MMJun 16

DiffPC: Diffusion-Based Projector Photometric Compensation

arXiv:2606.175216.7
Predicted impact top 66% in MM · last 90 daysOriginality Incremental advance
AI Analysis

This work addresses the practical problem of photometric compensation for projectors in unknown environments, offering a method that requires no scene-specific data collection.

DiffPC reformulates projector photometric compensation as a denoising task using a diffusion model, achieving superior visual performance in unknown scenarios compared to prior methods.

Projector photometric compensation corrects color distortions introduced by surface texture, reflection, and ambient lighting. Existing deep learning-based methods usually require professional scene-specific data collection and lack consideration for perceptual quality. To address this limitation, we present a diffusion-based photometric compensation method that reconstructs compensation images under photometric and content-aware guidance. Specifically, we first model the photometric distortions introduced during projection as environment-dependent additive noise, thereby reformulating the photometric compensation problem as a denoising task with physical constraints. Next, we introduce a diffusion model, which generates compensation images by following an additive trajectory to iteratively remove the noise. Finally, to accurately estimate the noise at each timestep, by analyzing the factors that contribute to distortions in the physical process of projection and capturing, we design a noise estimation network that incorporates features of both photometry-aware and content conditions. Experiments show that our method achieves superior visual performance in unknown scenarios, thereby exhibiting significant practical advantages over prior methods.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes