arXiv:2605.04412v3 Announce Type: replace Abstract: 3D asset generation plays a pivotal role in fields such as gaming and virtual reality, enabling the rapid synthesis of high-fidelity 3D objects fro...
The paper introduces GaussianBlender, a feed‑forward framework that enables instant, high‑fidelity, geometry‑preserving, and multi‑view consistent 3D stylization driven by text. It learns disentangled latent spaces for geometry and appearance using spatially‑grouped 3D Gaussians, and applies a latent diffusion model for text‑conditioned edits. Evaluations demonstrate that GaussianBlender outperforms methods requiring per‑instance optimization, making scalable 3D stylization practical for large‑scale production.
arXiv:2606. 05142v1 Announce Type: cross Abstract: Recent developments in multi-view image editing with generative models have brought us a step closer toward general 3D content generation and customization.
SpaceFlow is a training‑free pipeline that enables locally controllable 3D generation from text and geometric primitives. Each primitive acts as a proxy for an object part and receives a local control level, allowing users to dictate strict adherence to input shapes or permit generative completion in different regions. The method enforces spatial constraints during structure generation and matches appearance to primitives, limiting cross‑part leakage and achieving state‑of‑the‑art prompt faithfulness and material accuracy.
The paper introduces Chat-Edit-3D++ (CE3D++), an interactive 3D and 4D scene editing system that uses a Hash-Atlas network to separate 2D editing from 3D reconstruction. CE3D++ employs a large language model to accept arbitrary textual input, interpret user intent, and autonomously invoke appropriate visual models, enabling multi‑round dialogue and diverse editing effects. The approach is extended to monocular 4D scenes by adding motion constraints and a trajectory dataset, allowing a smaller LLM to schedule up to 30 visual tools accurately.
arXiv:2608.21438v1 Announce Type: new Abstract: Text guided 3D scene editing provides an intuitive interface for modifying reconstructed environments, but remains difficult because natural language d...
The paper introduces Abstraction in Style (AiS), a generative framework that separates structural abstraction from visual stylization. AiS first creates an abstraction proxy that reinterprets a target image’s structure according to the abstraction logic of a given style, then renders this proxy to produce a stylized output. By learning transformations from visual exemplars without explicit geometric supervision, AiS enables a broader range of stylistic transformations, improves controllability, and allows more expressive stylization.
LociArt introduces a unified framework for free‑style local video stylization, allowing precise specification of where to stylize and which style to apply while preserving non‑target content. The core method, GRNStyle, builds on Generative Refinement Networks and uses a polar style‑aware mask to embed style identities as equal‑norm directions within selected regions. An automated pipeline generates paired supervision, leading to the LociArt‑100K dataset and benchmark, which evaluate regional style quality, non‑target preservation, and temporal consistency, and experiments show GRNStyle outperforms existing methods in these aspects.
arXiv:2608.25461v1 Announce Type: cross Abstract: Using conditional image generators, texture artists can explore many single-view looks for an existing 3D shape. Despite impressive progress, state-o...
arXiv:2606.13345v2 Announce Type: replace Abstract: Existing 3D scene editing methods typically rely on per-scene optimization over explicit 3D representations or cascaded edit-and-reconstruct pipeli...
OREO is a framework that improves the visual fidelity of 3D generation models by using on-the-fly rendered and edited 2D views as pseudo-targets. It introduces a dynamic optimization loop where a 2D diffusion model refines rendered views, preserving geometry, viewpoint, and content while enhancing realism. These refined views serve as high‑quality supervision, enabling the 3D generator to learn from its own outputs and progressively improve its visual quality, outperforming pre‑trained baselines.
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...