Direct-PoseNet: Absolute Pose Regression with Photometric Consistency
Not on the map. Why?
Abstract (arXiv)
We present a relocalization pipeline, which combines an absolute pose regression (APR) network with a novel view synthesis based direct matching module, offering superior accuracy while maintaining low inference time. Our contribution is twofold: i) we design a direct matching module that supplies a photometric supervision signal to refine the pose regression network via differentiable rendering; ii) we modify the rotation representation from the classical quaternion to SO(3) in pose regression, removing the need for balancing rotation and translation loss terms. As a result, our network Direct-PoseNet achieves state-of-the-art performance among all other single-image APR methods on the 7-Scenes benchmark and the LLFF dataset.
Key facts. Cited by 61 papers in the map (data through 7 Oct 2026). Builds on 31 of its 63 references that are in the map. First posted on arXiv 8 Apr 2021.
Builds on
31 of 63 references.
References · 31
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
- 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
- 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
- 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
- 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
- 2020Neural Sparse Voxel Fieldscited by 959
- 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
- 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 857
- 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
- 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 688
19 more
- 2018DeepVoxels: Learning Persistent 3D Feature Embeddingscited by 401
- 2020INeRF: Inverting Neural Radiance Fields for Pose Estimationcited by 381
- 2020State of the Art on Neural Renderingcited by 276
- 2016DSAC - Differentiable RANSAC for Camera Localizationcited by 264
- 2019Deferred Neural Rendering: Image Synthesis using Neural Texturescited by 253
- 2017Geometric Loss Functions for Camera Pose Regression with Deep Learningcited by 224
- 2019Understanding the Limitations of CNN-based Absolute Camera Pose Regressioncited by 177
- 2020Visual Camera Re-Localization from RGB and RGB-D Images Using DSACcited by 176
- 2017Geometry-Aware Learning of Maps for Camera Localizationcited by 161
- 2017Learning Less is More - 6D Camera Localization via 3D Surface Regressioncited by 146
- 2016Image-based localization using LSTMs for structured feature correlationcited by 136
- 2015Modelling Uncertainty in Deep Learning for Camera Relocalizationcited by 133
- 2019Neural-Guided RANSAC: Learning Where to Sample Model Hypothesescited by 129
- 2019Neural Rerendering in the Wildcited by 121
- 2017Image-based Localization using Hourglass Networkscited by 63
- 2018VLocNet++: Deep Multitask Learning for Semantic Visual Localization and Odometrycited by 61
- 2019Neural Point Cloud Rendering via Multi-Plane Projectioncited by 60
- 2018Deep Auxiliary Learning for Visual Localization and Odometrycited by 59
- 2019Introduction to Camera Pose Estimation with Deep Learningcited by 25
Built on by
Citing papers per year: 2021: 2; 2022: 4; 2023: 10; 2024: 27; 2025: 12; 2026: 6.
61 papers.
Sort:
- 2021Neural Fields in Visual Computing and Beyondcited by 539
- 2021LENS: Localization enhanced by NeRF synthesiscited by 116
- 2022DFNet: Enhance Absolute Pose Regression with Direct Feature Matchingcited by 82
- 2024Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localizationcited by 81
- 2024Scene Coordinate Reconstruction: Posing of Image Collections via Incremental Learning of a Relocalizercited by 73
- 2022ViewFormer: NeRF-free Neural Rendering from Few Images Using Transformerscited by 70
- 2023CROSSFIRE: Camera Relocalization On Self-Supervised Features from an Implicit Representationcited by 45
- 2024Map-Relative Pose Regression for Visual Re-Localizationcited by 42
- 2023Neural Refinement for Absolute Pose Regression with Feature Synthesiscited by 37
- 2024The NeRFect Match: Exploring NeRF Features for Visual Localizationcited by 32
- 2024GS-CPR: Efficient Camera Pose Refinement via 3D Gaussian Splattingcited by 31
- 2023NeRF-Loc: Visual Localization with Conditional Neural Radiance Fieldcited by 29
38 more
- 2023360Loc: A Dataset and Benchmark for Omnidirectional Visual Localization with Cross-device Queriescited by 28
- 2023HSCNet++: Hierarchical Scene Coordinate Classification and Regression for Visual Localization with Transformercited by 26
- 2023PNeRFLoc: Visual Localization with Point-based Neural Radiance Fieldscited by 22
- 2022LATITUDE: Robotic Global Localization with Truncated Dynamic Low-pass Filter in City-scale NeRFcited by 17
- 2024HR-APR: APR-agnostic Framework with Uncertainty Estimation and Hierarchical Refinement for Camera Relocalisationcited by 16
- 2024NeRFs in Robotics: A Surveycited by 16
- 2024GSplatLoc: Grounding Keypoint Descriptors into 3D Gaussian Splatting for Improved Visual Localizationcited by 15
- 2024Towards Foundation Models for 3D Vision: How Close Are We?cited by 13
- 2025From Sparse to Dense: Camera Relocalization with Scene-Specific Detector from Feature Gaussian Splattingcited by 13
- 2023A Probabilistic Framework for Visual Localization in Ambiguous Scenescited by 12
- 2023Leveraging Neural Radiance Fields for Uncertainty-Aware Visual Localizationcited by 12
- 2024Learning Neural Volumetric Pose Features for Camera Localizationcited by 11
- 2025Gaussian Splatting Feature Fields for Privacy-Preserving Visual Localizationcited by 10
- 2024HGSLoc: 3DGS-based Heuristic Camera Pose Refinementcited by 8
- 2025ACE-G: Improving Generalization of Scene Coordinate Regression Through Query Pre-Trainingcited by 8
- 2024Toward Multi-class Anomaly Detection: Exploring Class-aware Unified Model against Inter-class Interferencecited by 7
- 2024Self-supervised Learning of Neural Implicit Feature Fields for Camera Pose Refinementcited by 5
- 2024LoGS: Visual Localization via Gaussian Splatting with Fewer Training Imagescited by 5
- 2024Adversarial Exploitation of Data Diversity Improves Visual Localizationcited by 4
- 2025Can we make NeRF-based visual localization privacy-preserving?cited by 3
- 2026Marginalized Bundle Adjustment: Multi-View Camera Pose from Monocular Depth Estimatescited by 3
- 2024AIR-HLoc: Adaptive Retrieved Images Selection for Efficient Visual Localisationcited by 2
- 2024Conditional Variational Autoencoders for Probabilistic Pose Regressioncited by 2
- 2024NaVIP: An Image-Centric Indoor Navigation Solution for Visually Impaired Peoplecited by 2
- 2024Activating Self-Attention for Multi-Scene Absolute Pose Regressioncited by 2
- 2024ConDo: Continual Domain Expansion for Absolute Pose Regressioncited by 2
- 2025Scene Coordinate Reconstruction Priorscited by 2
- 2024MobileARLoc: On-device Robust Absolute Localisation for Pervasive Markerless Mobile ARcited by 1
- 2024WSCLoc: Weakly-Supervised Sparse-View Camera Relocalizationcited by 1
- 2024Camera Relocalization in Shadow-free Neural Radiance Fieldscited by 1
- 2024FaVoR: Features via Voxel Rendering for Camera Relocalizationcited by 1
- 2024Enhancing Scene Coordinate Regression with Efficient Keypoint Detection and Sequential Informationcited by 1
- 2025Camera Pose Refinement via 3D Gaussian Splattingcited by 1
- 2025GRLoc: Geometric Representation Regression for Visual Localizationcited by 1
- 2022NOCaL: Calibration-Free Semi-Supervised Learning of Odometry and Camera Intrinsicscited by 0
- 2023Robust Localization with Visual-Inertial Odometry Constraints for Markerless Mobile ARcited by 0
- 2023KS-APR: Keyframe Selection for Robust Absolute Pose Regressioncited by 0
- 2024PoseINN: Realtime Visual-based Pose Regression and Localization with Invertible Neural Networkscited by 0
50 most cited of 61 All 61 (JSON)
- 2026GS-CPE: Unified 6-Degree-of-Freedom Camera Pose Estimation via 3D Gaussian Splatting11 Aug 2026
- 2026PoseCompass: Intelligent Synthetic Pose Selection for Visual Localization12 May 2026
- 2026Disambiguating 2D-3D Correspondences in Gaussian Splatting-based Feature Fields for Visual Localization8 May 2026
- 2026MultiLoc: Look Around As You Localize for Fast And Robust Visual Re-localization28 Mar 2026
- 2026L3:Scene-agnostic Visual Localization in the Wild9 Mar 2026
- 2026Marginalized Bundle Adjustment: Multi-View Camera Pose from Monocular Depth Estimates21 Feb 2026
- 2025Learning to Anchor Visual Odometry: KAN-Based Pose Regression for Planetary Landing30 Dec 2025
- 2025GRLoc: Geometric Representation Regression for Visual Localization17 Nov 2025
- 2025Visible Structure Retrieval for Lightweight Image-Based Relocalisation16 Nov 2025
- 2025Scene Coordinate Reconstruction Priors14 Oct 2025
- 2025ACE-G: Improving Generalization of Scene Coordinate Regression Through Query Pre-Training13 Oct 2025
- 2025Can we make NeRF-based visual localization privacy-preserving?26 Aug 2025
38 more
- 2025Camera Pose Refinement via 3D Gaussian Splatting25 Aug 2025
- 2025Gaussian Splatting Feature Fields for Privacy-Preserving Visual Localization31 Jul 2025
- 2025Hi^2-GSLoc: Dual-Hierarchical Gaussian-Specific Visual Relocalization for Remote Sensing21 Jul 2025
- 2025Robust Visual Localization via Semantic-Guided Multi-Scale Transformer10 Jun 2025
- 2025Quantifying Epistemic Uncertainty in Absolute Pose Regression9 Apr 2025
- 2025From Sparse to Dense: Camera Relocalization with Scene-Specific Detector from Feature Gaussian Splatting25 Mar 2025
- 2024ConDo: Continual Domain Expansion for Absolute Pose Regression18 Dec 2024
- 2024Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization11 Dec 2024
- 2024Enhancing Scene Coordinate Regression with Efficient Keypoint Detection and Sequential Information9 Dec 2024
- 2024Adversarial Exploitation of Data Diversity Improves Visual Localization28 Nov 2024
- 2024Activating Self-Attention for Multi-Scene Absolute Pose Regression3 Nov 2024
- 2024LoGS: Visual Localization via Gaussian Splatting with Fewer Training Images15 Oct 2024
- 2024Towards Foundation Models for 3D Vision: How Close Are We?14 Oct 2024
- 2024NaVIP: An Image-Centric Indoor Navigation Solution for Visually Impaired People8 Oct 2024
- 2024Conditional Variational Autoencoders for Probabilistic Pose Regression7 Oct 2024
- 2024GSplatLoc: Grounding Keypoint Descriptors into 3D Gaussian Splatting for Improved Visual Localization24 Sep 2024
- 2024HGSLoc: 3DGS-based Heuristic Camera Pose Refinement17 Sep 2024
- 2024FaVoR: Features via Voxel Rendering for Camera Relocalization11 Sep 2024
- 2024GS-CPR: Efficient Camera Pose Refinement via 3D Gaussian Splatting20 Aug 2024
- 2024MambaLoc: Efficient Camera Localisation via State Space Model19 Aug 2024
- 2024Self-supervised Learning of Neural Implicit Feature Fields for Camera Pose Refinement12 Jun 2024
- 2024Camera Relocalization in Shadow-free Neural Radiance Fields23 May 2024
- 2024NeRFs in Robotics: A Survey2 May 2024
- 2024Scene Coordinate Reconstruction: Posing of Image Collections via Incremental Learning of a Relocalizer22 Apr 2024
- 2024PoseINN: Realtime Visual-based Pose Regression and Localization with Invertible Neural Networks20 Apr 2024
- 2024Map-Relative Pose Regression for Visual Re-Localization15 Apr 2024
- 2024AIR-HLoc: Adaptive Retrieved Images Selection for Efficient Visual Localisation27 Mar 2024
- 2024WSCLoc: Weakly-Supervised Sparse-View Camera Relocalization22 Mar 2024
- 2024Toward Multi-class Anomaly Detection: Exploring Class-aware Unified Model against Inter-class Interference21 Mar 2024
- 2024Learning Neural Volumetric Pose Features for Camera Localization19 Mar 2024
- 2024The NeRFect Match: Exploring NeRF Features for Visual Localization14 Mar 2024
- 2024HR-APR: APR-agnostic Framework with Uncertainty Estimation and Hierarchical Refinement for Camera Relocalisation22 Feb 2024
- 2024MobileARLoc: On-device Robust Absolute Localisation for Pervasive Markerless Mobile AR21 Jan 2024
- 2023PNeRFLoc: Visual Localization with Point-based Neural Radiance Fields17 Dec 2023
- 2023360Loc: A Dataset and Benchmark for Omnidirectional Visual Localization with Cross-device Queries29 Nov 2023
- 2023Leveraging Neural Radiance Fields for Uncertainty-Aware Visual Localization10 Oct 2023
- 2023KS-APR: Keyframe Selection for Robust Absolute Pose Regression10 Aug 2023
- 2023Robust Localization with Visual-Inertial Odometry Constraints for Markerless Mobile AR10 Aug 2023
50 newest of 61 All 61 (JSON)
- 2021Neural Fields in Visual Computing and Beyondcited by 539
- 2021LENS: Localization enhanced by NeRF synthesiscited by 116
- 2022DFNet: Enhance Absolute Pose Regression with Direct Feature Matchingcited by 82
- 2024Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localizationcited by 81
- 2024Scene Coordinate Reconstruction: Posing of Image Collections via Incremental Learning of a Relocalizercited by 73
- 2022ViewFormer: NeRF-free Neural Rendering from Few Images Using Transformerscited by 70
- 2023CROSSFIRE: Camera Relocalization On Self-Supervised Features from an Implicit Representationcited by 45
- 2024Map-Relative Pose Regression for Visual Re-Localizationcited by 42
- 2023Neural Refinement for Absolute Pose Regression with Feature Synthesiscited by 37
- 2024The NeRFect Match: Exploring NeRF Features for Visual Localizationcited by 32
- 2024GS-CPR: Efficient Camera Pose Refinement via 3D Gaussian Splattingcited by 31
- 2023NeRF-Loc: Visual Localization with Conditional Neural Radiance Fieldcited by 29
12 most cited of 61 All 61 (JSON)
- 2026GS-CPE: Unified 6-Degree-of-Freedom Camera Pose Estimation via 3D Gaussian Splatting11 Aug 2026
- 2026PoseCompass: Intelligent Synthetic Pose Selection for Visual Localization12 May 2026
- 2026Disambiguating 2D-3D Correspondences in Gaussian Splatting-based Feature Fields for Visual Localization8 May 2026
- 2026MultiLoc: Look Around As You Localize for Fast And Robust Visual Re-localization28 Mar 2026
- 2026L3:Scene-agnostic Visual Localization in the Wild9 Mar 2026
- 2026Marginalized Bundle Adjustment: Multi-View Camera Pose from Monocular Depth Estimates21 Feb 2026
- 2025Learning to Anchor Visual Odometry: KAN-Based Pose Regression for Planetary Landing30 Dec 2025
- 2025GRLoc: Geometric Representation Regression for Visual Localization17 Nov 2025
- 2025Visible Structure Retrieval for Lightweight Image-Based Relocalisation16 Nov 2025
- 2025Scene Coordinate Reconstruction Priors14 Oct 2025
- 2025ACE-G: Improving Generalization of Scene Coordinate Regression Through Query Pre-Training13 Oct 2025
- 2025Can we make NeRF-based visual localization privacy-preserving?26 Aug 2025
12 newest of 61 All 61 (JSON)