Beiwen Tian

Beiwen Tian

Auto-generated profile, based on publicly available information

Beiwen Tian

Tsinghua University, Beijing, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 November 2022 in ISPRS Journal of Photogrammetry and Remote Sensing
Verified
Journal Article
Closed access
BTBeiwen Tian
Beiwen Tian
LLLiyi Luo
Liyi Luo
HZHao Zhao
Hao Zhao
GZGuyue Zhou
Guyue Zhou

27 March 2024 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
XLXiaoxiao Long
Xiaoxiao Long
YZYuhang Zheng
Yuhang Zheng
YZYupeng Zheng
Yupeng Zheng
BTBeiwen Tian
Beiwen Tian
CLCheng Lin
Cheng Lin
WWWenping Wang
Wenping Wang
We introduce a novel approach to learn geometries such as depth and surface normal from images while incorporating geometric context. The difficulty of reliably capturing geometric context in existing methods impedes their ability to accurately enforce the consistency between the different geometric properties, thereby leading to a bottleneck of geometric estimation quality. We therefore propose the Adaptive Surface Normal (ASN) constraint, a simple yet efficient method. Our approach extracts geometric context that encodes the geometric variations present in the input image and correlates depth estimation with geometric constraints. By dynamically determining reliable local geometry from randomly sampled candidates, we establish a surface normal constraint, where the validity of these candidates is evaluated using the geometric context. Furthermore, our normal estimation leverages the geometric context to prioritize regions that exhibit significant geometric variations, which makes the predicted normals accurately capture intricate and detailed geometric information. Through the integration of geometric context, our method unifies depth and surface normal estimations within a cohesive framework, which enables the generation of high-quality 3D geometry from images. We validate the superiority of our approach over state-of-the-art methods through extensive evaluations and comparisons on diverse indoor and outdoor datasets, showcasing its efficiency and robustness.

9 October 2025 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
YDYuhang Dong
Yuhang Dong
HGHaizhou Ge
Haizhou Ge
YZYupei Zeng
Yupei Zeng
JZJiangning Zhang
Jiangning Zhang
BTBeiwen Tian
Beiwen Tian
GTGuanzhong Tian
Guanzhong Tian
Visuomotor imitation learning policies enable robots to efficiently acquire manipulation skills from visual demonstrations. However, as scene complexity and visual distractions increase, policies that perform well in simple settings often experience substantial performance degradation. To address this challenge, we propose ImitDiff, a diffusion-based imitation learning policy guided by fine-grained semantics within a dual-resolution workflow. Leveraging pretrained priors of vision-language foundation models, our method transforms high-level instructions into pixel-level visual semantic masks. These masks guide a dual-resolution perception pipeline that captures both global context (e.g., overall layout) from low-resolution observation and fine-grained local features (e.g., geometric details) from high-resolution observation, enabling the policy to focus on task-relevant regions. Additionally, we introduce a consistency-driven diffusion transformer action head that bridges visual semantic conditions and real-time action generation. Extensive experiments demonstrate that ImitDiff outperforms state-of-the-art vision-language manipulation frameworks, as well as visuomotor imitation learning policies, particularly under increased scene complexity and visual distractions. Notably, ImitDiff exhibits strong generalization in zero-shot settings involving novel objects and visual distractions. Furthermore, our consistency-driven action head achieves an order-of-magnitude improvement in inference speed while maintaining competitive success rates.