Search Results for author: Young Min Kim

Found 25 papers, 15 papers with code

3Doodle: Compact Abstraction of Objects with 3D Strokes

no code implementations6 Feb 2024 Changwoon Choi, Jaeah Lee, Jaesik Park, Young Min Kim

We propose 3Dooole, generating descriptive and view-consistent sketch images given multi-view images of the target object.

Descriptive

Text2Scene: Text-driven Indoor Scene Stylization with Part-aware Details

no code implementations CVPR 2023 Inwoo Hwang, Hyeonwoo Kim, Young Min Kim

We propose Text2Scene, a method to automatically create realistic textures for virtual scenes composed of multiple objects.

Calibrating Panoramic Depth Estimation for Practical Localization and Mapping

1 code implementation ICCV 2023 Junho Kim, Eun Sun Lee, Young Min Kim

While panoramic images can easily capture the surrounding context from commodity devices, the estimated depth shares the limitations of conventional image-based depth estimation; the performance deteriorates under large domain shifts and the absolute values are still ambiguous to infer from 2D observations.

Depth Estimation Depth Prediction +1

LDL: Line Distance Functions for Panoramic Localization

1 code implementation ICCV 2023 Junho Kim, Changwoon Choi, Hojun Jang, Young Min Kim

We introduce LDL, a fast and robust algorithm that localizes a panorama to a 3D map using line segments.

Transformed Protoform Reconstruction

1 code implementation4 Jul 2023 Young Min Kim, Kalvin Chang, Chenxuan Cui, David Mortensen

We update their model with the state-of-the-art seq2seq model: the Transformer.

PMP: Learning to Physically Interact with Environments using Part-wise Motion Priors

no code implementations5 May 2023 Jinseok Bae, Jungdam Won, Donggeun Lim, Cheol-Hui Min, Young Min Kim

The proposed PMP allows us to assemble multiple part skills to animate a character, creating a diverse set of motions with different combinations of existing data.

Balanced Spherical Grid for Egocentric View Synthesis

1 code implementation CVPR 2023 Changwoon Choi, Sang Min Kim, Young Min Kim

However, the na\"ive spherical grid suffers from irregularities at two poles, and also cannot represent unbounded scenes.

valid

Dynamic Mesh Recovery from Partial Point Cloud Sequence

no code implementations ICCV 2023 Hojun Jang, Minkwan Kim, Jinseok Bae, Young Min Kim

The exact 3D dynamics of the human body provides crucial evidence to analyze the consequences of the physical interaction between the body and the environment, which can eventually assist everyday activities in a wide range of applications.

MoDA: Map style transfer for self-supervised Domain Adaptation of embodied agents

no code implementations29 Nov 2022 Eun Sun Lee, Junho Kim, SangWon Park, Young Min Kim

We propose a domain adaptation method, MoDA, which adapts a pretrained embodied agent to a new, noisy environment without ground-truth supervision.

Domain Adaptation Style Transfer +1

IBL-NeRF: Image-Based Lighting Formulation of Neural Radiance Fields

1 code implementation15 Oct 2022 Changwoon Choi, Juhyeon Kim, Young Min Kim

However, they are limited to representing isolated objects with a shared environment lighting, and suffer from computational burden to aggregate rays with Monte Carlo integration.

Inverse Rendering

CPO: Change Robust Panorama to Point Cloud Localization

1 code implementation12 Jul 2022 Junho Kim, Hojun Jang, Changwoon Choi, Young Min Kim

By utilizing the unique equivariance of spherical projections, we propose very fast color histogram generation for a large number of camera poses without explicitly rendering images for all candidate poses.

Visual Localization

Probabilistic Implicit Scene Completion

2 code implementations ICLR 2022 Dongsu Zhang, Changwoon Choi, Inbum Park, Young Min Kim

We also demonstrate that our approach outperforms deterministic models even in less ambiguous cases with a small amount of missing data, which infers that probabilistic formulation is crucial for high-quality geometry completion on input scans exhibiting any levels of completeness.

valid

Neural Marionette: Unsupervised Learning of Motion Skeleton and Latent Dynamics from Volumetric Video

no code implementations17 Feb 2022 Jinseok Bae, Hojun Jang, Cheol-Hui Min, Hyungun Choi, Young Min Kim

We present Neural Marionette, an unsupervised approach that discovers the skeletal structure from a dynamic sequence and learns to generate diverse motions that are consistent with the observed motion dynamics.

motion retargeting

SGoLAM: Simultaneous Goal Localization and Mapping for Multi-Object Goal Navigation

1 code implementation14 Oct 2021 Junho Kim, Eun Sun Lee, MinGi Lee, Donsu Zhang, Young Min Kim

We present SGoLAM, short for simultaneous goal localization and mapping, which is a simple and efficient algorithm for Multi-Object Goal navigation.

Navigate Visual Navigation

Self-Supervised Domain Adaptation for Visual Navigation with Global Map Consistency

no code implementations14 Oct 2021 Eun Sun Lee, Junho Kim, Young Min Kim

We propose a light-weight, self-supervised adaptation for a visual navigation agent to generalize to unseen environment.

Test-time Adaptation Visual Navigation

PICCOLO: Point Cloud-Centric Omnidirectional Localization

2 code implementations ICCV 2021 Junho Kim, Changwoon Choi, Hojun Jang, Young Min Kim

Our loss function, called sampling loss, is point cloud-centric, evaluated at the projected location of every point in the point cloud.

Visual Localization

GATSBI: Generative Agent-centric Spatio-temporal Object Interaction

1 code implementation CVPR 2021 Cheol-Hui Min, Jinseok Bae, Junho Lee, Young Min Kim

We present GATSBI, a generative model that can transform a sequence of raw observations into a structured latent representation that fully captures the spatio-temporal context of the agent's actions.

Decision Making Object +2

Learning to Generate 3D Shapes with Generative Cellular Automata

no code implementations ICLR 2021 Dongsu Zhang, Changwoon Choi, Jeonghwan Kim, Young Min Kim

We formulate the shape generation process as sampling from the transition kernel of a Markov chain, where the sampling chain eventually evolves to the full shape of the learned distribution.

Structure-From-Sherds: Incremental 3D Reassembly of Axially Symmetric Pots From Unordered and Mixed Fragment Collections

no code implementations ICCV 2021 Je Hyeong Hong, Seong Jong Yoo, Muhammad Arshad Zeeshan, Young Min Kim, Jinwook Kim

Motivated by the success of the incremental approach in robust SfM, we present an efficient reassembly method for axially symmetric pots based on iterative registration of one sherd at a time.

Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with Deep Metric Learning

1 code implementation7 Jul 2020 Dongsu Zhang, Junha Chun, Sang Kyun Cha, Young Min Kim

We propose spatial semantic embedding network (SSEN), a simple, yet efficient algorithm for 3D instance segmentation using deep metric learning.

3D Instance Segmentation 3D Reconstruction +3

RL-GAN-Net: A Reinforcement Learning Agent Controlled GAN Network for Real-Time Point Cloud Shape Completion

2 code implementations CVPR 2019 Muhammad Sarmad, Hyunjoo Jenny Lee, Young Min Kim

While a GAN is unstable and hard to train, we circumvent the problem by (1) training the GAN on the latent space representation whose dimension is reduced compared to the raw point cloud input and (2) using an RL agent to find the correct input to the GAN to generate the latent space representation of the shape that best fits the current input of incomplete point cloud.

Generative Adversarial Network Reinforcement Learning (RL)

Cannot find the paper you are looking for? You can Submit a new open access paper.