REVIEW 8 cited by
DGE: Direct Gaussian 3D Editing by Consistent Multi-view Editing
Not yet reviewed by Pith; the record is open.
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
read the original abstract
We consider the problem of editing 3D objects and scenes based on open-ended language instructions. A common approach to this problem is to use a 2D image generator or editor to guide the 3D editing process, obviating the need for 3D data. However, this process is often inefficient due to the need for iterative updates of costly 3D representations, such as neural radiance fields, either through individual view edits or score distillation sampling. A major disadvantage of this approach is the slow convergence caused by aggregating inconsistent information across views, as the guidance from 2D models is not multi-view consistent. We thus introduce the Direct Gaussian Editor (DGE), a method that addresses these issues in two stages. First, we modify a given high-quality image editor like InstructPix2Pix to be multi-view consistent. To do so, we propose a training-free approach that integrates cues from the 3D geometry of the underlying scene. Second, given a multi-view consistent edited sequence of images, we directly and efficiently optimize the 3D representation, which is based on 3D Gaussian Splatting. Because it avoids incremental and iterative edits, DGE is significantly more accurate and efficient than existing approaches and offers additional benefits, such as enabling selective editing of parts of the scene.
Forward citations
Cited by 8 Pith papers
-
Hallo4D: Multi-Modal Hallucination Mitigation for Consistent Spatio-Temporal Generation
Hallo4D uses vision-language models to detect and correct spatial and temporal mistakes in AI-generated 3D and 4D content, improving consistency without retraining the base generators.
-
AdaptiveSplat:Texture Aware Controllable 3D Gaussian Allocation for Feed-Forward Reconstruction
Texture-aware SuperCluster pruning plus an adaptive Gaussian head lets feed-forward 3DGS models hit a user budget β while outperforming post-hoc pruners on RE10K, ACID, DL3DV and DTU.
-
Edit in 2D, Verify in 3D: Reinforcement Learning for Multi-view Consistent Scene Editing
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.
-
Articulate3D: Zero-Shot Text-Driven 3D Object Posing
A zero-shot pipeline that reposes 3D meshes by generating text-conditioned target images with rewired multi-view attention and aligning mesh keypoints to them.
-
SplatPainter: Interactive Authoring of 3D Gaussians from 2D Edits via Test-Time Training
A test-time-trained feedforward model that propagates 2D edits onto 3D Gaussian attributes at interactive speeds.
-
Mastering Regional 3DGS: Locating, Initializing, and Editing with Diverse 2D Priors
A 3D Gaussian Splatting editing pipeline that combines 2D diffusion localization, depth-based point seeding, and sequential view refinement to achieve up to 4x faster local edits.
-
AvatarMakeup: Realistic Makeup Transfer for 3D Animatable Head Avatars
A coarse-to-fine pipeline transfers makeup from one reference image to an animatable 3D Gaussian avatar, using UV-map averaging for cross-view consistency and diffusion refinement for detail.
-
Stable Score Distillation
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.
Discussion (0). Continue with ORCID to comment.