4 papers
Scal3R: Learning Efficient Multi-Relative Pose Query for Scalable Online 3D Reconstruction
Chin-Yang Lin, Yang-Che Sun, Cheng Sun +5
Online 3D reconstruction models perform poorly on long videos. This happens because regressing poses relative to a fixed first-frame anchor forces extrapolation far beyond the trai…
StealthAttack: Robust 3D Gaussian Splatting Poisoning via Density-Guided Illusions
Bo-Hsu Ke, You-Zhe Xie, Yu-Lun Liu +1
3D scene representation methods like Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have significantly advanced novel view synthesis. As these methods become preval…
Improving Robustness for Joint Optimization of Camera Poses and Decomposed Low-Rank Tensorial Radiance Fields
Bo-Yu Cheng, Wei-Chen Chiu, Yu-Lun Liu
In this paper, we propose an algorithm that allows joint refinement of camera pose and scene geometry represented by decomposed low-rank tensor, using only 2D images as supervision…
Skin the sheep not only once: Reusing Various Depth Datasets to Drive the Learning of Optical Flow
Sheng-Chi Huang, Wei-Chen Chiu
Optical flow estimation is crucial for various applications in vision and robotics. As the difficulty of collecting ground truth optical flow in real-world scenarios, most of the e…