Temporal Reconstruction Network for Gradient-Domain Path Tracing

View Full Paper

Ask AI

Bookmark

Share

Key Points

The study aims to improve frame-to-frame consistency in gradient-domain path tracing by utilizing historical frame information.
Developed a temporal reconstruction network incorporating motion vectors for frame mapping.
Implemented a loss function based on temporal information for balancing spatial and temporal quality.
Designed a reweighted module for reasonable inter-frame transfer of reconstruction results.
Achieved 14.28% to 32.56% reduction in RelMSE compared to GradNet.
LPIPS errors improved by up to 50.95%, indicating better detail retention.
Significantly reduced flickering between consecutive frames.

Answers are grounded in this paper and cite their sources.

Demonstrates improved image reconstruction in gradient-domain path tracing, suggesting enhanced visual quality across frames.

No abstract yet. The journal hasn't published one we can show.

No takes yet. Share an insight, caveat, or question.

Ma et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

Share