As information exists in various modalities in real world, effective interaction and fusion
among multimodal information plays a key role for the creation and perception of multimodal …

We present Shap-E, a conditional generative model for 3D assets. Unlike recent work on 3D
generative models which produce a single output representation, Shap-E directly generates …

Abstract 3D editing plays a crucial role in many areas such as gaming and virtual reality.
Traditional 3D editing methods which rely on representations like meshes and point clouds …

Recently impressive results have been achieved in 3D scene editing with text instructions
based on a 2D diffusion model. However current diffusion models primarily generate images …

Neural fields have achieved impressive advancements in view synthesis and scene
reconstruction. However, editing these neural fields remains challenging due to the implicit …

As 3D content becomes increasingly prevalent, there'sa growing focus on the development
of engagements with 3D virtual content. Unfortunately, traditional techniques for creating …

This paper reviews the challenge on Sparse Neural Rendering that was part of the
Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2024. This …

Text-driven 3D scene editing has gained significant attention owing to its convenience and
user-friendliness. However, existing methods still lack accurate control of the specified …

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 …

The advent of 3D Gaussian Splatting (3DGS) has revolutionized 3D editing, offering efficient,
high-fidelity rendering and enabling precise local manipulations. Currently, diffusion-based …