JointEdit3D: Feed-Forward 3D Scene Editing in a Unified Latent Space
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
The Flow has not summarised this story yet — read it at arXiv Computer Vision.
arXiv:2610.27049v1 Announce Type: new Abstract: Recent advances in unified visual editing have begun to consolidate image and video editing within a single model, while 3D scene editing remains large...
arXiv:2607.07187v2 Announce Type: replace Abstract: Local editing of 3D objects remains a long-standing challenge. When interacting with 3D content, humans naturally tend to specify a coarse region o...
arXiv:2610.09125v1 Announce Type: new Abstract: Reference-based object compositing inserts or replaces an object using a background image, a reference image, and a 2D compositing mask. These inputs g...
arXiv:2508.01684v2 Announce Type: replace Abstract: While diffusion models have demonstrated remarkable progress in 2D image generation and editing, extending these capabilities to 3D editing remains...
StitchEdit introduces a method to integrate depth priors into diffusion‑based image editors by using per‑layer gradient probing. The approach first activates a pretrained diffusion backbone’s geometric capabilities with a lightweight depth‑denoising adapter, then fine‑tunes this adapter with a probe‑guided learning rate schedule that preserves depth knowledge where helpful and removes it where it conflicts. On the new StitchEditBench, which contains 150 geometry‑dependent edits, StitchEdit outperforms both instruction‑based and depth‑conditioned baselines in perceptual quality and geometric fidelity.
arXiv:2610.35756v1 Announce Type: new Abstract: Recent advancements in text-guided 3D editing, particularly with 3D Gaussian Splatting (3DGS), have shown promise but still lag behind the flexibility...