Search Results - "Sung, Minhyuk"

Supervised Fitting of Geometric Primitives to 3D Point Clouds by Li, Lingxiao, Sung, Minhyuk, Dubrovina, Anastasia, Yi, Li, Guibas, Leonidas J.

“…Fitting geometric primitives to 3D point cloud data bridges a gap between low-level digitized 3D data and high-level structural information on the underlying…”
Get full text

GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloud by Yi, Li, Zhao, Wang, Wang, He, Sung, Minhyuk, Guibas, Leonidas J.

“…We introduce a novel 3D object proposal approach named Generative Shape Proposal Network (GSPN) for instance segmentation in point cloud data. Instead of…”
Get full text

PartGlot: Learning Shape Part Segmentation from Language Reference Games by Koo, Juil, Huang, Ian, Achlioptas, Panos, Guibas, Leonidas, Sung, Minhyuk

“…We introduce PartGlot, a neural framework and associated architectures for learning semantic part segmentation of 3D shape geometry, based solely on part…”
Get full text

DeepMetaHandles: Learning Deformation Meta-Handles of 3D Meshes with Biharmonic Coordinates by Liu, Minghua, Sung, Minhyuk, Mech, Radomir, Su, Hao

“…We propose DeepMetaHandles, a 3D conditional generative model based on mesh deformation. Given a collection of 3D meshes of a category and their deformation…”
Get full text

OptCtrlPoints: Finding the Optimal Control Points for Biharmonic 3D Shape Deformation by Kim, Kunho, Angelina Uy, Mikaela, Paschalidou, Despoina, Jacobson, Alec, Guibas, Leonidas J., Sung, Minhyuk

“…We propose OptCtrlPoints, a data‐driven framework designed to identify the optimal sparse set of control points for reproducing target shapes using biharmonic…”
Get full text

Im2Hands: Learning Attentive Implicit Representation of Interacting Two-Hand Shapes by Lee, Jihyun, Sung, Minhyuk, Choi, Honggyu, Kim, Tae-Kyun

“…We present Implicit Two Hands (Im2Hands), the first neural implicit representation of two interacting hands. Unlike existing methods on two-hand reconstruction…”
Get full text

ShapeTalk: A Language Dataset and Framework for 3D Shape Edits and Deformations by Achlioptas, Panos, Huang, Ian, Sung, Minhyuk, Tulyakov, Sergey, Guibas, Leonidas

“…Editing 3D geometry is a challenging task requiring specialized skills. In this work, we aim to facilitate the task of editing the geometry of 3D models…”
Get full text

CTRL-C: Camera calibration TRansformer with Line-Classification by Lee, Jinwoo, Go, Hyunsung, Lee, Hyunjoon, Cho, Sunghyun, Sung, Minhyuk, Kim, Junho

“…Single image camera calibration is the task of estimating the camera parameters from a single input image, such as the vanishing points, focal length, and…”
Get full text

MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization by Huang, Jiahui, Wang, He, Birdal, Tolga, Sung, Minhyuk, Arrigoni, Federica, Hu, Shi-Min, Guibas, Leonidas

“…We present MultiBodySync, a novel, end-to-end trainable multi-body motion segmentation and rigid registration framework for multiple input 3D point clouds. The…”
Get full text

Point2Cyl: Reverse Engineering 3D Objects from Point Clouds to Extrusion Cylinders by Uy, Mikaela Angelina, Chang, Yen-Yu, Sung, Minhyuk, Goel, Purvi, Lambourne, Joseph, Birdal, Tolga, Guibas, Leonidas

“…We propose Point2Cyl, a supervised network transforming a raw 3D point cloud to a set of extrusion cylinders. Reverse engineering from a raw geometry to a CAD…”
Get full text

Seg&Struct: The Interplay Between Part Segmentation and Structure Inference for 3D Shape Parsing by Kim, Jeonghyun, Mo, Kaichun, Sung, Minhyuk, Woo, Woontack

“…We propose Seg&Struct, a supervised learning framework leveraging the interplay between part segmentation and structure inference and demonstrating their…”
Get full text

CPFN: Cascaded Primitive Fitting Networks for High-Resolution Point Clouds by Le, Eric-Tuan, Sung, Minhyuk, Ceylan, Duygu, Mech, Radomir, Boubekeur, Tamy, Mitra, Niloy J.

“…Representing human-made objects as a collection of base primitives has a long history in computer vision and reverse engineering. In the case of…”
Get full text

Learning Fuzzy Set Representations of Partial Shapes on Dual Embedding Spaces by Sung, Minhyuk, Dubrovina, Anastasia, Kim, Vladimir G., Guibas, Leonidas

“…Modeling relations between components of 3D objects is essential for many geometry editing tasks. Existing techniques commonly rely on labeled components,…”
Get full text

Joint Learning of 3D Shape Retrieval and Deformation by Uy, Mikaela Angelina, Kim, Vladimir G., Sung, Minhyuk, Aigerman, Noam, Chaudhuri, Siddhartha, Guibas, Leonidas

“…We propose a novel technique for producing high-quality 3D models that match a given target object image or scan. Our method is based on retrieving an existing…”
Get full text

Learning and Exploring the Compositional Structure of 3D Data by Sung, Minhyuk

“…3D data arising either from scanning real objects with depth sensors or from modeling by designers have a unique characteristic — they represent the entire…”
Get full text

Pop-Out Motion: 3D-Aware Image Deformation via Learning the Shape Laplacian by Lee, Jihyun, Sung, Minhyuk, Kim, Hyunjin, Kim, Tae-Kyun

“…We propose a framework that can deform an object in a 2D image as it exists in 3D space. Most existing methods for 3D-aware image manipulation are limited to…”
Get full text

Occupancy-Based Dual Contouring by Hwang, Jisung, Sung, Minhyuk

“…We introduce a dual contouring method that provides state-of-the-art performance for occupancy functions while achieving computation times of a few seconds…”
Get full text

Split, Merge, and Refine: Fitting Tight Bounding Boxes via Over-Segmentation and Iterative Search by Park, Chanhyeok, Sung, Minhyuk

“…Achieving tight bounding boxes of a shape while guaranteeing complete boundness is an essential task for efficient geometric operations and unsupervised…”
Get full text

PartSTAD: 2D-to-3D Part Segmentation Task Adaptation by Kim, Hyunjin, Sung, Minhyuk

“…We introduce PartSTAD, a method designed for the task adaptation of 2D-to-3D segmentation lifting. Recent studies have highlighted the advantages of utilizing…”
Get full text

Split, Merge, and Refine: Fitting Tight Bounding Boxes via Over-Segmentation and Iterative Search by Park, Chanhyeok, Sung, Minhyuk

“…Achieving tight bounding boxes of a shape while guaranteeing complete boundness is an essential task for efficient geometric operations and unsupervised…”
Get full text