NeuMesh++: Towards Versatile and Efficient Volumetric Editing with Disentangled Neural Mesh-based Implicit Field
2026-06-17 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors created a new way to represent 3D scenes by combining detailed shapes, colors, and meanings onto mesh points, which lets users easily edit the 3D models in many ways. They improved how these scenes are drawn and made editing textures more accurate using several new techniques. Their method works better and allows more types of edits than previous approaches, as shown by tests on real and simulated data. This makes changing 3D objects more flexible and easier.
neural implicit renderingneural radiance fieldmesh representationgeometry editingtexture editingsemantic editinglocal space parameterization3D scene reconstructionnovel view synthesis
Authors
Chong Bao, Yuan Li, Bangbang Yang, Yujun Shen, Hujun Bao, Zhaopeng Cui, Yinda Zhang, Guofeng Zhang
Abstract
Recently neural implicit rendering techniques have evolved rapidly and demonstrated significant advantages in novel view synthesis and 3D scene reconstruction. However, existing neural rendering methods for editing purposes offer limited functionalities, e.g., rigid transformation and category-specific editing. In this paper, we present a novel mesh-based representation by encoding the neural radiance field with disentangled geometry, texture, and semantic codes on mesh vertices, which empowers a set of efficient and comprehensive editing functionalities, including mesh-guided geometry editing, designated texture editing with texture swapping, filling and painting operations, and semantic-guided editing. To this end, we develop several techniques including a novel local space parameterization to enhance rendering quality and training stability, a learnable modification color on vertex to improve the fidelity of texture editing, a spatial-aware optimization strategy to realize precise texture editing, and a semantic-aided region selection to ease the laborious annotation of implicit field editing. Extensive experiments and editing examples on both real and synthetic datasets demonstrate the superiority of our method on representation quality and editing ability. Project page: https://zju3dv.github.io/neumeshplusplus/