Related papers: Joint 2D-3D-Semantic Data for Indoor Scene Underst…

The integration of language and 3D perception is critical for embodied AI and robotic systems to perceive, understand, and interact with the physical world. Spatial reasoning, a key capability for understanding spatial relationships between…

Depth estimation, as a necessary clue to convert 2D images into the 3D space, has been applied in many machine vision areas. However, to achieve an entire surrounding 360-degree geometric sensing, traditional stereo matching algorithms for…

This paper proposes a new method called Multimodal RNNs for RGB-D scene semantic segmentation. It is optimized to classify image pixels given two input sources: RGB color channels and Depth maps. It simultaneously performs training of two…

Recent developments in data acquisition technology allow us to collect 3D texture meshes quickly. Those can help us understand and analyse the urban environment, and as a consequence are useful for several applications like spatial analysis…

This paper considers outdoor terrain mapping using RGB images obtained from an aerial vehicle. While feature-based localization and mapping techniques deliver real-time vehicle odometry and sparse keypoint depth reconstruction, a dense…

Recent advances in 3D semantic segmentation with deep neural networks have shown remarkable success, with rapid performance increase on available datasets. However, current 3D semantic segmentation benchmarks contain only a small number of…

We present TartanGround, a large-scale, multi-modal dataset to advance the perception and autonomy of ground robots operating in diverse environments. This dataset, collected in various photorealistic simulation environments includes…

Reconstructing texture-less surfaces poses unique challenges in computer vision, primarily due to the lack of specialized datasets that cater to the nuanced needs of depth and normals estimation in the absence of textural information. We…

Learning-based methods for 3D scene reconstruction and object completion require large datasets containing partial scans paired with complete ground-truth geometry. However, acquiring such datasets using real-world scanning systems is…

Synthetic data has emerged as a promising source for 3D human research as it offers low-cost access to large-scale human datasets. To advance the diversity and annotation quality of human models, we introduce a new synthetic dataset,…

Various datasets have been proposed for simultaneous localization and mapping (SLAM) and related problems. Existing datasets often include small environments, have incomplete ground truth, or lack important sensor data, such as depth and…

In the last few years, there has been a growing interest in taking advantage of the 360 panoramic images potential, while managing the new challenges they imply. While several tasks have been improved thanks to the contextual information…

Neural implicit functions have demonstrated significant importance in various areas such as computer vision, graphics. Their advantages include the ability to represent complex shapes and scenes with high fidelity, smooth interpolation…

Glass surfaces are becoming increasingly ubiquitous as modern buildings tend to use a lot of glass panels. This, however, poses substantial challenges to the operations of autonomous systems such as robots, self-driving cars, and drones, as…

Visual understanding of complex urban street scenes is an enabling factor for a wide range of applications. Object detection has benefited enormously from large-scale datasets, especially in the context of deep learning. For semantic urban…

While deep learning has recently achieved great success on multi-view stereo (MVS), limited training data makes the trained model hard to be generalized to unseen scenarios. Compared with other computer vision tasks, it is rather difficult…

General scene understanding for robotics requires flexible semantic representation, so that novel objects and structures which may not have been known at training time can be identified, segmented and grouped. We present an algorithm which…

Automatic underground parking has attracted considerable attention as the scope of autonomous driving expands. The auto-vehicle is supposed to obtain the environmental information, track its location, and build a reliable map of the…

Collecting diverse sets of training images for RGB-D semantic image segmentation is not always possible. In particular, when robots need to operate in privacy-sensitive areas like homes, the collection is often limited to a small set of…

We propose a method for self-supervised image representation learning under the guidance of 3D geometric consistency. Our intuition is that 3D geometric consistency priors such as smooth regions and surface discontinuities may imply…