Inferring a meaningful geometric scene representation from a single image is a fundamental problem in computer vision. Approaches based on traditional depth map prediction can only …
K Zhou, JX Zhong, S Shin, K Lu… - Advances in …, 2024 - proceedings.neurips.cc
The introduction of neural radiance fields has greatly improved the effectiveness of view synthesis for monocular videos. However, existing algorithms face difficulties when dealing …
This paper tackles the challenges of self-supervised monocular depth estimation in indoor scenes caused by large rotation between frames and low texture. We ease the learning …
Monocular Depth Estimation (MDE) is a critical component in applications such as autonomous driving. There are various attacks against MDE networks. These attacks …
Inferring scene geometry from images via Structure from Motion is a long-standing and fundamental problem in computer vision. While classical approaches and more recently …
S Hu, K Zhou, K Li, L Yu, L Hong, T Hu, Z Li… - arXiv preprint arXiv …, 2023 - arxiv.org
Neural Radiance Fields (NeRF) has demonstrated remarkable 3D reconstruction capabilities with dense view images. However, its performance significantly deteriorates …
J Liu, L Kong, J Yang, W Liu - IEEE Robotics and Automation …, 2023 - ieeexplore.ieee.org
Depth estimation plays an important role in robotic perception systems. The self-supervised monocular paradigm has gained significant attention since it can free training from the …
JLG Bello, M Kim - … of the IEEE/CVF Conference on …, 2024 - openaccess.thecvf.com
In this paper we address single image-based novel view synthesis (NVS) by firstly integrating view-dependent effects (VDE) into the process. Our approach leverages camera …
Robotic research encounters a significant hurdle when it comes to the intricate task of grasping objects that come in various shapes, materials, and textures. Unlike many prior …