Through the Curved Cover: Synthesizing Cover Aberrated Scenes with Refractive Field
Not on the map. Why?
Abstract (arXiv)
Recent extended reality headsets and field robots have adopted covers to protect the front-facing cameras from environmental hazards and falls. The surface irregularities on the cover can lead to optical aberrations like blurring and non-parametric distortions. Novel view synthesis methods like NeRF and 3D Gaussian Splatting are ill-equipped to synthesize from sequences with optical aberrations. To address this challenge, we introduce SynthCover to enable novel view synthesis through protective covers for downstream extended reality applications. SynthCover employs a Refractive Field that estimates the cover's geometry, enabling precise analytical calculation of refracted rays. Experiments on synthetic and real-world scenes demonstrate our method's ability to accurately model scenes viewed through protective covers, achieving a significant improvement in rendering quality compared to prior methods. We also show that the model can adjust well to various cover geometries with synthetic sequences captured with covers of different surface curvatures. To motivate further studies on this problem, we provide the benchmarked dataset containing real and synthetic walkable scenes captured with protective cover optical aberrations.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 16 of its 46 references that are in the map. First posted on arXiv 10 Nov 2024.
Builds on
16 of 46 references.
References · 16
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
- 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
- 2016Density estimation using Real NVPcited by 2,029
- 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
- 2014NICE: Non-linear Independent Components Estimationcited by 1,052
- 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
- 2023Nerfstudio: A Modular Framework for Neural Radiance Field Developmentcited by 596
- 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
- 2018Invertible Residual Networkscited by 364
- 2021Self-Calibrating Neural Radiance Fieldscited by 204
- 2023VR-NeRF: High-Fidelity Virtualized Walkable Spacescited by 86
- 2021Learning Neural Light Fields with Ray-Space Embedding Networkscited by 49
4 more
- 2019Why Having 10,000 Parameters in Your Camera Model is Better Than Twelvecited by 43
- 2022Eikonal Fields for Refractive Novel-View Synthesiscited by 30
- 2017Online Photometric Calibration for Auto Exposure Video for Realtime Visual Odometry and SLAMcited by 9
- 2022DeepFormableTag: End-to-end Generation and Recognition of Deformable Fiducial Markerscited by 3
Built on by
Not cited yet.