no code implementations • 26 Mar 2024 • Jihyun Lee, Shunsuke Saito, Giljoo Nam, Minhyuk Sung, Tae-Kyun Kim
Sampling from our model yields plausible and diverse two-hand shapes in close interaction with or without an object.
no code implementations • 21 Mar 2024 • Jaihoon Kim, Juil Koo, Kyeongmin Yeo, Minhyuk Sung
We introduce a general framework for generating diverse visual content, including ambiguous images, panorama images, mesh textures, and Gaussian splat textures, by synchronizing multiple diffusion processes.
no code implementations • 20 Mar 2024 • Yuseung Lee, Minhyuk Sung
Our analysis of a pretrained image diffusion model that integrates gated self-attention into the U-Net reveals that spatial grounding often outweighs textual grounding due to the sequential flow from gated self-attention to cross-attention.
no code implementations • 11 Jan 2024 • HyunJin Kim, Minhyuk Sung
Our proposed task adaptation method finetunes a 2D bounding box prediction model with an objective function for 3D segmentation.
no code implementations • 28 Nov 2023 • Seungwoo Yoo, Kunho Kim, Vladimir G. Kim, Minhyuk Sung
To better preserve the identity of the edited mesh, we fine-tune our 2D diffusion model with LoRA.
no code implementations • 23 Nov 2023 • Juil Koo, Chanho Park, Minhyuk Sung
PDS matches the stochastic latents of the source and the target, enabling the sampling of targets in diverse parameter spaces that align with a desired attribute while maintaining the source's identity.
no code implementations • 10 Apr 2023 • Chanhyeok Park, Minhyuk Sung
We propose a novel framework for finding a set of tight bounding boxes of a 3D shape via over-segmentation and iterative merging and refinement.
no code implementations • ICCV 2023 • Juil Koo, Seungwoo Yoo, Minh Hieu Nguyen, Minhyuk Sung
We present a cascaded diffusion model based on a part-level implicit 3D representation.
1 code implementation • CVPR 2023 • Jihyun Lee, Minhyuk Sung, Honggyu Choi, Tae-Kyun Kim
To handle the shape complexity and interaction context between two hands, Im2Hands models the occupancy volume of two hands - conditioned on an RGB image and coarse 3D keypoints - by two novel attention-based modules responsible for (1) initial occupancy estimation and (2) context-aware occupancy refinement, respectively.
1 code implementation • CVPR 2023 • Panos Achlioptas, IAn Huang, Minhyuk Sung, Sergey Tulyakov, Leonidas Guibas
In this work, we aim to facilitate the task of editing the geometry of 3D models through the use of natural language.
1 code implementation • 9 Dec 2022 • IAn Huang, Panos Achlioptas, Tianyi Zhang, Sergey Tulyakov, Minhyuk Sung, Leonidas Guibas
Additionally, to measure edit locality, we define a new metric that we call part-wise edit precision.
no code implementations • 1 Nov 2022 • Jeonghyun Kim, Kaichun Mo, Minhyuk Sung, Woontack Woo
We propose Seg&Struct, a supervised learning framework leveraging the interplay between part segmentation and structure inference and demonstrating their synergy in an integrated framework.
no code implementations • CVPR 2022 • Jihyun Lee, Minhyuk Sung, HyunJin Kim, Tae-Kyun Kim
We propose a framework that can deform an object in a 2D image as it exists in 3D space.
no code implementations • 12 Mar 2022 • Minsoo Lee, Chaeyeon Chung, Hojun Cho, Minjung Kim, Sanghun Jung, Jaegul Choo, Minhyuk Sung
While NeRF-based 3D-aware image generation methods enable viewpoint control, limitations still remain to be adopted to various 3D applications.
no code implementations • CVPR 2022 • Mikaela Angelina Uy, Yen-Yu Chang, Minhyuk Sung, Purvi Goel, Joseph Lambourne, Tolga Birdal, Leonidas Guibas
We propose Point2Cyl, a supervised network transforming a raw 3D point cloud to a set of extrusion cylinders.
2 code implementations • CVPR 2022 • Juil Koo, IAn Huang, Panos Achlioptas, Leonidas Guibas, Minhyuk Sung
We introduce PartGlot, a neural framework and associated architectures for learning semantic part segmentation of 3D shape geometry, based solely on part referential language.
no code implementations • 1 Dec 2021 • Kai Wang, Paul Guerrero, Vladimir Kim, Siddhartha Chaudhuri, Minhyuk Sung, Daniel Ritchie
We present the Shape Part Slot Machine, a new method for assembling novel 3D shapes from existing parts by performing contact-based reasoning.
1 code implementation • ICCV 2021 • Jinwoo Lee, Hyunsung Go, Hyunjoon Lee, Sunghyun Cho, Minhyuk Sung, Junho Kim
In this work, we propose Camera calibration TRansformer with Line-Classification (CTRL-C), an end-to-end neural network-based approach to single image camera calibration, which directly estimates the camera parameters from an image and a set of line segments.
1 code implementation • ICCV 2021 • Eric-Tuan Lê, Minhyuk Sung, Duygu Ceylan, Radomir Mech, Tamy Boubekeur, Niloy J. Mitra
We present Cascaded Primitive Fitting Networks (CPFN) that relies on an adaptive patch sampling network to assemble detection results of global and local primitive detection networks.
1 code implementation • CVPR 2021 • Minghua Liu, Minhyuk Sung, Radomir Mech, Hao Su
Given a collection of 3D meshes of a category and their deformation handles (control points), our method learns a set of meta-handles for each shape, which are represented as combinations of the given handles.
1 code implementation • CVPR 2021 • Mikaela Angelina Uy, Vladimir G. Kim, Minhyuk Sung, Noam Aigerman, Siddhartha Chaudhuri, Leonidas Guibas
In fact, we use the embedding space to guide the shape pairs used to train the deformation module, so that it invests its capacity in learning deformations between meaningful shape pairs.
1 code implementation • CVPR 2021 • Jiahui Huang, He Wang, Tolga Birdal, Minhyuk Sung, Federica Arrigoni, Shi-Min Hu, Leonidas Guibas
We present MultiBodySync, a novel, end-to-end trainable multi-body motion segmentation and rigid registration framework for multiple input 3D point clouds.
1 code implementation • 3 Sep 2020 • Minhyuk Sung, Zhenyu Jiang, Panos Achlioptas, Niloy J. Mitra, Leonidas J. Guibas
Shape deformation is an important component in any geometry processing toolbox.
Graphics
1 code implementation • ECCV 2020 • Jiahui Lei, Srinath Sridhar, Paul Guerrero, Minhyuk Sung, Niloy Mitra, Leonidas J. Guibas
We investigate the problem of learning to generate 3D parametric surface representations for novel object instances, as seen from one or more views.
1 code implementation • ECCV 2020 • Jinwoo Lee, Minhyuk Sung, Hyunjoon Lee, Junho Kim
With the supervision of datasets consisting of the horizontal line and focal length of the images, our networks can be trained to estimate the same camera parameters.
1 code implementation • ECCV 2020 • Mikaela Angelina Uy, Jingwei Huang, Minhyuk Sung, Tolga Birdal, Leonidas Guibas
We introduce a new problem of retrieving 3D models that are deformable to a given query shape and present a novel deep deformation-aware embedding to solve this retrieval task.
1 code implementation • ECCV 2020 • Yichen Li, Kaichun Mo, Lin Shao, Minhyuk Sung, Leonidas Guibas
Autonomous assembly is a crucial capability for robots in many applications.
1 code implementation • CVPR 2019 • Li Yi, Wang Zhao, He Wang, Minhyuk Sung, Leonidas Guibas
We introduce a novel 3D object proposal approach named Generative Shape Proposal Network (GSPN) for instance segmentation in point cloud data.
Ranked #26 on 3D Object Detection on ScanNetV2
2 code implementations • CVPR 2019 • Lingxiao Li, Minhyuk Sung, Anastasia Dubrovina, Li Yi, Leonidas Guibas
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 3D shapes.
1 code implementation • 4 Jul 2018 • Minhyuk Sung, Anastasia Dubrovina, Vladimir G. Kim, Leonidas Guibas
Modeling relations between components of 3D objects is essential for many geometry editing tasks.
Graphics I.3.5
1 code implementation • NeurIPS 2018 • Minhyuk Sung, Hao Su, Ronald Yu, Leonidas Guibas
Even though our shapes have independent discretizations and no functional correspondences are provided, the network is able to generate latent bases, in a consistent order, that reflect the shared semantic structure among the shapes.
1 code implementation • 6 Aug 2017 • Minhyuk Sung, Hao Su, Vladimir G. Kim, Siddhartha Chaudhuri, Leonidas Guibas
The combinatorial nature of part arrangements poses another challenge, since the retrieval network is not a function: several complements can be appropriate for the same input.
Graphics I.3.5