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

cs.CV, cs.GR

Submitted: 2026-10-06

Updated: 2026-10-06

Comments: 14 pages, 11 figures, including appendices

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• 3D-Consistent Multi-View Editing by Correspondence Guidance
• Progressive3D: Progressively Local Editing for Text-to-3D Content Creation with Complex Semantic Prompts
• Guiding Instruction-based Image Editing via Multimodal Large Language Models
• Prompt-to-Prompt Image Editing with Cross Attention Control
• Instruct 3D-to-3D: Text Instruction Guided 3D-to-3D conversion
• DreamFusion: Text-to-3D using 2D Diffusion
• C3Editor: Achieving Controllable Consistency in 2D Model for 3D Editing

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models