Related papers: 3D Gated Recurrent Fusion for Semantic Scene Compl…

In this paper, we propose our Correlation For Completion Network (CFCNet), an end-to-end deep learning model that uses the correlation between two data sources to perform sparse depth completion. CFCNet learns to capture, to the largest…

Utilizing multi-view inputs to synthesize novel-view images, Neural Radiance Fields (NeRF) have emerged as a popular research topic in 3D vision. In this work, we introduce a Generalizable Semantic Neural Radiance Field (GSNeRF), which…

Understanding 3D scenes from a single image is fundamental to a wide variety of tasks, such as for robotics, motion planning, or augmented reality. Existing works in 3D perception from a single RGB image tend to focus on geometric…

3D semantic scene completion (SSC) is an ill-posed perception task that requires inferring a dense 3D scene from limited observations. Previous camera-based methods struggle to predict accurate semantic scenes due to inherent geometric…

The goal of multi-modal learning is to use complimentary information on the relevant task provided by the multiple modalities to achieve reliable and robust performance. Recently, deep learning has led significant improvement in multi-modal…

Dense indoor scene modeling from 2D images has been bottlenecked due to the absence of depth information and cluttered occlusions. We present an automatic indoor scene modeling approach using deep features from neural networks. Given a…

RGB-D semantic segmentation methods conventionally use two independent encoders to extract features from the RGB and depth data. However, there lacks an effective fusion mechanism to bridge the encoders, for the purpose of fully exploiting…

Traffic object detection under variable illumination is challenging due to the information loss caused by the limited dynamic range of conventional frame-based cameras. To address this issue, we introduce bio-inspired event cameras and…

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…

Scene understanding is a critical problem in computer vision. In this paper, we propose a 3D point-based scene graph generation ($\mathbf{SGG_{point}}$) framework to effectively bridge perception and reasoning to achieve scene understanding…

The reasonable employment of RGB and depth data show great significance in promoting the development of computer vision tasks and robot-environment interaction. However, there are different advantages and disadvantages in the early and late…

In recent years, the research community has shown a lot of interest to panoramic images that offer a 360-degree directional perspective. Multiple data modalities can be fed, and complimentary characteristics can be utilized for more robust…

Depth completion is a key task in autonomous driving, aiming to complete sparse LiDAR depth measurements into high-quality dense depth maps through image guidance. However, existing methods usually treat depth maps as an additional channel…

Effective integration of local and global contextual information is crucial for semantic segmentation and dense image labeling. We develop two encoder-decoder based deep learning architectures to address this problem. We first propose a…

Semantic Scene Completion (SSC) aims to jointly estimate the complete geometry and semantics of a scene, assuming partial sparse input. In the last years following the multiplication of large-scale 3D datasets, SSC has gained significant…

Semantic understanding of 3D scenes is essential for robots to operate effectively and safely in complex environments. Existing methods for semantic scene reconstruction and semantic-aware novel view synthesis often rely on dense multi-view…

Multi-scale deep CNNs have been used successfully for problems mapping each pixel to a label, such as depth estimation and semantic segmentation. It has also been shown that such architectures are reusable and can be used for multiple…

Burst image processing is becoming increasingly popular in recent years. However, it is a challenging task since individual burst images undergo multiple degradations and often have mutual misalignments resulting in ghosting and zipper…

Infrared and visible image fusion (IVIF) is essential for integrating thermal saliency with textural details to support downstream perception. However, most existing approaches suffer from "semantic blindness," leading to the erroneous…

Surgical scene understanding is a key technical component for enabling intelligent and context aware systems that can transform various aspects of surgical interventions. In this work, we focus on the semantic segmentation task, propose a…