Search Results for author: Injae Kim

Found 4 papers, 2 papers with code

UP-NeRF: Unconstrained Pose-Prior-Free Neural Radiance Fields

1 code implementation7 Nov 2023 Injae Kim, Minhyuk Choi, Hyunwoo J. Kim

Neural Radiance Field (NeRF) has enabled novel view synthesis with high fidelity given images and camera poses.

Novel View Synthesis Pose Estimation

Concept Bottleneck with Visual Concept Filtering for Explainable Medical Image Classification

no code implementations23 Aug 2023 Injae Kim, Jongha Kim, Joonmyung Choi, Hyunwoo J. Kim

However, those methods do not consider whether a concept is visually relevant or not, which is an important factor in computing meaningful concept scores.

Image Classification Medical Image Classification

Semantic-aware Occlusion Filtering Neural Radiance Fields in the Wild

no code implementations5 Mar 2023 Jaewon Lee, Injae Kim, Hwan Heo, Hyunwoo J. Kim

We present a learning framework for reconstructing neural scene representations from a small number of unconstrained tourist photos.

Novel View Synthesis

SageMix: Saliency-Guided Mixup for Point Clouds

1 code implementation13 Oct 2022 Sanghyeok Lee, Minkyu Jeon, Injae Kim, Yunyang Xiong, Hyunwoo J. Kim

Mixup is a simple and widely-used data augmentation technique that has proven effective in alleviating the problems of overfitting and data scarcity.

3D Part Segmentation 3D Point Cloud Classification +3

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