Zexin He

4 papers · 2023–2025 · 2 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 · Bronze 🌉 Interdisciplinary Bridge · Bronze

Venues

CVPR (3) ICLR (1)

Top co-authors

Ziwei Liu (2) Tengfei Wang (2) Jiaya Jia (2) Gerhard Petrus Hancke (1) Xin Huang (1) Yuechen Zhang (1) Xingang Pan (1) Jingyao Li (1) Shaozuo Yu (1) Jinbo Xing (1)

Research topics

Computer Vision (2) Deep Learning (2) Machine Learning (2) Models (2) Analysis (1) Application Areas (1) Core AI (1) Core Methods (1) Generation (1) Learning Types (1) Processing (1)

Keywords

diffusion model (2) self-supervised learning (1) geometry estimation (1) surface normal estimation (1) out-of-distribution detection (1) 3d generation (1) neural radiance field (1) scene stylization (1) controllable generation (1) material estimation (1) surface normal (1) semantic correspondence (1) pretext task (1) masked image modeling (1) multi-light diffusion (1) intrinsic estimation (1) non-photorealistic rendering (1) reference-based stylization (1) ray registration (1) reconstruction-based method (1)

Papers

Neural LightRig: Unlocking Accurate Object Normal and Material Estimation with Multi-Light Diffusion CVPR 2025 Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion ICLR 2025 Ref-NPR: Reference-Based Non-Photorealistic Radiance Fields for Controllable Scene Stylization CVPR 2023 Rethinking Out-of-Distribution (OOD) Detection: Masked Image Modeling Is All You Need CVPR 2023