Related papers: SuperDec: 3D Scene Decomposition with Superquadric…

3D occupancy prediction plays a pivotal role in the realm of autonomous driving, as it provides a comprehensive understanding of the driving environment. Most existing methods construct dense scene representations for occupancy prediction,…

Humans can naturally identify and mentally complete occluded objects in cluttered environments. However, imparting similar cognitive ability to robotics remains challenging even with advanced reconstruction techniques, which models scenes…

Decompositional reconstruction of 3D scenes, with complete shapes and detailed texture of all objects within, is intriguing for downstream applications but remains challenging, particularly with sparse views as input. Recent approaches…

One challenge that remains open in 3D deep learning is how to efficiently represent 3D data to feed deep networks. Recent works have relied on volumetric or point cloud representations, but such approaches suffer from a number of issues…

Introducing semantically meaningful objects to visual Simultaneous Localization And Mapping (SLAM) has the potential to improve both the accuracy and reliability of pose estimates, especially in challenging scenarios with significant…

Inferring 3D structure of a generic object from a 2D image is a long-standing objective of computer vision. Conventional approaches either learn completely from CAD-generated synthetic data, which have difficulty in inference from real…

Contemporary point cloud segmentation approaches largely rely on richly annotated 3D training data. However, it is both time-consuming and challenging to obtain consistently accurate annotations for such 3D scene data. Moreover, there is…

In this work, we propose a novel method for generating 3D point clouds that leverage properties of hyper networks. Contrary to the existing methods that learn only the representation of a 3D object, our approach simultaneously finds a…

The key to integrating visual language tasks is to establish a good alignment strategy. Recently, visual semantic representation has achieved fine-grained visual understanding by dividing grids or image patches. However, the coarse-grained…

We present a simple yet effective general-purpose framework for modeling 3D shapes by leveraging recent advances in 2D image generation using CNNs. Using just a single depth image of the object, we can output a dense multi-view depth map…

Various SDF-based neural implicit surface reconstruction methods have been proposed recently, and have demonstrated remarkable modeling capabilities. However, due to the global nature and limited representation ability of a single network,…

We propose an efficient Stereographic Projection Neural Network (SPNet) for learning representations of 3D objects. We first transform a 3D input volume into a 2D planar image using stereographic projection. We then present a shallow 2D…

Reconstructing the underlying 3D surface of an object from a single image is a challenging problem that has received extensive attention from the computer vision community. Many learning-based approaches tackle this problem by learning a 3D…

We introduce Patchwork, a new general-purpose shape representation capable of modeling 2D and 3D geometry with a small number of parameters. Patchwork is grounded in a rigorous mathematical framework, providing provable complexity bounds…

Knowledge of 3D properties of objects is a necessity in order to build effective computer vision systems. However, lack of large scale 3D datasets can be a major constraint for data-driven approaches in learning such properties. We consider…

We propose a new supervized learning framework for oversegmenting 3D point clouds into superpoints. We cast this problem as learning deep embeddings of the local geometry and radiometry of 3D points, such that the border of objects presents…

We introduce a highly efficient method for panoptic segmentation of large 3D point clouds by redefining this task as a scalable graph clustering problem. This approach can be trained using only local auxiliary tasks, thereby eliminating the…

Dense captioning in 3D point clouds is an emerging vision-and-language task involving object-level 3D scene understanding. Apart from coarse semantic class prediction and bounding box regression as in traditional 3D object detection, 3D…

A fully automated object reconstruction pipeline is crucial for digital content creation. While the area of 3D reconstruction has witnessed profound developments, the removal of background to obtain a clean object model still relies on…

Deep image generation is becoming a tool to enhance artists and designers creativity potential. In this paper, we aim at making the generation process more structured and easier to interact with. Inspired by vector graphics systems, we…