Mode-GS: Monocular Depth Guided Anchored 3D Gaussian Splatting for Robust Ground-View Scene Rendering
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913535420792832 |
|---|---|
| author | Lee, Yonghan Choi, Jaehoon Jung, Dongki Yun, Jaeseong Ryu, Soohyun Manocha, Dinesh Yeon, Suyong |
| author_facet | Lee, Yonghan Choi, Jaehoon Jung, Dongki Yun, Jaeseong Ryu, Soohyun Manocha, Dinesh Yeon, Suyong |
| contents | We present a novel-view rendering algorithm, Mode-GS, for ground-robot trajectory datasets. Our approach is based on using anchored Gaussian splats, which are designed to overcome the limitations of existing 3D Gaussian splatting algorithms. Prior neural rendering methods suffer from severe splat drift due to scene complexity and insufficient multi-view observation, and can fail to fix splats on the true geometry in ground-robot datasets. Our method integrates pixel-aligned anchors from monocular depths and generates Gaussian splats around these anchors using residual-form Gaussian decoders. To address the inherent scale ambiguity of monocular depth, we parameterize anchors with per-view depth-scales and employ scale-consistent depth loss for online scale calibration. Our method results in improved rendering performance, based on PSNR, SSIM, and LPIPS metrics, in ground scenes with free trajectory patterns, and achieves state-of-the-art rendering performance on the R3LIVE odometry dataset and the Tanks and Temples dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_04646 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Mode-GS: Monocular Depth Guided Anchored 3D Gaussian Splatting for Robust Ground-View Scene Rendering Lee, Yonghan Choi, Jaehoon Jung, Dongki Yun, Jaeseong Ryu, Soohyun Manocha, Dinesh Yeon, Suyong Computer Vision and Pattern Recognition Robotics We present a novel-view rendering algorithm, Mode-GS, for ground-robot trajectory datasets. Our approach is based on using anchored Gaussian splats, which are designed to overcome the limitations of existing 3D Gaussian splatting algorithms. Prior neural rendering methods suffer from severe splat drift due to scene complexity and insufficient multi-view observation, and can fail to fix splats on the true geometry in ground-robot datasets. Our method integrates pixel-aligned anchors from monocular depths and generates Gaussian splats around these anchors using residual-form Gaussian decoders. To address the inherent scale ambiguity of monocular depth, we parameterize anchors with per-view depth-scales and employ scale-consistent depth loss for online scale calibration. Our method results in improved rendering performance, based on PSNR, SSIM, and LPIPS metrics, in ground scenes with free trajectory patterns, and achieves state-of-the-art rendering performance on the R3LIVE odometry dataset and the Tanks and Temples dataset. |
| title | Mode-GS: Monocular Depth Guided Anchored 3D Gaussian Splatting for Robust Ground-View Scene Rendering |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2410.04646 |