Výsledky vyhledávání - "Park, Seonghoon"

Report

Cross-View Completion Models are Zero-shot Correspondence Estimators

Autor: An, Honggyu, Kim, Jinhyeon, Park, Seonghoon, Jung, Jaewoo, Han, Jisang, Hong, Sunghwan, Kim, Seungryong

In this work, we explore new perspectives on cross-view completion learning by drawing an analogy to self-supervised correspondence learning. Through our analysis, we demonstrate that the cross-attention map within cross-view completion models captur

Externí odkaz: http://arxiv.org/abs/2412.09072

Zobrazit plný text záznamu

Report

Relaxing Accurate Initialization Constraint for 3D Gaussian Splatting

Autor: Jung, Jaewoo, Han, Jisang, An, Honggyu, Kang, Jiwon, Park, Seonghoon, Kim, Seungryong

3D Gaussian splatting (3DGS) has recently demonstrated impressive capabilities in real-time novel view synthesis and 3D reconstruction. However, 3DGS heavily depends on the accurate initialization derived from Structure-from-Motion (SfM) methods. Whe

Externí odkaz: http://arxiv.org/abs/2403.09413

Zobrazit plný text záznamu

Report

Context Enhanced Transformer for Single Image Object Detection

Autor: An, Seungjun, Park, Seonghoon, Kim, Gyeongnyeon, Baek, Jeongyeol, Lee, Byeongwon, Kim, Seungryong

With the increasing importance of video data in real-world applications, there is a rising need for efficient object detection methods that utilize temporal information. While existing video object detection (VOD) techniques employ various strategies

Externí odkaz: http://arxiv.org/abs/2312.14492

Zobrazit plný text záznamu

Report

DaRF: Boosting Radiance Fields from Sparse Inputs with Monocular Depth Adaptation

Autor: Song, Jiuhn, Park, Seonghoon, An, Honggyu, Cho, Seokju, Kwak, Min-Seop, Cho, Sungjin, Kim, Seungryong

Neural radiance fields (NeRF) shows powerful performance in novel view synthesis and 3D geometry reconstruction, but it suffers from critical performance degradation when the number of known viewpoints is drastically reduced. Existing works attempt t

Externí odkaz: http://arxiv.org/abs/2305.19201

Zobrazit plný text záznamu

Report

MaskingDepth: Masked Consistency Regularization for Semi-supervised Monocular Depth Estimation

Autor: Baek, Jongbeom, Kim, Gyeongnyeon, Park, Seonghoon, An, Honggyu, Poggi, Matteo, Kim, Seungryong

We propose MaskingDepth, a novel semi-supervised learning framework for monocular depth estimation to mitigate the reliance on large ground-truth depth quantities. MaskingDepth is designed to enforce consistency between the strongly-augmented unlabel

Externí odkaz: http://arxiv.org/abs/2212.10806

Zobrazit plný text záznamu