Gyeongsu (Bob) Cho

I am a Ph.D. student in the Artificial Intelligence Graduate School at UNIST, where I am a member of the 3D Vision & Robotics Lab under Prof. Kyungdon Joo's supervision. I received a B.Eng. in Mechanical Engineering from Chung-Ang University.

I am actively seeking internship opportunities at academic or industrial research teams.
I’m always open to new collaborations — feel free to reach out to me at threedv@unist.ac.kr.

Email / CV / LinkedIn / GitHub

Research

I am passionate about creating models that do not yet exist — models capable of reconstructing, animating, and generating dynamic 3D and 4D content, especially for animals and humans. My work combines synthetic data pipelines, parametric animal/human models, and generative methods to lift 2D images and videos into animatable 3D/4D representations. I enjoy building tools and models that unlock new creative and scientific possibilities in computer vision and graphics.

	AniGauss: Toward Animatable Animal Reconstruction from Single In-the-Wild Images via Topology-Aware Gaussians CV4Animals Workshop @ CVPR 2026 [paper] / [project page] We present a topology-aware Gaussian framework for animatable animal reconstruction from a single in-the-wild image.
	Multi Dance Project In submission (ECCV) [paper] / [project page] An ongoing project on multi-dance modeling is currently under review. More details will be released after the review process.
	Video Anomaly Detection in Display Inspection In submission (IROS) [paper] / [project page] We present a novel framework for video anomaly detection, where multiple devices are concurrently monitored by an external camera during operation. This work was done in collaboration with Samsung Electronics.
	WildAni4D: Towards 4D Animal Mesh Reconstruction Gyeongsu Cho, Hezhen Hu, Donghyeon Soon, Changwoo Kang, Kyungdon Joo CVPR 2026 Findings [paper] / [project page] We present a synthetic animal video pipeline and a video transformer model for reconstructing temporally coherent 4D animal motion and global trajectories from monocular in-the-wild videos. This project is part of a research collaboration with UT Austin.
	Pose-Diverse Multi-View Virtual Try-on from a Single Frontal Image Seonghee Han, Minchang Chung, Gyeongsu Cho, Kyungdon Joo, Taehwan Kim WACV 2026 [paper] / [project page] This work generates pose-diverse, multi-view images for virtual try-on starting from a single frontal input. By leveraging multi-view consistency and pose conditioning, the method produces realistic, view-consistent outfits under large pose variations.
	Avatar++: Fast and Pose-Controllable 3D Human Avatar Generation from a Single Image Seonghee Han, Minchang Chung, Gyeongsu Cho, Kyungdon Joo, Taehwan Kim Wild3D Workshop @ ICCVW 2025 [paper] / [project page] Avatar++ generates an animation-ready 3D human avatar from a single image in seconds. By combining identity-preserving features with pose-guided multi-view synthesis, the framework enables fast and controllable avatar creation for downstream animation and XR applications.
	DogRecon: Canine Prior-Guided Animatable 3D Gaussian Dog Reconstruction From a Single Image Gyeongsu Cho, Changwoo Kang, Donghyeon Soon, Kyungdon Joo International Journal of Computer Vision (IJCV), 2025 [paper] / [project page] DogRecon is a framework that reconstructs animatable 3D Gaussian dog models from a single RGB image. It leverages a canine prior and a reliable sampling strategy to obtain high-quality 3D shapes and realistic animations of dogs from in-the-wild photos.
	Canine Prior-Guided Animatable 3D Gaussian Dog Reconstruction From a Single Image Gyeongsu Cho, Changwoo Kang, Donghyeon Soon, Kyungdon Joo CV4Animals Workshop @ CVPRW 2024 (Oral) [paper] / [oral video] This workshop version presents the initial DogRecon framework for animatable 3D Gaussian dog reconstruction from a single image, focusing on canine priors and practical reconstruction quality for in-the-wild photos.
	SlaBins: Fisheye Depth Estimation using Slanted Bins on Road Environments Jongsung Lee, Gyeongsu Cho, Jeongin Park, Kyongjun Kim, Seongoh Lee, Jung Hee Kim, Seong-Gyun Jeong, Kyungdon Joo ICCV 2023 [paper] / [project page] SlaBins introduces a slanted multi-cylindrical representation and adaptive depth bins to achieve accurate and dense depth estimation from automotive fisheye cameras in road environments. This work was done in collaboration with 42dot.

Selected Seminar Slides

A small archive of research seminar slides I presented while exploring topics in 3D vision, generative models, human/animal reconstruction, and research workflows.

2026.05	Agentic Coding Workflow for Research [slides]
2025.10	From Single-Image HMR to World-Grounded Video HMR [slides]
2025.05	AniMer (CVPR 2025) [slides]
2025.02	SEVA (arXiv 2025) [slides]
2025.02	LGM: Large Multi-view Gaussian Model (ECCV 2024) [slides]
2024.12	WonderJourney (CVPR 2024) [slides]
2024.05	Generative Rendering: Controllable 4D-Guided Video Generation with 2D Diffusion Models (CVPR 2024) [slides]
2024.01	ControlNet: Adding Conditional Control to Text-to-Image Diffusion Models (ICCV 2023) [slides]
2023.09	BANMo: Building Animatable 3D Neural Models from Many Casual Videos (CVPR 2022) [slides]
2023.05	NeuMan: Neural Human Radiance Field from a Single Video (ECCV 2022) [slides]
2022.07	Digging Into Self-Supervised Monocular Depth Estimation (ICCV 2019) [slides]
2022.04	MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesis (ICCV 2021) [slides]
2022.03	PixelSynth: Generating a 3D-Consistent Experience from a Single Image (ICCV 2021) [slides]

Academic Services

Reviewer, CVPR 2026
Reviewer, CV4Animals Workshop @ CVPR 2026
Reviewer, 4D Vision Workshop @ CVPR 2026

Education

Integrated M.S.–Ph.D. in Artificial Intelligence, Artificial Intelligence Graduate School, UNIST, South Korea (2022.03 – Present)
B.Eng. in Mechanical Engineering, Chung-Ang University, South Korea (2018.03 – 2021.08)

Research & Industry Experience

Graduate Researcher, UNIST – 3D/4D Vision & Graphics (2022 – Present)
Lead author of DogRecon (IJCV 2025), AniGauss (CV4Animals Workshop @ CVPR 2026), and WildAni4D (CVPR 2026 Findings) on single-image and 4D animatable animal reconstruction. Develop synthetic video pipelines, SMAL-based animal models, and PyTorch3D-based renderers for large-scale training and evaluation. Explore generative pipelines that lift text/video outputs into animatable 3D/4D representations.
Research Collaboration with Samsung Electronics – Video Anomaly Detection (2024 – 2025)
Co-developed a video anomaly detection framework for industrial display inspection using real manufacturing data. Contributed to dataset design, model architecture, and experiments for an IROS submission on reference-guided video anomaly detection.
Research Collaboration with UT Austin – 4D Animal and Human Reconstruction (2025 – Present)
Ongoing collaboration with Dr. Hezhen Hu (Postdoctoral Fellow, UT Austin) on 4D animal and human reconstruction research. Co-develop research projects including WildAni4D, AniGauss, and an ECCV-submitted multi-dance project. Work on model design and research development for animatable 4D animal and human motion and mesh reconstruction from monocular videos.
Startup Project – Real-Time 3D Human Pose Estimation (KIC & GWU Program, 2024)
Built a 3-camera real-time 3D human pose estimation system with smoothing algorithms for stable motion analysis in gyms, designed as an AI-based personal training assistant. Selected for a Korean government startup support program and a 3-week entrepreneurship program at George Washington University. Conducted 50+ interviews with fitness and healthcare professionals across major U.S. cities and refined a US-market–focused business model, ranking 1st in track.
Research Collaboration with 42dot – Autonomous Driving Research (Hyundai Motor Group) (ICCV 2023)
Collaborated on autonomous driving research with 42dot, the autonomous driving division of Hyundai Motor Group. Contributed to a project that was accepted to ICCV 2023.

Template from this website.