paper-with-me

3D Object Editing

1개 벤치마크 · 논문 12편 · 이 태스크의 논문 보기 →

Benchmarks

LLFF

결과 1개

Most implemented

Papers

EditVerse3D: High-Quality 3D Object Editing with Region-Aware Learning

2026-07-08 · Youtan Yin, Yanning Zhou, Jiacheng Wei, Xiaofeng Yang 외 arxiv

Local editing of 3D objects remains a long-standing challenge. When interacting with 3D content, humans naturally tend to specify a coarse region of interest for modification rather than defining precise editing boundari…

3D Object Editing

SVGS: Single-View to 3D Object Editing via Gaussian Splatting

2026-03-30 · Pengcheng Xue, Yan Tian, Qiutao Song, Ziyi Wang 외 arxiv

Text-driven 3D scene editing has attracted considerable interest due to its convenience and user-friendliness. However, methods that rely on implicit 3D representations, such as Neural Radiance Fields (NeRF), while effec…

3D Object Editing3D scene Editing

Muses: Designing, Composing, Generating Nonexistent Fantasy 3D Creatures without Training

2026-01-06 · Hexiao Lu, Xiaokun Sun, Zeyu Cai, Hao Guo 외 arxiv

We present Muses, the first training-free method for fantastic 3D creature generation in a feed-forward paradigm. Previous methods, which rely on part-aware optimization, manual assembly, or 2D image generation, often pr…

3D Object EditingImage Generation

NANO3D: A Training-Free Approach for Efficient 3D Editing Without Masks

2025-10-16 · Junliang Ye, Shenghao Xie, Ruowen Zhao, Zhengyi Wang 외 arxiv

3D object editing is essential for interactive content creation in gaming, animation, and robotics, yet current approaches remain inefficient, inconsistent, and often fail to preserve unedited regions. Most methods rely …

3D Object Editing

Manipulating Vehicle 3D Shapes through Latent Space Editing

2024-10-31 · JiangDong Miao, Tatsuya Ikeda, Bisser Raytchev, Ryota Mizoguchi 외

Although 3D object editing has the potential to significantly influence various industries, recent research in 3D generation and editing has primarily focused on converting text and images into 3D models, often overlooki…

3D Generation3D Object EditingAttribute

SIn-NeRF2NeRF: Editing 3D Scenes with Instructions through Segmentation and Inpainting

2024-08-23 · Jiseung Hong, Changmin Lee, Gyusang Yu

TL;DR Perform 3D object editing selectively by disentangling it from the background scene. Instruct-NeRF2NeRF (in2n) is a promising method that enables editing of 3D scenes composed of Neural Radiance Field (NeRF) using …

3D Object EditingNeRFObjectSemantic Segmentation

전체 12편 보기 →