Interactive3D: Create What You Want by Interactive 3D Generation
Shaocong Dong, Lihe Ding, Zhanpeng Huang, Zibin Wang, Tianfan Xue, Dan Xu
摘要
Stretch to enlarge wings (c) Rigid Drag to swing wings (d) Local Semantic Editing for burning wings I. First Stage: Gaussian Splatting II. Second Stage: InstantNGP (e) Combine to dragon knight (f) Representation Converter (g) Interactive Hash Refinement "A Draven Knight" "A red fire dragon" Figure 1 . Interactive 3D Generation. The first stage involves using Gaussian ellipsoids for creating a base model where users can interact through different operations, such as deformable dragging to add features like wings, stretching to enlarge parts, rigid dragging to reposition elements, and local semantic editing to apply specific visual effects, e.g., making wings appear aflame. The second stage shows the conversion of this proposed Gaussian representation into an InstantNGP structure followed by an Interactive Hash Refinement process, allowing for further detailed enhancements. It demonstrates the framework's capability to merge and refine complex generations.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper11
- FullPart: Generating each 3D Part at Full ResolutionLihe Ding, Shaocong Dong, Yaokun Li, Chenjian Gao 等ICLR 2026 · 被引用 17 次
- TINKER: Diffusion's Gift to 3D--Multi-View Consistent Editing From Sparse Inputs without Per-Scene OptimizationCanyu Zhao, Xiaoman Li, Tianjian Feng, Zhiyue Zhao 等ICLR 2026 · 被引用 9 次
- Towards Scalable and Consistent 3D EditingRuihao Xia, Yang Tang, Pan ZhouICML 2026 · 被引用 8 次
- ScanEdit: Hierarchically-Guided Functional 3D Scan EditingMohamed El Amine Boudjoghra, Ivan Laptev, Angela DaiICCV 2025 · 被引用 6 次
- From One to More: Contextual Part Latents for 3D GenerationShaocong Dong, Lihe Ding, Xiao Chen, Yaokun Li 等ICCV 2025 · 被引用 4 次
它引用的顶会 Paper23
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 被引用 35,902 次
- Segment AnythingAlexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao 等ICCV 2023 · 被引用 13,211 次
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser 等CVPR 2022 · 被引用 13,123 次
- Photorealistic Text-to-Image Diffusion Models with Deep Language UnderstandingChitwan Saharia, William Chan, Saurabh Saxena, Lala Li 等NeurIPS 2022 · 被引用 8,965 次
- Adding Conditional Control to Text-to-Image Diffusion ModelsLvmin Zhang, Anyi Rao, Maneesh AgrawalaICCV 2023 · 被引用 6,759 次
相关 Paper
- ObjectMorpher: 3D-Aware Image Editing via Deformable 3DGSYuhuan Xie, Aoxuan Pan, Yihua Huang, Chirui Chang 等CVPR 2026
- Drag Your Gaussian: Effective Drag-Based Editing with Score Distillation for 3D Gaussian SplattingYansong Qu, Dian Chen, Xinyang Li, Xiaofan Li 等SIGGRAPH 2025 · 被引用 14 次
- Hash3D: Training-free Acceleration for 3D GenerationXingyi Yang, Songhua Liu, Xinchao WangCVPR 2025
- 3DGS-Drag: Dragging Gaussians for Intuitive Point-Based 3D EditingJiahua Dong, Yu-Xiong WangICLR 2025
- Deformable Radial Kernel SplattingYi-Hua Huang, Ming-Xian Lin, Yang-Tian Sun, Ziyi Yang 等CVPR 2025
