Picture for Seunghyeon Seo

Seunghyeon Seo

DivCon-NeRF: Generating Augmented Rays with Diversity and Consistency for Few-shot View Synthesis

Add code
Mar 17, 2025
Viaarxiv icon

ROODI: Reconstructing Occluded Objects with Denoising Inpainters

Add code
Mar 13, 2025
Viaarxiv icon

Unleash the Potential of CLIP for Video Highlight Detection

Add code
Apr 02, 2024
Figure 1 for Unleash the Potential of CLIP for Video Highlight Detection
Figure 2 for Unleash the Potential of CLIP for Video Highlight Detection
Figure 3 for Unleash the Potential of CLIP for Video Highlight Detection
Viaarxiv icon

HourglassNeRF: Casting an Hourglass as a Bundle of Rays for Few-shot Neural Rendering

Add code
Mar 16, 2024
Viaarxiv icon

Fast Sun-aligned Outdoor Scene Relighting based on TensoRF

Add code
Nov 07, 2023
Viaarxiv icon

ConcatPlexer: Additional Dim1 Batching for Faster ViTs

Add code
Aug 22, 2023
Viaarxiv icon

FlipNeRF: Flipped Reflection Rays for Few-shot Novel View Synthesis

Add code
Jul 16, 2023
Viaarxiv icon

MixNeRF: Modeling a Ray with Mixture Density for Novel View Synthesis from Sparse Inputs

Add code
Feb 17, 2023
Viaarxiv icon

MDPose: Real-Time Multi-Person Pose Estimation via Mixture Density Model

Add code
Feb 17, 2023
Viaarxiv icon

Sparse MDOD: Training End-to-End Multi-Object Detector without Bipartite Matching

Add code
May 18, 2022
Figure 1 for Sparse MDOD: Training End-to-End Multi-Object Detector without Bipartite Matching
Figure 2 for Sparse MDOD: Training End-to-End Multi-Object Detector without Bipartite Matching
Figure 3 for Sparse MDOD: Training End-to-End Multi-Object Detector without Bipartite Matching
Figure 4 for Sparse MDOD: Training End-to-End Multi-Object Detector without Bipartite Matching
Viaarxiv icon