Tiange Xiang

Tiange Xiang 向天戈

Ph.D. Student, Stanford Vision and Learning Lab

Contact: {X @ Y}, X=xtiange, Y=stanford.edu

Biography

Tiange Xiang (向天戈) is a third-year CS Ph.D. student at Stanford University. He is affiliated with Stanford AI Lab & Stanford Vision and Learning Lab. He is advised by Prof. Fei-Fei Li, co-advised by Prof. Scott Delp and Prof. Ehsan Adeli. Part of his research is generously funded by Stanford HAI fellowship.

I am actively looking for junior students to collaborate on inetersting (and also challenging) 3D vision research problems. Please drop me an email if you are a Stanford student and want to do serious research on 3D digital human.

Name

Family name: 向(Xiàng) means the direction.

Given name: 天(Tiān) 戈(Gē) means the weapon from the heavenly realm.

Selected Conference Publications

[* indicates equal contribution, ^† indicates equal mentorship.]

OccFusion: Rendering Occluded Humans with Generative Diffusion Priors

Adam Sun*, Tiange Xiang*, Scott Delp, Li Fei-Fei^†, and Ehsan Adeli^†

[NeurIPS 2024] [Homepage] [Paper] [Code]

2D generative priors help inpaint occluded 3D humans.

NeuHMR: Neural Rendering-Guided Human Motion Reconstruction

Tiange Xiang, Kuan-Chieh Wang, Jaewoo Heo, Ehsan Adeli, Serena Yeung, Scott Delp, and Li Fei-Fei

[3DV 2025] [paper] [code]

Human mesh recovery guided via generalizable neural rendering.

Rendering Humans from Object-Occluded Monocular Videos

Tiange Xiang, Adam Sun, Jiajun Wu, Ehsan Adeli, and Li Fei-Fei

[ICCV 2023] [Homepage] [Paper] [Code]

We rendered human from object occluded videos.

SQUID: Deep Feature In-Painting for Unsupervised Anomaly Detection

Tiange Xiang, Yixiao Zhang, Yongyi Lu, Alan L. Yuille, Chaoyi Zhang, Weidong Cai, and Zongwei Zhou

[CVPR 2023] [Paper] [Code]

We re-formulated unsupervised anomaly detection as semantic-sapce in-painting.

Seeing Beyond the Brain: Conditional Diffusion Model with Sparse Masked Modeling for Vision Decoding

Zijiao Chen*, Jiaxin Qing*, Tiange Xiang, Wan Lin Yue, and Juan Helen Zhou

[CVPR 2023] [Homepage] [Paper] [Code]

We decoded photo-realistic visual stimuli from fMRI brain signals.

DDM²: Self-Supervised Diffusion MRI Denoising with Generative Diffusion Models

Tiange Xiang, Mahmut Yurt, Ali B Syed, Kawin Setsompop, and Akshay Chaudhari

[ICLR 2023] [Paper] [Code]

We achieved self-supervised MRI denoising through generative diffusion models.

Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis

Tiange Xiang, Chaoyi Zhang, Yang Song, Jianhui Yu, and Weidong Cai

[ICCV 2021] [Homepage] [Paper] [Code]

We proposed a geometry-aware feature aggregation operator for point cloud analysis.

BiX-NAS: Searching Efficient Bi-directional Architectures for Medical Image Segmentation

Xinyi Wang*, Tiange Xiang*, Chaoyi Zhang, Yang Song, Dongnan Liu, Heng Huang, and Weidong Cai

[MICCAI 2021] [Homepage] [Paper] [Code]

We proposed a NAS method to search efficient bi-directional architectures.

BiO-Net: Learning Recurrent Bidirectional Connections for Encoder-Decoder Architecture

Tiange Xiang, Chaoyi Zhang, Dongnan Liu, Yang Song, Heng Huang, and Weidong Cai

[MICCAI 2020] [Homepage] [Paper] [Code]

We proposed bi-directional skip connections in the encoder-decoder architecture.

Journal Publications

[* indicates equal contribution]

Exploiting Structural Consistency of Chest Anatomy for Unsupervised Anomaly Detection in Radiography Images

Tiange Xiang*, Yixiao Zhang*, Yongyi Lu, Alan L. Yuille, Chaoyi Zhang, Weidong Cai, and Zongwei Zhou

[TPAMI 2024] [Paper] [Code]

A faster and stronger network for chest X-ray anomaly detection.

Towards Bi-directional Skip Connections in Encoder-Decoder Architectures and Beyond

Tiange Xiang, Chaoyi Zhang, Xinyi Wang, Yang Song, Dongnan Liu, Heng Huang, and Weidong Cai

[MedIA 2022] [Homepage] [Paper]

An efficient and light-weight encoder-decoder network with SOTA performances.

DSNet: A Weakly-Supervised Dual-Stream Framework for Effective Gigapixel Pathology Image Analysis

Tiange Xiang, Yang Song, Chaoyi Zhang, Dongnan Liu, Mei Chen, Fan Zhang, Heng Huang, Lauren O'Donnell, and Weidong Cai

[TMI 2022] [Paper]

We proposed to combine global-local clues for weakly-supervised WSI analysis.

Preprints

[* indicates equal contribution]

Wild2Avatar: Rendering Humans Behind Occlusions

Tiange Xiang, Adam Sun, Scott Delp, Kazuki Kozuka, Li Fei-Fei^†, and Ehsan Adeli^†

[Arxiv] [Homepage] [Paper] [Code]

High-fidelity human rendering from monocular occluded videos.

Partial Graph Reasoning for Neural Network Regularization

Tiange Xiang, Chaoyi Zhang, Yang Song, Siqi Liu, Hongliang Yuan, and Weidong Cai

[arXiv] [Paper]

Two-Stage Monte Carlo Denoising with Adaptive Sampling and Kernel Pool

Tiange Xiang, Hongliang Yuan, Haozhi Huang, and Yujin Shi

[arXiv] [Paper]

Education

Stanford University

Ph.D. Student in Computer Science

Palo Alto, CA, U.S.

Present

Stanford University

M.S. in Computer Science (petition during Ph.D.)

Palo Alto, CA, U.S.

June. 2024

the University of Sydney

B.S. in Computer Science and Technology (Advanced) (Honours)

Sydney, NSW, Australia

July. 2022

Service

Conference reviewer:

CVPR (2021,2022,2023,2024,2025), MICCAI (2021,2022,2023,2024), ICCV 2023, ECCV (2022,2024), ICLR 2025, ICML 2022, NeurIPS (2022,2024), WACV (2023,2024), AAAI 2025, AISTATS 2025.

Jounral reviewer:

IEEE TPAMI, IEEE TIP, IEEE TMI, IEEE IV, Neurocomputing, Scientific Reports.

Teaching assistant:

CS 231n (Stanford, Spring 2024), CS 231n (Stanford, Spring 2023), COMP 3419 (USYD, Fall 2019)