Shangzhan Zhang

Selected Work

• 2026

  Geometric Context Transformer for Streaming 3D Reconstruction

  Lin-Zhuo Chen*, Jian Gao*, Shangzhan Zhang*, Yihang Chen, Nan Xue, Jianyuan Wang, Christian Rupprecht, Xun Cao, Xing Zhu, Yujun Shen, Yao Yao, Yinghao Xu

  ECCV 2026 · Best Paper Candidate

  Reconstructing 3D scenes from streaming video with a geometric context transformer that maintains spatial consistency over long sequences.

  Project Paper Code
• 2026

  VGGT-Ω

  Jianyuan Wang, Minghao Chen, Shangzhan Zhang, Nikita Karaev, Johannes Schönberger, Patrick Labatut, Piotr Bojanowski, David Novotny, Andrea Vedaldi, Christian Rupprecht

  CVPR 2026 · Best Paper Finalist

  Scaling feed-forward 3D reconstruction to learn spatial representations that also support language alignment and vision-language-action models.

  Project Paper Code
• 2026

  GUI-SAGE: Enhancing GUI Automation with Self-Explanatory Learning

  Fei Tang, Zhangxuan Gu, Zhengxi Lu, Shangzhan Zhang, Zhengwen Zeng, Shuheng Shen, Changhua Meng, Yuchen Yan, Wenqi Zhang, Yongliang Shen, Weiming Lu, Yueting Zhuang

  CVPR 2026

  Improving GUI agents through self-explanatory reasoning and reinforcement learning, with entropy-aware credit assignment for more effective action learning.

  Paper
• 2025

  FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views

  Shangzhan Zhang*, Jianyuan Wang*, Yinghao Xu*, Nan Xue, Christian Rupprecht, Xiaowei Zhou, Yujun Shen, Gordon Wetzstein

  CVPR 2025

  Jointly estimating cameras, 3D geometry, and appearance from a few unposed images in a single forward pass.

  Project Paper Code
• 2024

  MaPa: Text-driven Photorealistic Material Painting for 3D Shapes

  Shangzhan Zhang, Sida Peng, Tao Xu, Yuanbo Yang, Tianrun Chen, Nan Xue, Yujun Shen, Hujun Bao, Ruizhen Hu, Xiaowei Zhou

  SIGGRAPH 2024

  An early exploration of LLM tool calling for graphics, enabling language-guided editing of procedural materials for 3D shapes.

  Paper