Although the recent rapid evolution of 3D generative neural networks greatly improves 3D shape generation, it is still not convenient for ordinary users to create 3D shapes and control …
3D reconstruction is a longstanding ill-posed problem, which has been explored for decades by the computer vision, computer graphics, and machine learning communities. Since 2015 …
Convolutional networks for single-view object reconstruction have shown impressive performance and have become a popular subject of research. All existing techniques are …
We present an approach to semantic scene analysis using deep convolutional networks. Our approach is based on tangent convolutions-a new construction for convolutional …
Text-to-image diffusion models are gradually introduced into computer graphics, recently enabling the development of Text-to-3D pipelines in an open domain. However, for …
M Gadelha, R Wang, S Maji - Proceedings of the European …, 2018 - openaccess.thecvf.com
We present multiresolution tree-structured networks to process point clouds for 3D shape understanding and generation tasks. Our network represents a 3D shape as set of locality …
K Deng, G Yang, D Ramanan… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
We propose pix2pix3D, a 3D-aware conditional generative model for controllable photorealistic image synthesis. Given a 2D label map, such as a segmentation or edge map …
We present an Adaptive Octree-based Convolutional Neural Network (Adaptive O-CNN) for efficient 3D shape encoding and decoding. Different from volumetric-based or octree-based …
R Wu, Y Zhuang, K Xu, H Zhang… - Proceedings of the …, 2020 - openaccess.thecvf.com
We introduce PQ-NET, a deep neural network which represents and generates 3D shapes via sequential part assembly. The input to our network is a 3D shape segmented into parts …