I'm actively seeking a research scientist position for alternative military service! for Fall 2026
I am a ML-aided visual computing researcher—computer vision, computer graphics, and generative AI. My academic footprints cross 2D/3D editing, multimodal generation, and neural rendering system for entertainment fields.
Tex-Shadow: Synthesizing Textured 3D Shadow Art via 3D-Aware Diffusion Prior
SIGGRAPH Posters, 2026 (accepted)
Sounds That Shape: Audio-Driven 3D Mesh Generation with Attribute-Decoupled Score Distillation Sampling
ICASSP, 2026
Make VLM Recognize Visual Hallucination or Cartoon Character Image with Pose Information
Bumsoo Kim*, Wonseop Shin*, Kyuchul Lee, Yonghoon Jung, Sanghyun Seo
WACV, 2025
ToonAging: Face Re-Aging upon Artistic Portrait Style Transfer
Bumsoo Kim, Abdul Muqeet, Kyuchul Lee, Sanghyun Seo
Minecraft-ify: Minecraft Style Image Generation with Text-guided Image Editing for In-Game Application
Bumsoo Kim, Sanghyun Byun, Yonghoon Jung, Wonseop Shin, Sareer UI Amin, Sanghyun Seo
Tex-Shadow: Synthesizing Textured 3D Shadow Art via 3D-Aware Diffusion Prior
SIGGRAPH Posters, 2026 (accepted)
How Generative Models Serve as Visual Artists for Creative Interpolation
CVPR Workshop, 2026 (rejected)
Sounds That Shape: Audio-Driven 3D Mesh Generation with Attribute-Decoupled Score Distillation Sampling
ICASSP, 2026
Learning Pose‑to‑Semantic for 3D Anamorphic Art based on 2D Diffusion Guidance
MS Thesis, 2026
VideoTimeTravel: high-fidelity face re-aging diffusion models for production video
Visual Computer (IF:2.9), 2026
Taming Gaussian Densification in Score Distillation Sampling for High-Fidelity Text-to-3D Generation
CGI, 2026 (rejected)
MultiFloodSynth: Multi-Annotated Flood Synthetic Dataset Generation
YoonJe Kang*, Yonghoon Jung*, Wonseop Shin*,
Bumsoo Kim*, Sanghyun Seo
Make VLM Recognize Visual Hallucination or Cartoon Character Image with Pose Information
Bumsoo Kim*, Wonseop Shin*, Kyuchul Lee, Yonghoon Jung, Sanghyun Seo
WACV, 2025
Scent2Scene: A Participatory Olfactory-to-Visual Experience Using Brain-Computer Interfaces and Generative AI
Rakbin Sung*, Seongmi Woo*, Dongmin Shin,
Bumsoo Kim, Yonghoon Jung, Daewon Lee†, Sanghyun Seo†, Hye-Young Jo†, Yoonji Kim†
2025
Explicitly Color-Inspired Neural Style Transfer Using Patchified AdaIN
Bumsoo Kim, Wonseop Shin, Younghoon Jung, Youngsup Park, Sanghyun Seo
CMES (Q2), 2024
ToonAging: Face Re-Aging upon Artistic Portrait Style Transfer
Bumsoo Kim, Abdul Muqeet, Kyuchul Lee, Sanghyun Seo
Minecraft-ify: Minecraft Style Image Generation with Text-guided Image Editing for In-Game Application
Bumsoo Kim, Sanghyun Byun, Yonghoon Jung, Wonseop Shin, Sareer UI Amin, Sanghyun Seo
Video Face Re-Aging: Toward Temporally Consistent Face Re-Aging
Abdul Muqeet*, Kyuchul Lee*,
Bumsoo Kim, Yohan Hong, Hyungrae Lee, Woonggon Kim, KwangHee Lee
arXiv, 2023
EfficientNetV2-based dynamic gesture recognition using transformed scalogram from triaxial acceleration signal
JCDE (IF:4.9), 2023
Intelligent Digital Human Agent Service With Deep Learning Based-Face Recognition
IEEE Access (IF:3.9), 2022
Tex-Shadow: Synthesizing Textured 3D Shadow Art via 3D-Aware Diffusion Prior
SIGGRAPH Posters, 2026 (accepted)
Sounds That Shape: Audio-Driven 3D Mesh Generation with Attribute-Decoupled Score Distillation Sampling
ICASSP, 2026
Taming Gaussian Densification in Score Distillation Sampling for High-Fidelity Text-to-3D Generation
CGI, 2026 (rejected)
MultiFloodSynth: Multi-Annotated Flood Synthetic Dataset Generation
YoonJe Kang*, Yonghoon Jung*, Wonseop Shin*,
Bumsoo Kim*, Sanghyun Seo
VideoTimeTravel: high-fidelity face re-aging diffusion models for production video
Visual Computer (IF:2.9), 2026
ToonAging: Face Re-Aging upon Artistic Portrait Style Transfer
Bumsoo Kim, Abdul Muqeet, Kyuchul Lee, Sanghyun Seo
Video Face Re-Aging: Toward Temporally Consistent Face Re-Aging
Abdul Muqeet*, Kyuchul Lee*,
Bumsoo Kim, Yohan Hong, Hyungrae Lee, Woonggon Kim, KwangHee Lee
arXiv, 2023
Awesome Physical Audio
(TBD)
Awesome Acoustic-Image
(TBD)
Sounds That Shape: Audio-Driven 3D Mesh Generation with Attribute-Decoupled Score Distillation Sampling
ICASSP, 2026
Tex-Shadow: Synthesizing Textured 3D Shadow Art via 3D-Aware Diffusion Prior
SIGGRAPH Posters, 2026 (accepted)
How Generative Models Serve as Visual Artists for Creative Interpolation
CVPR Workshop, 2026 (rejected)
Learning Pose‑to‑Semantic for 3D Anamorphic Art based on 2D Diffusion Guidance
MS Thesis, 2026
Make VLM Recognize Visual Hallucination or Cartoon Character Image with Pose Information
Bumsoo Kim*, Wonseop Shin*, Kyuchul Lee, Yonghoon Jung, Sanghyun Seo
WACV, 2025
Scent2Scene: A Participatory Olfactory-to-Visual Experience Using Brain-Computer Interfaces and Generative AI
Rakbin Sung*, Seongmi Woo*, Dongmin Shin,
Bumsoo Kim, Yonghoon Jung, Daewon Lee†, Sanghyun Seo†, Hye-Young Jo†, Yoonji Kim†
2025
Explicitly Color-Inspired Neural Style Transfer Using Patchified AdaIN
Bumsoo Kim, Wonseop Shin, Younghoon Jung, Youngsup Park, Sanghyun Seo
CMES (Q2), 2024
Minecraft-ify: Minecraft Style Image Generation with Text-guided Image Editing for In-Game Application
Bumsoo Kim, Sanghyun Byun, Yonghoon Jung, Wonseop Shin, Sareer UI Amin, Sanghyun Seo
EfficientNetV2-based dynamic gesture recognition using transformed scalogram from triaxial acceleration signal
JCDE (IF:4.9), 2023
Intelligent Digital Human Agent Service With Deep Learning Based-Face Recognition
IEEE Access (IF:3.9), 2022
Biography (2026)
Bumsoo Kim received the BSc and MSc in art and technology from Chung-Ang University, South Korea, in 2023, 2026. He worked for machine learning algorithm and its industrial system at ETRI, VIVE STUDIOS, and Boeing Research & Technology, South Korea. His research areas include generative models on computer graphics.
Research fields: Multi-modal 2D/3D/Video generation and editing, audio-visual integration, differentiable rendering, and other artistic and gaming tasks.
Academic lineage
Community Service
- (2024) Reviewer for CVPR 2024, ICLR 2025, WACV 2025
- (2025) Reviewer for AAAI 2026, ICLR 2026, ICASSP 2026
- (2026) Reviewer for ECCV 2026
Miscellaneous
I’ve always been fascinated by artistic and immersive experiences. I enjoy films, music, and creative media, and I was once the lead guitarist in my school rock band. After completing final degree, I plan to present my own interactive artworks in an exhibition.
Official Code Implementation
Unofficial Code Implementation
Stable Maintenance Version from Official Repo