MrNeRF (@janusch_patas)
2025-01-28 | โค๏ธ 45 | ๐ 9
Towards Better Robustness: Progressively Joint Pose-3DGS Learning for Arbitrarily Long Videos
Contributions: โข We propose a novel framework to progressively estimate camera poses and optimize 3DGS for arbitrarily long video sequences without losing rendering quality or suffering from memory constraints.
โข We design an adaptive segmentation strategy and a robust pose estimation method to effectively handle challenging camera trajectories captured casually (e.g., with large or fast camera motion).
โข We conduct extensive experiments to show that our RobGS outperforms state-of-the-art methods in terms of rendering quality and pose estimation accuracy, while also achieving faster training speed.
๋ฏธ๋์ด
๐ Related
Auto-generated - needs manual review
Tags
domain-vision-3d domain-rendering domain-dev-tools domain-visionos