Related papers: Decomposed Guided Dynamic Filters for Efficient RG…

Depth information has proven to be a useful cue in the semantic segmentation of RGB-D images for providing a geometric counterpart to the RGB representation. Most existing works simply assume that depth measurements are accurate and…

Depth completion aims to recover dense depth maps from sparse ones, where color images are often used to facilitate this task. Recent depth methods primarily focus on image guided learning frameworks. However, blurry guidance in the image…

Providing machines with the ability to recognize objects like humans has always been one of the primary goals of machine vision. The introduction of RGB-D cameras has paved the way for a significant leap forward in this direction thanks to…

Most existing RGB-D semantic segmentation methods focus on the feature level fusion, including complex cross-modality and cross-scale fusion modules. However, these methods may cause misalignment problem in the feature fusion process and…

Convolution is one of the basic building blocks of CNN architectures. Despite its common use, standard convolution has two main shortcomings: Content-agnostic and Computation-heavy. Dynamic filters are content-adaptive, while further…

An autonomous system's perception engine must provide an accurate understanding of the environment for it to make decisions. Deep learning based object detection networks experience degradation in the performance and robustness for small…

The raw depth image captured by the indoor depth sensor usually has an extensive range of missing depth values due to inherent limitations such as the inability to perceive transparent objects and limited distance range. The incomplete…

This work proposes a new method to accurately complete sparse LiDAR maps guided by RGB images. For autonomous vehicles and robotics the use of LiDAR is indispensable in order to achieve precise depth predictions. A multitude of applications…

This paper addresses the issue on how to more effectively coordinate the depth with RGB aiming at boosting the performance of RGB-D object detection. Particularly, we investigate two primary ideas under the CNN model: property derivation…

Robust gait recognition requires highly discriminative representations, which are closely tied to input modalities. While binary silhouettes and skeletons have dominated recent literature, these 2D representations fall short of capturing…

The goal of our work is to complete the depth channel of an RGB-D image. Commodity-grade depth cameras often fail to sense depth for shiny, bright, transparent, and distant surfaces. To address this problem, we train a deep network that…

A vast majority of augmented reality devices come equipped with depth and color cameras. Despite their advantages, extracting both photometric and depth features simultaneously in real-time remains challenging due to inherent differences…

Accurate dense depth estimation is crucial for autonomous vehicles to analyze their environment. This paper presents a non-deep learning-based approach to densify a sparse LiDAR-based depth map using a guidance RGB image. To achieve this…

Combining RGB images and the corresponding depth maps in semantic segmentation proves the effectiveness in the past few years. Existing RGB-D modal fusion methods either lack the non-linear feature fusion ability or treat both modal images…

RGB-D has gradually become a crucial data source for understanding complex scenes in assisted driving. However, existing studies have paid insufficient attention to the intrinsic spatial properties of depth maps. This oversight…

Current deep learning approaches in computer vision primarily focus on RGB data sacrificing information. In contrast, RAW images offer richer representation, which is crucial for precise recognition, particularly in challenging conditions…

Majority of the perception methods in robotics require depth information provided by RGB-D cameras. However, standard 3D sensors fail to capture depth of transparent objects due to refraction and absorption of light. In this paper, we…

Depth information provides valuable insights into the 3D structure especially the outline of objects, which can be utilized to improve the semantic segmentation tasks. However, a naive fusion of depth information can disrupt feature and…

Depth-aware panoptic segmentation is an emerging topic in computer vision which combines semantic and geometric understanding for more robust scene interpretation. Recent works pursue unified frameworks to tackle this challenge but mostly…

Although large-scale visual foundation models (VFMs) achieve remarkable performance in semantic understanding, they still underperform in instance-aware dense prediction tasks. They exhibit different biases in representation: for instance,…