4 accepted papers
Encoder-decoder networks are commonly used model architectures for dense prediction tasks, where the encoder typically employs a model pre-trained on upstream tasks, while the decoder is often either randomly initialized or pre-trained on other tasks. In this paper, we introduce ×Net, a novel framew…
We introduce GaussianOcc, a systematic method that investigates Gaussian splatting for fully self-supervised and efficient 3D occupancy estimation in surround views. First, traditional methods for self-supervised 3D occupancy estimation still require ground truth 6D poses from sensors during trainin…
Monocular depth estimation (MDE) is crucial for various computer vision applications, but existing methods often struggle to balance inference speed and accuracy when processing large-region visual information. This paper introduces LR<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="
In this paper, a computation efficient regression framework is presented for estimating the 6D pose of rigid objects from a single RGB-D image, which is applicable to handling symmetric objects. This framework is designed in a simple architecture that efficiently extracts point-wise features from RG…