Haian Jin's Homepage

⚓ About Me

Hi👋! My name is Haian Jin (金海岸), which means "Golden Coast" in Chinese. I'm currently a second-year Ph.D. student in Computer Science at Cornell University working with Prof. Noah Snavely. My research interest lies in the intersection between Computer Vision, Graphics, and Machine Learning.

Previously, I completed my bachelor's degree (2019-2023) in Computer Science with highest honors from the Chu Kochen Honors College of Zhejiang University, ranking top 1% (overall GPA: 3.98/4.0, 92.7/100). During my undergraduate, I was fortunate to work closely with Prof. Hao Su at UCSD and Prof. Xiaowei Zhou at ZJU.

📝 Publications and Preprints

(* denotes equal contribution, and † denotes equal advisory.)

	LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias Haian Jin, Hanwen Jiang, Hao Tan, Kai Zhang, Sai Bi, Tianyuan Zhang, Fujun Luan, Noah Snavely, Zexiang Xu arXiv 2024 [New] Project Page / Paper / Code (coming soon!)
	RelitLRM: Generative Relightable Radiance for Large Reconstruction Models Tianyuan Zhang, Zhengfei Kuang, Haian Jin, Zexiang Xu, Sai Bi, Hao Tan, He Zhang, Yiwen Hu, Milos Hasan, William T. Freeman, Kai Zhang^†, Fujun Luan^† arXiv 2024 [New] Project Page / Paper
	Neural Gaffer: Relighting Any Object via Diffusion Haian Jin, Yuan Li, Fujun Luan, Yuanbo Xiangli, Sai Bi, Kai Zhang, Zexiang Xu, Jin Sun, Noah Snavely NeurIPS 2024 Project Page / Paper / Code
	OpenIllumination: A Multi-Illumination Dataset for Inverse Rendering Evaluation on Real Objects Isabella Liu^, Linghao Chen^, Ziyang Fu, Liwen Wu, Haian Jin, Zhong Li, Chin Ming Ryan Wong, Yi Xu, Ravi Ramamoorthi, Zexiang Xu, Hao Su NeurIPS 2023 Datasets and Benchmarks Project Page / Paper
	One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization Minghua Liu^, Chao Xu^, Haian Jin^, Linghao Chen^, Mukund Varma T, Zexiang Xu, Hao Su NeurIPS 2023 Project Page / Paper / Code 👉Brief summary: Many existing image-to-3D methods optimizes a neural radiance field under the guidance of 2D diffusion models but suffer from lengthy optimization time, 3D inconsistency results, and poor geometry. In this work, we propose a novel method that takes a single image of any object as input and generates a full 360-degree 3D textured mesh in a single feed-forward pass. Without costly optimizations, our method reconstructs 3D shapes in significantly less time than existing methods. Moreover, our method favors better geometry, generates more 3D consistent results, and adheres more closely to the input image. In addition, our approach can seamlessly support the text-to-3D task by integrating with off-the-shelf text-to-image diffusion models.
	TensoIR: Tensorial Inverse Rendering Haian Jin^, Isabella Liu^, Peijia Xu, Xiaoshuai Zhang, Songfang Han, Sai Bi, Xiaowei Zhou, Zexiang Xu^†, Hao Su^† CVPR 2023 Project Page / Video / Paper / Code 👉Method highlights: Accurate modeling of visibility and indirect illumination on-the-fly Enable efficient BRDF and geometry reconstruction under a single or multiple unknown lighting conditions Outperform previous NeRF-based and SDF-based inverse rendering pipelines

🎖 Honors and Awards

2022 - 2023 Outstanding Graduation Thesis Award of Zhejiang University
2022 - 2023 Outstanding Graduates of Zhejiang Province
2022 - 2023 Outstanding Graduates of Zhejiang University
2021 - 2022 Zhejiang Provincial Government Scholarship (top 5%)
2021 - 2022 Pilot Scholarship in Chu Kochen Honors College (top 5%)
2020 - 2021 Scholarship for Excellence in Chu Kochen Honors College (top 1%)
2020 - 2021 Zhejiang University Scholarship - First Prize (top 3%)
2019 - 2020 Zhejiang University Scholarship - First Prize (top 3%)
2019 - 2020 China National Scholarship (top 1%)