Related papers: DFormerv2: Geometry Self-Attention for RGBD Semant…
In this paper, we tackle the problem of RGB-D semantic segmentation of indoor images. We take advantage of deconvolutional networks which can predict pixel-wise class labels, and develop a new structure for deconvolution of multiple…
Recent advances in 3D semantic scene understanding have shown impressive progress in 3D instance segmentation, enabling object-level reasoning about 3D scenes; however, a finer-grained understanding is required to enable interactions with…
Most of the existing handcrafted and learning-based local descriptors are still at best approximately invariant to affine image transformations, often disregarding deformable surfaces. In this paper, we take one step further by proposing a…
Estimating a depth map from a single RGB image has been investigated widely for localization, mapping, and 3-dimensional object detection. Recent studies on a single-view depth estimation are mostly based on deep Convolutional neural…
Sparse depth measurements are widely available in many applications such as augmented reality, visual inertial odometry and robots equipped with low cost depth sensors. Although such sparse depth samples work well for certain applications…
Indoor semantic segmentation is fundamental to computer vision and robotics, supporting applications such as autonomous navigation, augmented reality, and smart environments. Although RGB-D fusion leverages complementary appearance and…
Accurate depth estimation from images is a fundamental task in many applications including scene understanding and reconstruction. Existing solutions for depth estimation often produce blurry approximations of low resolution. This paper…
Gated cameras hold promise as an alternative to scanning LiDAR sensors with high-resolution 3D depth that is robust to back-scatter in fog, snow, and rain. Instead of sequentially scanning a scene and directly recording depth via the photon…
Researchers have now achieved great success on dealing with 2D images using deep learning. In recent years, 3D computer vision and Geometry Deep Learning gain more and more attention. Many advanced techniques for 3D shapes have been…
RGB-D semantic segmentation can be advanced with convolutional neural networks due to the availability of Depth data. Although objects cannot be easily discriminated by just the 2D appearance, with the local pixel difference and geometric…
3D perception tasks, such as 3D object detection and Bird's-Eye-View (BEV) segmentation using multi-camera images, have drawn significant attention recently. Despite the fact that accurately estimating both semantic and 3D scene layouts are…
We consider image classification with estimated depth. This problem falls into the domain of transfer learning, since we are using a model trained on a set of depth images to generate depth maps (additional features) for use in another…
Depth estimation plays a pivotal role in advancing human-robot interactions, especially in indoor environments where accurate 3D scene reconstruction is essential for tasks like navigation and object handling. Monocular depth estimation,…
Semantic image and video segmentation stand among the most important tasks in computer vision nowadays, since they provide a complete and meaningful representation of the environment by means of a dense classification of the pixels in a…
This paper presents a GPU implementation of two foreground object segmentation algorithms: Gaussian Mixture Model (GMM) and Pixel Based Adaptive Segmenter (PBAS) modified for RGB-D data support. The simultaneous use of colour (RGB) and…
Our goal is to develop stable, accurate, and robust semantic scene understanding methods for wide-area scene perception and understanding, especially in challenging outdoor environments. To achieve this, we are exploring and evaluating a…
Accurate 3D lane segment detection and topology reasoning are critical for structured online map construction in autonomous driving. Recent transformer-based approaches formulate this task as query-based set prediction, yet largely inherit…
The Segment Anything Model (SAM) has demonstrated its effectiveness in segmenting any part of 2D RGB images. However, SAM exhibits a stronger emphasis on texture information while paying less attention to geometry information when…
Guided depth super-resolution (GDSR) is a multi-modal approach for depth map super-resolution that relies on a low-resolution depth map and a high-resolution RGB image to restore finer structural details. However, the misleading color and…
Multimodal perception systems for robotics and embodied AI often assume reliable RGB-D sensing, but in practice, depth is frequently missing, noisy, or corrupted. We thus present GeomPrompt, a lightweight cross-modal adaptation module that…