Xinran Duan / 段欣然

Xinran Duan / 段欣然

Multimodal foundation models, agentic AI, and video understanding.

Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Pages

Posts

Future Blog Post

less than 1 minute read

Published:

This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.

Blog Post number 4

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 3

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 2

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 1

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

portfolio

publications

ST-4DGS: Spatial-Temporally Consistent 4D Gaussian Splatting for Efficient Dynamic Scene Rendering

Published in SIGGRAPH 2024, 2024

Dynamic scene rendering at any novel views continues to be a difficult but important task, especially for high-fidelity rendering quality at real-time rendering speed. The recent 3D Gaussian Splatting, i.e., 3DGS, shows great success for static scene rendering with impressive quality at very efficient speed, however, the extension of 3DGS from static scene to dynamic as 4DGS is still challenging, especially to maintain the spatial-temporally persistent dynamic rendering quality. This paper proposes a novel spatial-temporally consistent 4D Gaussian Splatting, i.e., ST-4DGS, for real-time dynamic scene rendering which especially aims at the spatial-temporally persistent dynamic rendering quality and maintain the real-time efficiency. The key ideas of ST-4DGS are two new novel mechanisms: (1) a spatial-temporal encoder for 4D Gaussians representations but with a motion-aware shape regularization, and (2) a spatial-temporally joint density control, which are very effective to prevent the compactness degeneration for the 4D Gaussians representation during the dynamic scene learning, thus leading to spatial-temporally consistent dynamic rendering quality while in efficient manner. With extensive evaluation on public datasets, our ST-4DGS can achieve much better dynamic rendering quality than previous dynamic rendering approaches, such as 4DGS, HexPlane, K-Plane etc, and in a more efficient way for real-time dynamic rendering. To our best knowledge, we are the first 4D Gaussian Splatting for high-fidelity dynamic rendering at real-time speed, especially ensuring the spatial-temporally consistent rendering quality.

Download here

RemapVR: An Immersive Authoring Tool for Rapid Prototyping of Remapped Interaction in VR

Published in CHI 2025, 2025

Remapping techniques in VR such as repositioning, redirection, and resizing have been extensively studied. Still, interaction designers rarely have the opportunity to use them due to high technical and knowledge barriers. In the paper, we extract common features of 24 existing remapping techniques and develop a high-fidelity immersive authoring tool, namely RemapVR, for rapidly building and experiencing prototypes of remapped space properties in VR that are unperceivable or acceptable to users. RemapVR provides designers with a series of functions for editing remappings and visualizing spatial property changes, mapping relationships between real and virtual worlds, sensory conflicts, etc. Designers can quickly build existing remappings via templates, and author new remappings by interactively recording spatial relations between input trajectory in real world and output trajectory in virtual world. User studies showed that the designs of RemapVR can effectively improve designers' authoring experience and efficiency, and support designers to author remapping prototypes that meet scene requirements and provide good user experience.

Recommended citation: it is not available yet. http://kong-johnny.github.io/files/RemapVR-An-Immersive-Authoring-Tool-for-Rapid-Prototyping-of-Remapped-Interaction-in-VR.pdf

Curvature-Guided Task Synergy for Skeleton based Temporal Action Segmentation

Published in ICLR 2026, 2026

CurvSeg addresses the conflicting temporal requirements of action classification and boundary localization through expert-driven decoupling and curvature-guided bidirectional collaboration.

Recommended citation: Guozhang Li*, Xinran Duan*, Mei Wang, Lizhi Wang, and Hua Huang. Curvature-Guided Task Synergy for Skeleton based Temporal Action Segmentation. ICLR 2026. *Equal contribution. https://openreview.net/forum?id=Vgh30npuN3

talks

teaching

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.

Undergraduate educational experience

Undergraduate course, Beijing Normal University, School of Artificial Intelligence, 2020

This is a description of a teaching experience. You can use markdown like any other post.