LAPIG: Language Guided Projector Image Generation with Surface Adaptation and
Stylization

IEEE VR 2025 / IEEE TVCG

1Southwest University        2Stony Brook University
*Indicates the corresponding author

Abstract

We propose LAPIG, a language guided projector image generation method with surface adaptation and stylization. LAPIG consists of a projector-camera system and a target textured projection surface. LAPIG takes the user text prompt as input and aims to transform the surface style using the projector. LAPIG's key challenge is that due to the projector's physical brightness limitation and the surface texture, the viewer's perceived projection may suffer from color saturation and artifacts in both dark and bright regions, such that even with the state-of-the-art projector compensation techniques, the viewer may see clear surface texture-related artifacts. Therefore, how to generate a projector image that follows the user's instruction while also displaying minimum surface artifacts is an open problem. To address this issue, we propose projection surface adaptation (PSA) that can generate compensable surface stylization. We first train two networks to simulate the projector compensation and project-and-capture processes, this allows us to find a satisfactory projector image without real project-and-capture and utilize gradient descent for fast convergence. Then, we design content and saturation losses to guide the projector image generation, such that the generated image shows no clearly perceivable artifacts when projected. Finally, the generated image is projected for visually pleasing surface style morphing effects.

See below for PSA results.

Projection Surface Adaptation (PSA)

The following examples are from our paper. Try to move over to the images ⤸ and observe them.

 

User input text prompt:  "reimagine with the delicate brushstrokes of John Singer Sargent" 

Surface
StylizedWithPSA
withPSA
StylizedWithoutPSA
withoutPSA

Surface

Stylized Surface

(w/ 

Real Captured Projection

PSA)

Stylized Surface

(w/o

Real Captured Projection

PSA)

User input text prompt:  "convert into the expressive, gestural strokes of Abstract Expressionism" 

Surface
StylizedWithPSA
withPSA
StylizedWithoutPSA
withoutPSA

Surface

Stylized Surface

(w/ 

Real Captured Projection

PSA)

Stylized Surface

(w/o

Real Captured Projection

PSA)

User input text prompt:  "paint with the dark, emotional intensity of Edvard Munch" 

Surface
StylizedWithPSA
withPSA
StylizedWithoutPSA
withoutPSA

Surface

Stylized Surface

(w/ 

Real Captured Projection

PSA)

Stylized Surface

(w/o

Real Captured Projection

PSA)

User input text prompt:  "paint with the dark, emotional intensity of Edvard Munch" 

Surface
StylizedWithPSA
withPSA
StylizedWithoutPSA
withoutPSA

Surface

Stylized Surface

(w/ 

Real Captured Projection

PSA)

Stylized Surface

(w/o

Real Captured Projection

PSA)

Visualization of Our Work

Text prompt:  "make it night city" 

Text prompt:  "make it California style" 

surface1
surface1

Text prompt:  "make it night city" 

Text prompt:  "make it Van Goph style" 

surface1
surface2

BibTeX

@ARTICLE{Deng2025LAPIG,
  author  = {Deng, Yuchen and Ling, Haibin and Huang, Bingyao},
  journal = {IEEE Transactions on Visualization and Computer Graphics},
  title   = {LAPIG: Language Guided Projector Image Generation with Surface Adaptation and Stylization},
  year    = {2025},
}