Guangkai Xu

6 papers · 2023–2026 · 5 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (14) 🐣 Hot Topic Early Bird ❓ The Questioner

Venues

ICCV (2) AAAI (1) CVPR (1) ICLR (1) NeurIPS (1)

Top co-authors

Hao Chen (6) Chunhua Shen (5) Yongtao Ge (2) Bo Zhang (1) Muzhi Zhu (1) Dongyan Guo (1) Yang Liu (1) Xinlong Wang (1) Yanlong Sun (1) Huanyi Zheng (1)

Research topics

Computer Vision (6) Analysis (6) Deep Learning (3) Models (3) Artificial Intelligence (2) Machine Learning (2) Core AI (1) Generation (1) Learning Paradigms (1) Learning Types · Machine Learning (1) Learning Types · Deep Learning (1) Optimization & Theory (1) Processing (1)

Keywords

depth estimation (4) diffusion model (2) 3d reconstruction (2) image restoration (1) pose estimation (1) motion estimation (1) in-context learning (1) monocular depth estimation (1) surface normal estimation (1) scene reconstruction (1) dynamic scene (1) test-time optimization (1) latent diffusion model (1) camera pose (1) camera pose estimation (1) few-shot semantic segmentation (1) in-context segmentation (1) support-query interaction (1) geometric consistency (1) image matting (1)

Papers

Unlocking the Power of Critical Factors for 3D Visual Geometry Estimation CVPR 2026 DiffCalib: Reformulating Monocular Camera Calibration as Diffusion-Based Dense Incident Map Generation AAAI 2025 POMATO: Marrying Pointmap Matching with Temporal Motions for Dynamic 3D Reconstruction ICCV 2025 What Matters When Repurposing Diffusion Models for General Dense Perception Tasks? ICLR 2025 Unleashing the Potential of the Diffusion Model in Few-shot Semantic Segmentation NeurIPS 2024 FrozenRecon: Pose-free 3D Scene Reconstruction with Frozen Depth Models ICCV 2023