94 citations · 120 across the 6 of their papers we have counts for
7 papers
ExCellGen: Fast, Controllable, Photorealistic 3D Scene Generation from a Single Real-World Exemplar
Clément Jambon, Changwoon Choi, Dongsu Zhang +2
Photorealistic 3D scene generation is challenging due to the scarcity of large-scale, high-quality real-world 3D datasets and complex workflows requiring specialized expertise for…
Outdoor Scene Extrapolation with Hierarchical Generative Cellular Automata
Dongsu Zhang, Francis Williams, Zan Gojcic +4
We aim to generate fine-grained 3D geometry from large-scale sparse LiDAR scans, abundantly captured by autonomous vehicles (AV). Contrary to prior work on AV scene completion, we…
Probabilistic Implicit Scene Completion
Dongsu Zhang, Changwoon Choi, Inbum Park +1
We propose a probabilistic shape completion method extended to the continuous geometry of large-scale 3D scenes. Real-world scans of 3D scenes suffer from a considerable amount of…
N-ImageNet: Towards Robust, Fine-Grained Object Recognition with Event Cameras
Junho Kim, Jaehyeok Bae, Gangin Park +2
We introduce N-ImageNet, a large-scale dataset targeted for robust, fine-grained object recognition with event cameras. The dataset is collected using programmable hardware in whic…
Learning to Generate 3D Shapes with Generative Cellular Automata
Dongsu Zhang, Changwoon Choi, Jeonghwan Kim +1
We present a probabilistic 3D generative model, named Generative Cellular Automata, which is able to produce diverse and high quality shapes. We formulate the shape generation proc…
Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with Deep Metric Learning
Dongsu Zhang, Junha Chun, Sang Kyun Cha +1
We propose spatial semantic embedding network (SSEN), a simple, yet efficient algorithm for 3D instance segmentation using deep metric learning. The raw 3D reconstruction of an ind…
A Neural Dirichlet Process Mixture Model for Task-Free Continual Learning
Soochan Lee, Junsoo Ha, Dongsu Zhang +1
Despite the growing interest in continual learning, most of its contemporary works have been studied in a rather restricted setting where tasks are clearly distinguishable, and tas…