Differentiable SV-FBP Algorithm Boosts Cone-Beam CT Reconstruction Speed 10x
maier_ak · x · 2026-08-12
Research introduces a differentiable Shift-Variant Filtered Backprojection (SV-FBP) algorithm for cone-beam CT reconstruction. In sparse-view tests, it matches the iterative AIR baseline in MSE, PSNR, and SSIM with 300-400 projections while running about ten times faster. However, below 200 projections, its quality degrades faster than AIR, requiring data-consistency.
Related event: Differentiable SV-FBP Algorithm Accelerates Cone-Beam CT Reconstruction 10x(2 posts)→
More from Research
- Agent Harness Matters: Rust-based Ante Aces 10 Terminal-Bench Tasks — VoidAsuka · 2026-08-12
- Open-Source Project Visualizes and Derives ML Algorithms from First Principles — Roger_M_Taylor · 2026-08-12
- MIT Study: ChatGPT Use Leads to Weaker Brain Neural Connectivity — aakashgupta · 2026-08-12
- Reconstructing Articulated Objects from a Single Rest-State Image — snu · 2026-08-12
- DistilVDR: A 524M Compact Visual Document Retriever Distilled from 8B — nanovdr · 2026-08-12
- AdvFD: Boosting Visual Generation via Adversarial Fréchet Distance Loss — Kwai-Kolors · 2026-08-12