mlsanityData to 14 Oct 2026

Invertible Neural Warp for NeRF

arXiv 2407.12354 ↗First posted 17 Jul 2024cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

This paper tackles the simultaneous optimization of pose and Neural Radiance Fields (NeRF). Departing from the conventional practice of using explicit global representations for camera pose, we propose a novel overparameterized representation that models camera poses as learnable rigid warp functions. We establish that modeling the rigid warps must be tightly coupled with constraints and regularization imposed. Specifically, we highlight the critical importance of enforcing invertibility when learning rigid warp functions via neural network and propose the use of an Invertible Neural Network (INN) coupled with a geometry-informed constraint for this purpose. We present results on synthetic and real-world datasets, and demonstrate that our approach outperforms existing baselines in terms of pose estimation and high-fidelity reconstruction due to enhanced optimization convergence.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 36 of its 48 references that are in the map. First posted on arXiv 17 Jul 2024.

Builds on

36 of 48 references.

References · 36

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2018Neural Ordinary Differential Equationscited by 3,779
  3. 2016Density estimation using Real NVPcited by 2,042
  4. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,198
  5. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  6. 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 642
  7. 2023Nerfstudio: A Modular Framework for Neural Radiance Field Developmentcited by 600
  8. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 589
  9. 2019Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networkscited by 566
  10. 2023LERF: Language Embedded Radiance Fieldscited by 543
  11. 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
  12. 2018Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layerscited by 340
24 more
  1. 2015Norm-Based Capacity Control in Neural Networkscited by 299
  2. 2018Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Datacited by 261
  3. 2022NoPe-NeRF: Optimising Neural Radiance Field with No Pose Priorcited by 235
  4. 2021Self-Calibrating Neural Radiance Fieldscited by 204
  5. 2022SPARF: Neural Radiance Fields from Sparse and Noisy Posescited by 195
  6. 2023Tracking Everything Everywhere All at Oncecited by 193
  7. 2019Towards moderate overparameterization: global convergence guarantees for training shallow neural networkscited by 176
  8. 2021HumanNeRF: Efficiently Generated Human Radiance Field from Sparse Inputscited by 112
  9. 2021Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networkscited by 103
  10. 2022Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstructioncited by 94
  11. 2020Object-Centric Neural Scene Renderingcited by 90
  12. 2022GARF: Gaussian Activated Radiance Fields for High Fidelity Reconstruction and Pose Estimationcited by 86
  13. 2020Global Convergence of Deep Networks with One Wide Layer Followed by Pyramidal Topologycited by 66
  14. 2023DBARF: Deep Bundle-Adjusting Generalizable Neural Radiance Fieldscited by 60
  15. 2022Local-to-Global Registration for Bundle-Adjusting Neural Radiance Fieldscited by 58
  16. 2022CaDeX: Learning Canonical Deformation Coordinate Space for Dynamic Surface Representation via Neural Homeomorphismcited by 57
  17. 2022Neural Surface Reconstruction of Dynamic Scenes with Monocular RGB-D Cameracited by 57
  18. 2023CamP: Camera Preconditioning for Neural Radiance Fieldscited by 55
  19. 2023NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detectioncited by 51
  20. 2022SiNeRF: Sinusoidal Neural Radiance Fields for Joint Pose Estimation and Scene Reconstructioncited by 49
  21. 2023Flow supervision for Deformable NeRFcited by 42
  22. 2022ActiveRMAP: Radiance Field for Active Mapping And Planningcited by 30
  23. 2023PoRF: Pose Residual Field for Accurate Neural Surface Reconstructioncited by 19
  24. 2021Rotation Coordinate Descent for Fast Globally Optimal Rotation Averagingcited by 14

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 4.

5 papers.

  1. 2025From Tables to Signals: Revealing Spectral Adaptivity in TabPFNcited by 4
  2. 2025Enhancing Transformers Through Conditioned Embedded Tokenscited by 3
  3. 2025G3Splat: Geometrically Consistent Generalizable Gaussian Splattingcited by 3
  4. 2025NoPe-NeRF++: Local-to-Global Optimization of NeRF with No Pose Priorcited by 1
  5. 2024Robust SG-NeRF: Robust Scene Graph Aided Neural Surface Reconstructioncited by 0