Research map / 3D vision / Gaussian splatting
GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing
Jing Wu, Jia-Wang Bian, Xinghui Li, Guangrun Wang, Ian Reid, Philip Torr, Victor Adrian Prisacariu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use depth-conditioned ControlNet editing with inverted latent codes and attention alignment instead of Instruct-Pix2Pix iterative editing | GaussCtrl · 360-degree and forward-facing scenes | CLIP direction similarity: best in four of six scenes | Mixed |
| use GaussCtrl vs IN2N(GS) for editing time | GaussCtrl · editing time | time: ~13.5min -> ~9min | Improved |
| replace random noise with DDIM-inverted latent codes in ControlNet editing (ablation) | GaussCtrl · Bear statue (qualitative) | style alignment and consistency (visual) | Improved |
| add attention-based latent code alignment on top of inverted latent codes (ablation) | GaussCtrl · Bear statue (qualitative) | artefacts (visual) | Improved |
| use depth-conditioned ControlNet instead of one-time Instruct-Pix2Pix edit (ablation) | GaussCtrl · Bear statue (qualitative) | editing at challenging views (visual) | Improved |
| CLIP direction similarity as a quality metric | evaluation · edit evaluation | CLIP_dir | No clear effect |
| condition editing on depth maps for large geometry changes | GaussCtrl · bear to giraffe | edit success (visual) | Hurt |
Later papers that compared with this method
13 later accepted papers report GaussCtrl as a baseline in their results tables; 12 of them report a better number on most of the results they share with it.
- Let it Snow! Animating 3D Gaussian Scenes with Dynamic Weather Effects via Physics-Guided Score Distillation (CVPR 2026 · better on 6 of 6 shared results)
- Mastering Regional 3DGS: Locating, Initializing, and Editing with Diverse 2D Priors (IJCV 2026 · better on 5 of 5 shared results)
- Edit3r: Instant 3D Scene Editing from Sparse Unposed Images (ECCV 2026 · better on 2 of 4 shared results)
- Edit in 2D, Verify in 3D: Reinforcement Learning for Multi-view Consistent Scene Editing (ECCV 2026 · better on 4 of 4 shared results)
- TINKER: Diffusion's Gift to 3D--Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization (ICLR 2026 · better on 3 of 3 shared results)
- 3D-LATTE: Latent Space 3D Editing from Textual Instructions (CVPR 2026 · better on 2 of 3 shared results)
- Fast Multi-view Consistent 3D Editing with Video Priors (AAAI 2026 · better on 2 of 2 shared results)
- Morpheus: Text-Driven 3D Gaussian Splat Shape and Color Stylization (CVPR 2025 · better on 4 of 4 shared results)
5 more not listed.
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- ViCA-NeRF — ViCA-NeRF: View-Consistency-Aware 3D Editing of Neural Radiance Fields (NeurIPS 2023) · better on 2 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- EditSplat: Multi-View Fusion and Attention-Guided Optimization for View-Consistent 3D Scene Editing with 3D Gaussian Splatting (CVPR 2025 · similarity 0.93)
- SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesis (CVPR 2025 · similarity 0.92)
- GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting (CVPR 2024 · similarity 0.91)
- 3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting (ICLR 2025 · similarity 0.91)
- GaussianEditor: Editing 3D Gaussians Delicately with Text Instructions (CVPR 2024 · similarity 0.90)
- GaussianSpa: An "Optimizing-Sparsifying" Simplification Framework for Compact and High-Quality 3D Gaussian Splatting (CVPR 2025 · similarity 0.90)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
