Yichen Sheng
9 papers · 2021–2026 · 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 ↓+4 more ↓ Show less ↑
🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🗺️ Taxonomy Completionist (19) 🌉 Interdisciplinary Bridge · Silver 🌱 Topic Pioneer
👥
Mega-Team · Squad
📈
Trend Setter
🔥
Unstoppable · Bronze
🗃️
Keyword Collector
(53)
Top co-authors
Research topics
Computer Vision
(8)
Deep Learning
(6)
Generation
(6)
Models
(4)
Analysis
(3)
Application Areas · Deep Learning
(3)
Processing
(3)
Computer Science
(2)
Machine Learning
(2)
Application Areas · Machine Learning
(2)
Applications
(2)
Architectures
(2)
Core AI · Computer Vision
(2)
Artificial Intelligence
(1)
Core AI · Artificial Intelligence
(1)
Keywords
soft shadow
(2)
image compositing
(2)
neural rendering
(2)
image generation
(1)
3d vision
(1)
text-to-image generation
(1)
depth estimation
(1)
occlusion handling
(1)
diffusion model
(1)
foundation model
(1)
geometry reconstruction
(1)
differentiable rendering
(1)
neural radiance field
(1)
novel view synthesis
(1)
camera control
(1)
spatial reasoning
(1)
3d scene generation
(1)
3d geometry
(1)
diffusion transformer
(1)
text-to-image synthesis
(1)
Papers
I-Scene: 3D Instance Models are Implicit Generalizable Spatial Learners
CVPR 2026
PixelDiT: Pixel Diffusion Transformers for Image Generation
CVPR 2026
Floating No More: Object-Ground Reconstruction from a Single Image
CVPR 2025
Generative Photography: Scene-Consistent Camera Control for Realistic Text-to-Image Synthesis
CVPR 2025
DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision
CVPR 2024
Dr. Bokeh: DiffeRentiable Occlusion-aware Bokeh Rendering
CVPR 2024
PixHt-Lab: Pixel Height Based Light Effect Generation for Image Compositing
CVPR 2023
Controllable Shadow Generation Using Pixel Height Maps
ECCV 2022
SSN: Soft Shadow Network for Image Compositing
CVPR 2021