ViSculpt: Visual-Centric Agentic Geometry Editing

• URL: http://arxiv.org/abs/2608.24169v1
• Date: Tue, 25 Aug 2026 07:37:34 GMT
• Title: ViSculpt: Visual-Centric Agentic Geometry Editing
• Abstract summary: Large language models (LLMs) have shown promise for script-based 3D creation, but script generation is less suited to perception-driven editing of arbitrary existing meshes.<n>We present a emphvisual-centric, training-free multi-agent system that edits existing 3D meshes directly in Blender by emulating the iterative workflow of human artists.
• Score: 21.128169435798704
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 3D geometry editing is a critical yet labor-intensive part of the graphics pipeline, requiring artists to translate creative intent into precise operations in complex professional software. Large language models (LLMs) have shown promise for script-based 3D creation, but script generation is less suited to perception-driven editing of arbitrary existing meshes, where execution must remain visually grounded and untouched regions should be preserved. We present a \emph{visual-centric}, training-free multi-agent system that edits existing 3D meshes directly in Blender by emulating the iterative workflow of human artists. Rather than generating scripts or regenerating geometry, our system operates through the Blender GUI: multimodal LLM agents observe the viewport, reason about the current mesh state, and execute localized edits through simulated user interactions. Experiments on a curated benchmark provide initial evidence that this agentic approach can follow natural language instructions, perform representative localized mesh edits, and preserve the overall identity of the input asset. Our results highlight a complementary regime for language-driven 3D editing: direct in-place modification of existing meshes within the native 3D editing workflow. We view this work as an exploratory step toward visual-centric agentic geometry editing in professional graphics software.

Related papers

• Chat-Edit-3D++: Interactive 3D and 4D Scene Editing via Large Language Models [57.59888019135289]
  Hash-Atlas network reformulates 3D scene editing as operations on 2D atlas images.<n>We introduce a dialogue-based 3D scene editing approach, termed CE3D++.<n>Results demonstrate that CE3D++ effectively integrates multiple visual models to achieve diverse visual editing effects.
  arXiv  Detail & Related papers  (2026-08-29T08:25:58Z)
• Procedura: Agentic 3D Modeling with Procedural Control [52.232812096564906]
  Procedura is a novel 3D modeling agent framework that writes an object as a procedural assembly.<n>From a text prompt, the agent plans the object as an assembly graph and writes the program part by part.<n>A decoupled vision critic then refines the assembly one diagnosed fix at a time.
  arXiv  Detail & Related papers  (2026-08-26T17:54:39Z)
• DesignAgent3D: Interactive 3D Scene Editing via Designer-like Multimodal Reasoning [32.91291969659809]
  Text guided 3D scene editing provides an intuitive interface for modifying reconstructed environments.<n>Existing methods typically formulate the task as one-shot conditional generation from a single prompt.<n>We present DesignAgent3D, an interactive multimodal agentic framework that reformulates 3D scene editing as a designer-like Plan-Perceive-Act paradigm.
  arXiv  Detail & Related papers  (2026-08-18T01:16:13Z)
• ES3D: Embedding Semantics into 3D Space for Component-Aware Editing [31.12252706485155]
  ES3D is a framework that embeds semantics directly into 3D space.<n>It retrieves editable regions based on semantic cues and uses multiple images as conditions.<n> ES3D produces geometrically consistent and semantically coherent edits.
  arXiv  Detail & Related papers  (2026-08-16T13:58:08Z)
• SimWorlds: A Multi-Agent System for Dynamic 3D Scene Creation [50.175987640001644]
  We present SimWorlds: a multi-agent framework that produces dynamic, editable 4D scenes from text.<n>We also introduce 4DBuildBench, a benchmark for assessing both visual fidelity and physical consistency of the procedural dynamic 3D scenes.
  arXiv  Detail & Related papers  (2026-07-02T06:29:18Z)
• Vinedresser3D: Agentic Text-guided 3D Editing [26.81659566314386]
  Vinedresser3D is an agentic framework for high-quality text-guided 3D editing.<n>It operates directly in the latent space of a native 3D generative model.<n>Experiments on diverse 3D edits demonstrate that Vinedresser3D outperforms prior baselines in both automatic metrics and human preference studies.
  arXiv  Detail & Related papers  (2026-02-23T06:30:36Z)
• LangDriveCTRL: Natural Language Controllable Driving Scene Editing with Multi-modal Agents [61.91651123290512]
  LangDriveCTRL is a framework for editing real-world driving videos to synthesize diverse traffic scenarios.<n>It supports both object node editing (removal, insertion and replacement) and multi-object behavior editing from a single natural-language instruction.
  arXiv  Detail & Related papers  (2025-12-19T10:57:03Z)
• LL3M: Large Language 3D Modelers [18.23329430829059]
  We present LL3M, a system that generates 3D assets by writing interpretable Python code in Blender.<n>We reformulate shape generation as a code-writing task, enabling greater modularity, editability, and integration with artist Blender.<n>Our experiments showcase the power of code as a generative and interpretable medium for 3D asset creation.
  arXiv  Detail & Related papers  (2025-08-11T17:48:02Z)
• EditRoom: LLM-parameterized Graph Diffusion for Composable 3D Room Layout Editing [114.14164860467227]
  We propose EditRoom, a framework capable of executing a variety of layout edits through natural language commands.<n>Specifically, EditRoom leverages Large Language Models (LLMs) for command planning and generates target scenes.<n>We have developed an automatic pipeline to augment existing 3D scene datasets and introduced EditRoom-DB, a large-scale dataset with 83k editing pairs.
  arXiv  Detail & Related papers  (2024-10-03T17:42:24Z)
• Chat-Edit-3D: Interactive 3D Scene Editing via Text Prompts [76.73043724587679]
  We propose a dialogue-based 3D scene editing approach, termed CE3D. Hash-Atlas represents 3D scene views, which transfers the editing of 3D scenes onto 2D atlas images. Results demonstrate that CE3D effectively integrates multiple visual models to achieve diverse editing visual effects.
  arXiv  Detail & Related papers  (2024-07-09T13:24:42Z)
• 3D-GPT: Procedural 3D Modeling with Large Language Models [47.72968643115063]
  We introduce 3D-GPT, a framework utilizing large language models(LLMs) for instruction-driven 3D modeling. 3D-GPT positions LLMs as proficient problem solvers, dissecting the procedural 3D modeling tasks into accessible segments and appointing the apt agent for each task. Our empirical investigations confirm that 3D-GPT not only interprets and executes instructions, delivering reliable results but also collaborates effectively with human designers.
  arXiv  Detail & Related papers  (2023-10-19T17:41:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.