Picture for Dongseok Shim

Dongseok Shim

Seoul National University

MVLight: Relightable Text-to-3D Generation via Light-conditioned Multi-View Diffusion

Add code
Nov 18, 2024
Viaarxiv icon

Magnituder Layers for Implicit Neural Representations in 3D

Add code
Oct 13, 2024
Viaarxiv icon

Object Remover Performance Evaluation Methods using Class-wise Object Removal Images

Add code
Apr 17, 2024
Figure 1 for Object Remover Performance Evaluation Methods using Class-wise Object Removal Images
Figure 2 for Object Remover Performance Evaluation Methods using Class-wise Object Removal Images
Figure 3 for Object Remover Performance Evaluation Methods using Class-wise Object Removal Images
Figure 4 for Object Remover Performance Evaluation Methods using Class-wise Object Removal Images
Viaarxiv icon

AURA : Automatic Mask Generator using Randomized Input Sampling for Object Removal

Add code
May 13, 2023
Figure 1 for AURA : Automatic Mask Generator using Randomized Input Sampling for Object Removal
Figure 2 for AURA : Automatic Mask Generator using Randomized Input Sampling for Object Removal
Figure 3 for AURA : Automatic Mask Generator using Randomized Input Sampling for Object Removal
Figure 4 for AURA : Automatic Mask Generator using Randomized Input Sampling for Object Removal
Viaarxiv icon

SNeRL: Semantic-aware Neural Radiance Fields for Reinforcement Learning

Add code
Jan 27, 2023
Viaarxiv icon

SwinDepth: Unsupervised Depth Estimation using Monocular Sequences via Swin Transformer and Densely Cascaded Network

Add code
Jan 17, 2023
Viaarxiv icon

DiffuPose: Monocular 3D Human Pose Estimation via Denoising Diffusion Probabilistic Model

Add code
Dec 09, 2022
Figure 1 for DiffuPose: Monocular 3D Human Pose Estimation via Denoising Diffusion Probabilistic Model
Figure 2 for DiffuPose: Monocular 3D Human Pose Estimation via Denoising Diffusion Probabilistic Model
Figure 3 for DiffuPose: Monocular 3D Human Pose Estimation via Denoising Diffusion Probabilistic Model
Figure 4 for DiffuPose: Monocular 3D Human Pose Estimation via Denoising Diffusion Probabilistic Model
Viaarxiv icon

S2P: State-conditioned Image Synthesis for Data Augmentation in Offline Reinforcement Learning

Add code
Sep 30, 2022
Figure 1 for S2P: State-conditioned Image Synthesis for Data Augmentation in Offline Reinforcement Learning
Figure 2 for S2P: State-conditioned Image Synthesis for Data Augmentation in Offline Reinforcement Learning
Figure 3 for S2P: State-conditioned Image Synthesis for Data Augmentation in Offline Reinforcement Learning
Figure 4 for S2P: State-conditioned Image Synthesis for Data Augmentation in Offline Reinforcement Learning
Viaarxiv icon

FS-NCSR: Increasing Diversity of the Super-Resolution Space via Frequency Separation and Noise-Conditioned Normalizing Flow

Add code
Apr 20, 2022
Figure 1 for FS-NCSR: Increasing Diversity of the Super-Resolution Space via Frequency Separation and Noise-Conditioned Normalizing Flow
Figure 2 for FS-NCSR: Increasing Diversity of the Super-Resolution Space via Frequency Separation and Noise-Conditioned Normalizing Flow
Figure 3 for FS-NCSR: Increasing Diversity of the Super-Resolution Space via Frequency Separation and Noise-Conditioned Normalizing Flow
Figure 4 for FS-NCSR: Increasing Diversity of the Super-Resolution Space via Frequency Separation and Noise-Conditioned Normalizing Flow
Viaarxiv icon

Learning a Domain-Agnostic Visual Representation for Autonomous Driving via Contrastive Loss

Add code
Mar 10, 2021
Figure 1 for Learning a Domain-Agnostic Visual Representation for Autonomous Driving via Contrastive Loss
Figure 2 for Learning a Domain-Agnostic Visual Representation for Autonomous Driving via Contrastive Loss
Figure 3 for Learning a Domain-Agnostic Visual Representation for Autonomous Driving via Contrastive Loss
Figure 4 for Learning a Domain-Agnostic Visual Representation for Autonomous Driving via Contrastive Loss
Viaarxiv icon