View Matters: Keyframe-Guided Text-Driven 3D Gaussian Editing

Key points

• Text-driven 3D Gaussian editing commonly does not distinguish the editing reliability of rendered views, although different viewpoints provide supervision of substantially different quality.1
• Keyframe Importance Estimation (KIE) identifies reliable views using geometric visibility, semantic distinctiveness, and edit relevance.1
• Keyframe-Guided Editing (KGE) then propagates their editing signals asymmetrically to non-keyframes without noisy reverse influence, while Importance-Aware Optimization (IAO) preserves this reliability preference during 3DGS optimization.1
• Additional adjacent-view analysis indicates that the fidelity-oriented editing process maintains cross-view coherence.1

Sources (1)

• [1]View Matters: Keyframe-Guided Text-Driven 3D Gaussian Editing
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 11:31 AM

  We present View Matters, a view-importance-aware framework that conducts editing around reliable keyframes.

  Text-driven 3D Gaussian editing commonly does not distinguish the editing reliability of rendered views, although different viewpoints provide supervision of substantially different quality.

Extractive summary: sentences quoted from the sources.