Injae Kim profile photo

Injae Kim

M.S & Ph.D Integrated Student in MLV Lab, advised by Prof. Hyunwoo J. Kim.

School of Computing at KAIST, Daejeon, Republic of Korea.

My research focuses on 3D computer vision, neural rendering, and 3D scene representation. I am interested in Neural Radiance Fields, 3D Gaussian Splatting, feed-forward 3D reconstruction, and robust visual understanding.

If you are interested in collaboration, opportunities, or just a quick chat, please feel free to reach out to me.

selected publications [full list]

(*) denotes equal contribution

  1. arXiv
    RLSplat Figure 1: quality, memory, and inference latency across Gaussian budgets
    RLSplat: Resource-Linear Budget Control for Feed-forward 3D Gaussian Splatting
    Injae Kim, Minseok Joo, Jihwan Park, Sehyung Kim, Minseong Bae, and Hyunwoo J. Kim
    arXiv preprint arXiv:2610.27712, 2026
    Paper Code Project
  2. ECCV
    F4Splat teaser
    F4Splat: Feed-Forward Predictive Densification for Feed-Forward 3D Gaussian Splatting
    Injae Kim, Chaehyeon Kim, Minseong Bae, Minseok Joo, and Hyunwoo J. Kim
    In European Conference on Computer Vision (ECCV 2026)
    PDF Code Project
  3. NeurIPS
    UP-NeRF teaser
    UP-NeRF: Unconstrained Pose-Prior-Free Neural Radiance Fields
    Injae Kim*, Minhyuk Choi*, and Hyunwoo J. Kim
    In Advances in Neural Information Processing Systems (NeurIPS 2023)
    PDF Code Project
  4. MICCAI Workshop
    Concept Bottleneck teaser
    Concept Bottleneck with Visual Concept Filtering for Explainable Medical Image Classification
    Injae Kim, Jongha Kim, Joonmyung Choi, and Hyunwoo J. Kim
    In MICCAI 2023 Workshop (Oral Presentation)
    PDF
  5. NeurIPS
    SageMix teaser
    SageMix: Saliency-Guided Mixup for Point Clouds
    Sanghyeok Lee*, Minkyu Jeon*, Injae Kim, Yunyang Xiong, and Hyunwoo J. Kim
    In Advances in Neural Information Processing Systems (NeurIPS 2022)
    PDF Code