Pith. sign in

REVIEW 5 cited by

GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2403.08733 v4 pith:GC4B7DKY submitted 2024-03-13 cs.CV

Jing Wu , Jia-Wang Bian , Xinghui Li , Guangrun Wang , Ian Reid , Philip Torr , Victor Adrian Prisacariu This is my paper
classification cs.CV
keywords editingimagesconsistentmethodmodelmulti-viewfastergaussctrl
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We propose GaussCtrl, a text-driven method to edit a 3D scene reconstructed by the 3D Gaussian Splatting (3DGS). Our method first renders a collection of images by using the 3DGS and edits them by using a pre-trained 2D diffusion model (ControlNet) based on the input prompt, which is then used to optimise the 3D model. Our key contribution is multi-view consistent editing, which enables editing all images together instead of iteratively editing one image while updating the 3D model as in previous works. It leads to faster editing as well as higher visual quality. This is achieved by the two terms: (a) depth-conditioned editing that enforces geometric consistency across multi-view images by leveraging naturally consistent depth maps. (b) attention-based latent code alignment that unifies the appearance of edited images by conditioning their editing to several reference views through self and cross-view attention between images' latent representations. Experiments demonstrate that our method achieves faster editing and better visual results than previous state-of-the-art methods.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. SceneExpander: Text-Guided 3D Scene Expansion via Free-Form View Insertion

    cs.CV 2026-03 conditional novelty 6.0 of 10

    A test-time adaptation method integrates a 3D-misaligned, AI-generated inserted view into a reconstructed 3D scene, preserving the captured region while extending it.

  2. Edit in 2D, Verify in 3D: Reinforcement Learning for Multi-view Consistent Scene Editing

    cs.CV 2026-03 conditional novelty 6.0 of 10

    RL3DEdit fine-tunes FLUX-Kontext with GRPO using VGGT confidence and pose rewards to produce multi-view consistent 3D scene edits in a single pass.

  3. Efficient multi-view training for 3D Gaussian Splatting

    cs.CV 2025-06 conditional novelty 6.0 of 10

    Training 3D Gaussian Splatting with multiple images per iteration, using partial rendering and a 3D-aware SSIM loss, improves novel-view synthesis quality over single-view training.

  4. DrivingGaussian++: Towards Realistic Reconstruction and Editable Simulation for Surrounding Dynamic Driving Scenes

    cs.CV 2025-08 conditional novelty 4.0 of 10

    DrivingGaussian++ reconstructs dynamic surround-view driving scenes and performs training-free multi-task editing (weather, texture, object manipulation) using Gaussians, diffusion models, and LLM-generated trajectories.

  5. Stable Score Distillation

    cs.CV 2025-07 conditional novelty 4.0 of 10

    SSD is a diffusion score-distillation loss for text-guided 2D and 3D editing that combines a CFG cross-prompt term, a null-text cross-trajectory regularizer, and a prompt-enhancement term to stabilize edits.

Pith tools