**|Xinlin Ren et.al.|[2408.02079v2](http://arxiv.org/abs/2408.02079v2)|**[link](https://github.com/maybeLx/MVS_NeuS)**|\n", "2407.19812": "|**2024-07-29**|**Image-text matching for large-scale book collections**|Artemis Llabr\u00e9s et.al.|[2407.19812v1](http://arxiv.org/abs/2407.19812v1)|**[link](https://github.com/llabres/library-dataset)**|\n", "2407.11637": "|**2024-07-16**|**REMM:Rotation-Equivariant Framework for End-to-End Multimodal Image Matching**|Han Nie et.al.|[2407.11637v1](http://arxiv.org/abs/2407.11637v1)|**[link](https://github.com/hanniewhu/remm)**|\n", "2406.10902": "|**2024-06-16**|**Light Up the Shadows: Enhance Long-Tailed Entity Grounding with Concept-Guided Vision-Language Models**|Yikai Zhang et.al.|[2406.10902v1](http://arxiv.org/abs/2406.10902v1)|**[link](https://github.com/ykzhang721/COG)**|\n", "2406.09756": "|**2024-06-14**|**Grounding Image Matching in 3D with MASt3R**|Vincent Leroy et.al.|[2406.09756v1](http://arxiv.org/abs/2406.09756v1)|**[link](https://github.com/naver/mast3r)**|\n", "2405.12979": "|**2024-05-21**|**OmniGlue: Generalizable Feature Matching with Foundation Model Guidance**|Hanwen Jiang et.al.|[2405.12979v1](http://arxiv.org/abs/2405.12979v1)|**[link](https://github.com/google-research/omniglue)**|\n", "2405.08556": "|**2024-07-09**|**Shape-aware synthesis of pathological lung CT scans using CycleGAN for enhanced semi-supervised lung segmentation**|Rezkellah Noureddine Khiati et.al.|[2405.08556v2](http://arxiv.org/abs/2405.08556v2)|**[link](https://github.com/noureddinekhiati/semi-supervised-lung-segmentation)**|\n", "2404.17993": "|**2024-06-10**|**MinBackProp -- Backpropagating through Minimal Solvers**|Diana Sungatullina et.al.|[2404.17993v2](http://arxiv.org/abs/2404.17993v2)|**[link](https://github.com/disungatullina/minbackprop)**|\n", "2404.11302": "|**2024-05-23**|**A Semantic Segmentation-guided Approach for Ground-to-Aerial Image Matching**|Francesco Pro et.al.|[2404.11302v2](http://arxiv.org/abs/2404.11302v2)|**[link](https://github.com/pro1944191/semanticalignnet)**|\n", "2404.09692": "|**2024-04-15**|**XoFTR: Cross-modal Feature Matching Transformer**|\u00d6nder Tuzcuo\u011flu et.al.|[2404.09692v1](http://arxiv.org/abs/2404.09692v1)|**[link](https://github.com/ondert/xoftr)**|\n", "2404.08928": "|**2024-04-13**|**DeDoDe v2: Analyzing and Improving the DeDoDe Keypoint Detector**|Johan Edstedt et.al.|[2404.08928v1](http://arxiv.org/abs/2404.08928v1)|**[link](https://github.com/parskatt/dedode)**|\n", "2403.15901": "|**2024-08-17**|**MatchSeg: Towards Better Segmentation via Reference Image Matching**|Jiayu Huo et.al.|[2403.15901v3](http://arxiv.org/abs/2403.15901v3)|**[link](https://github.com/keeplearning-again/matchseg)**|\n"}, "Keypoint Detection": {"2410.05729": "|**2024-10-08**|**Equi-GSPR: Equivariant SE(3) Graph Network Model for Sparse Point Cloud Registration**|Xueyang Kang et.al.|[2410.05729v1](http://arxiv.org/abs/2410.05729v1)|**[link](https://github.com/alexandor91/se3-equi-graph-registration)**|\n", "2409.19899": "|**2024-09-30**|**OpenKD: Opening Prompt Diversity for Zero- and Few-shot Keypoint Detection**|Changsheng Lu et.al.|[2409.19899v1](http://arxiv.org/abs/2409.19899v1)|**[link](https://github.com/alanlusun/openkd)**|\n", "2409.16502": "|**2024-09-24**|**GSplatLoc: Grounding Keypoint Descriptors into 3D Gaussian Splatting for Improved Visual Localization**|Gennady Sidorov et.al.|[2409.16502v1](http://arxiv.org/abs/2409.16502v1)|**[link](https://github.com/haksorus/gsplatloc)**|\n", "2409.08695": "|**2024-09-25**|**Precision Aquaculture: An Integrated Computer Vision and IoT Approach for Optimized Tilapia Feeding**|Rania Hossam et.al.|[2409.08695v3](http://arxiv.org/abs/2409.08695v3)|**[link](https://github.com/ahmedheakl/fish-counting)**|\n", "2407.18232": "|**2024-07-25**|**LION: Linear Group RNN for 3D Object Detection in Point Clouds**|Zhe Liu et.al.|[2407.18232v1](http://arxiv.org/abs/2407.18232v1)|**[link](https://github.com/happinesslz/LION)**|\n", "2407.03857": "|**2024-07-04**|**PFGS: High Fidelity Point Cloud Rendering via Feature Splatting**|Jiaxu Wang et.al.|[2407.03857v1](http://arxiv.org/abs/2407.03857v1)|**[link](https://github.com/Mercerai/PFGS)**|\n", "2407.02830": "|**2024-07-03**|**A Radiometric Correction based Optical Modeling Approach to Removing Reflection Noise in TLS Point Clouds of Urban Scenes**|Li Fang et.al.|[2407.02830v1](http://arxiv.org/abs/2407.02830v1)|**[link](https://github.com/tsuiky/3drn)**|\n", "2407.02014": "|**2024-07-02**|**Multi-Grained Contrast for Data-Efficient Unsupervised Representation Learning**|Chengchao Shen et.al.|[2407.02014v1](http://arxiv.org/abs/2407.02014v1)|**[link](https://github.com/visresearch/mgc)**|\n", "2406.16837": "|**2024-07-23**|**A Certifiable Algorithm for Simultaneous Shape Estimation and Object Tracking**|Lorenzo Shaikewitz et.al.|[2406.16837v2](http://arxiv.org/abs/2406.16837v2)|**[link](https://github.com/mit-spark/certifiable_tracking)**|\n", "2406.01315": "|**2024-06-03**|**Scale-Free Image Keypoints Using Differentiable Persistent Homology**|Giovanni Barbarani et.al.|[2406.01315v1](http://arxiv.org/abs/2406.01315v1)|**[link](https://github.com/gbarbarani/MorseDet)**|\n", "2405.12476": "|**2024-06-01**|**Benchmarking Fish Dataset and Evaluation Metric in Keypoint Detection -- Towards Precise Fish Morphological Assessment in Aquaculture Breeding**|Weizhen Liu et.al.|[2405.12476v2](http://arxiv.org/abs/2405.12476v2)|**[link](https://github.com/weizhenliubioinform/fish-phenotype-detect)**|\n", "2403.19885": "|**2024-03-28**|**Towards Long Term SLAM on Thermal Imagery**|Colin Keil et.al.|[2403.19885v1](http://arxiv.org/abs/2403.19885v1)|**[link](https://github.com/neufieldrobotics/irslam_baseline)**|\n", "2403.19527": "|**2024-03-28**|**Instance-Adaptive and Geometric-Aware Keypoint Learning for Category-Level 6D Object Pose Estimation**|Xiao Lin et.al.|[2403.19527v1](http://arxiv.org/abs/2403.19527v1)|**[link](https://github.com/leeiieeo/ag-pose)**|\n", "2403.11662": "|**2024-03-18**|**FE-DeTr: Keypoint Detection and Tracking in Low-quality Image Frames with Events**|Xiangyuan Wang et.al.|[2403.11662v1](http://arxiv.org/abs/2403.11662v1)|**[link](https://github.com/yuyangpoi/fe-detr)**|\n"}}