PrinGS anonymizes faces in Gaussian Splatting scenes without original images, ICVGIP 2026
ponguru · x · 2026-10-30
PrinGS: Privacy Preservation in Gaussian Splatting, a course project by IIIT Hyderabad students accepted at ICVGIP 2026, anonymizes sensitive content (e.g., faces) in trained 3DGS scenes. It localizes sensitive Gaussians via 3D segmentation and applies localized volumetric blurring—without requiring the original training images—preserving scene quality across novel viewpoints. The team also released the PrinGS-Humans dataset, code, and an arXiv paper.
Related event: IIIT Hyderabad's PrinGS Paper Accepted by ICVGIP 2026(2 posts)→
More from Multimodal
- AI-generated Winamp lighter concept goes viral with retro EQ and playlist details — Delahuntagram · 2026-10-30
- Rapid-H3 generates video + audio in ~2 minutes on a single DGX Spark — vchauhan_ · 2026-10-30
- Midjourney Style Code sref 3594718371 Produces Striking Metallic Armor Fashion Portraits — sergeantsref · 2026-10-30
- Native 4K with MoSS Image: RoPE NTK vs Upscale Workflows Put to the Test — No-Sleep-4069 · 2026-10-30
- Open-source openjutsu adds 17 relight presets and two-pass Qwen3-VL scene describing — Devajyoti1231 · 2026-10-30
- SpecSlot Boosts Pixel-Space Image Generation: +2.84 FID on ImageNet-512 at Lower Cost — Jiongfan Yang · 2026-10-30