Yiwei Hu

Yiwei Hu

Senior Research Scientist

Adobe Research

Biography

I am a Senior Research Scientist at Adobe Research. I received my Ph.D. from Yale University, advised by Prof. Holly Rushmeier and Prof. Julie Dorsey. Prior to Yale, I received my bachelor’s degree from Zhejiang University, where I was advised by Prof. Rui Wang.

My research focuses on 2D and 3D graphics, with a particular interest in generative AI for spatial content creation. At Adobe, we bring research prototypes into real-world creative workflows, with technologies shipped in Adobe Substance 3D, Firefly Services, Firefly Boards, and Project Aqua. Our work spans generative 3D asset creation, image composition, and spatial content workflows. Most recently, our research combining generative 3D AI with image editing led to Photoshop’s Rotate Object, enabling precise 3D-aware control of objects in 2D images. Our generative models have also been deployed in enterprise workflows, including Adobe’s collaboration with Disney Imagineering.

I am currently exploring generative world models and agentic workflows for visual content creation. I am open to collaborations and welcome strong Ph.D. students interested in research internships at Adobe Research.

Interests
  • Computer Graphics
  • Spatial Generation
Education
  • PhD in Computer Graphics, 2023

    Yale University

  • BSc in Computer Science, 2018

    Zhejiang University

Publications

(2026). OmniRoam: World Wandering via Long-Horizon Panoramic Video Generation. SIGGRAPH 2026.

PDF Project

(2026). Neural Representation and Latent Space Synthesis of Bidirectional Texture Functions. EGSR 2026.

PDF Project

(2026). tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction. CVPR 2026.

PDF Project

(2026). V-RGBX: Video Editing with Accurate Controls over Intrinsic Properties. CVPR 2026.

PDF Project

(2026). HiMat: DiT-based Ultra-High Resolution SVBRDF Generation. Computer Graphics Forum, Proc. of Eurographics (EG 2026).

PDF

(2026). RealMat: Realistic Materials with Diffusion and Reinforcement Learning. Computer Graphics Forum 2026.

Project

(2025). OmniVCus: Feedforward Subject-driven Video Customization with Multimodal Control Conditions. NeurIPS 2025.

Project

(2025). AniTex: light-geometry consistent PBR Material Generation for Animatable Objects. SIGGRAPH ASIA 2025.

PDF

(2025). Generating 360 Video is What You Need For a 3D Scene. SIGGRAPH ASIA 2025.

Project

(2025). MaterialPicker: Multi-Modal DiT-Based Material Generation. ACM Transactions on Graphics (SIGGRAPH 2025).

Project

(2025). Buffer Anytime: Zero-Shot Video Depth and Normal from Image Priors. CVPR 2025.

PDF Project

(2025). Turbo3D: Ultra-fast Text-to-3D Generation. CVPR 2025.

PDF Project

(2025). RelitLRM: Generative Relightable Radiance for Large Reconstruction Models. ICLR 2025.

PDF Project

(2024). Procedural Material Generation with Reinforcement Learning. ACM Transactions on Graphics (SIGGRAPH ASIA 2024).

PDF Code DOI

(2024). RGB↔X: Image Decomposition and Synthesis Using Material- and Lighting-aware Diffusion Models. SIGGRAPH 2024.

PDF Project

(2024). TexSliders: Diffusion-Based Texture Editing in CLIP Space. SIGGRAPH 2024.

PDF Cite Project

(2023). Generating Procedural Materials from Text or Image Prompts. SIGGRAPH 2023.

PDF Cite Project DOI

(2022). Multirate Shading with Piecewise Interpolatory Approximation. Computer Graphics Forum, Proc. of Pacific Graphics (PG 2022).

PDF Cite Project DOI

(2022). Node Graph Optimization Using Differentiable Proxies. SIGGRAPH 2022.

PDF Cite Project DOI

(2022). Controlling Material Appearance by Examples. Computer Graphics Forum, Proc. of Eurographics Symposium on Rendering (EGSR 2022).

PDF Cite Project DOI

(2022). An Inverse Procedural Modeling Pipeline for SVBRDF Maps. ACM Transactions on Graphics (Presented at SIGGRAPH 2022).

PDF Cite Project DOI

(2019). A Novel Framework for Inverse Procedural Texture Modeling. ACM Transactions on Graphics (SIGGRAPH ASIA 2019).

PDF Cite Project DOI

(2019). Novel Radiomic Features Based on Graph Theory for PET Image Analysis. IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019).

PDF Cite DOI