paper-with-me

홈 › Papers

Mode-GS: Monocular Depth Guided Anchored 3D Gaussian Splatting for Robust Ground-View Scene Rendering

2024-10-06 · Yonghan Lee, Jaehoon Choi, Dongki Jung, JaeSeong Yun, Soohyun Ryu, Dinesh Manocha, Suyong Yeon

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.

📄 PDF Abstract BibTeX arXiv:2410.04646

Code (0)

등록된 구현이 없습니다.

Tasks

Neural RenderingSSIM

Similar Papers 제목 키워드 기반

MOGS: Monocular Object-guided Gaussian Splatting in Large Scenes

2025-09-08 · Shengkai Zhang, Yuhe Liu, Jianhua He, Xuedou Xiao 외 arxiv

Recent advances in 3D Gaussian Splatting (3DGS) deliver striking photorealism, and extending it to large scenes opens new opportunities for semantic reasoning and prediction in applications such as autonomous driving. To…

Autonomous DrivingPoint Clouds

HI-SLAM2: Geometry-Aware Gaussian SLAM for Fast Monocular Scene Reconstruction

2024-11-27 · Wei zhang, Qing Cheng, David Skuddis, Niclas Zeller 외

We present HI-SLAM2, a geometry-aware Gaussian SLAM system that achieves fast and accurate monocular scene reconstruction using only RGB input. Existing Neural SLAM or 3DGS-based SLAM methods often trade off between rend…

3DGS

Endo-4DGS: Endoscopic Monocular Scene Reconstruction with 4D Gaussian Splatting

2024-01-29 · Yiming Huang, Beilei Cui, Long Bai, Ziqi Guo 외

In the realm of robot-assisted minimally invasive surgery, dynamic scene reconstruction can significantly enhance downstream tasks and improve surgical outcomes. Neural Radiance Fields (NeRF)-based methods have recently …

Depth EstimationDynamic ReconstructionMonocular Depth EstimationMonocular Reconstruction+2

Dynamic Gaussians Mesh: Consistent Mesh Reconstruction from Monocular Videos

2024-04-18 · Isabella Liu, Hao Su, Xiaolong Wang

Modern 3D engines and graphics pipelines require mesh as a memory-efficient representation, which allows efficient rendering, geometry processing, texture editing, and many other downstream operations. However, it is sti…

Towards Accurate Single Panoramic 3D Detection: A Semantic Gaussian Centric Approach

2026-05-14 · Kanglin Ning, Yiran Zhao, Wenrui Li, Shaoru Sun 외 arxiv

Three-dimensional object detection in panoramic imagery is crucial for comprehensive scene understanding, yet accurately mapping 2D features to 3D remains a significant challenge. Prevailing methods often project 2D feat…

Scene UnderstandingDepth EstimationObject Detection