Instant3dit: Multiview Inpainting for Fast Editing of 3D Objects
Amir Barda, Matheus Gadelha, Vladimir G. Kim, Noam Aigerman, Amit H. Bermano, Thibault Groueix
摘要
Original Mesh Input mesh + mask "An elven warrior" Original Mesh 25 sec. "Man wearing a medieval helmet" Mesh Adaptive Remeshing NeRF Mesh Adaptive Remeshing Figure 1. Our method takes as input a 3D object along with a 3D mask (first column) and a text prompt, and uses our multiview inpainting diffusion model to consistently paint the mask in four rendered views of the object. Off-the-shelf reconstructors can be used on the multiview output to give an NeRF, a Gaussian Splat (second column), or a mesh (third column) that can be used along with adaptive remeshing to ensure the unmasked region is exactly preserved e.g. topology, uvs, (fourth and fifth column). This feedforward approach is orders of magnitude faster than previous works in generative 3D editing, taking just ≈ 3 seconds per multiview edit, then 0.7 seconds to reconstruct a GS or a NeRF, 3 seconds for a mesh, and ≈ 20 seconds for optional mesh post-processing.
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 Paper12
- Nano3D: A Training-Free Approach for Efficient 3D Editing Without MasksJunliang Ye, Shenghao Xie, Ruowen Zhao, Zhengyi Wang 等ICLR 2026 · 被引用 32 次
- SpaceControl: Introducing Test-Time Spatial Control to 3D Generative ModelingElisabetta Fedele, Francis Engelmann, Ian Huang, Or Litany 等ICLR 2026 · 被引用 11 次
- AnchorFlow: Training-Free 3D Editing via Latent Anchor-Aligned FlowsZhenglin Zhou, Fan Ma, Chengzhuo Gui, Xiaobo Xia 等CVPR 2026 · 被引用 11 次
- Towards Scalable and Consistent 3D EditingRuihao Xia, Yang Tang, Pan ZhouICML 2026 · 被引用 8 次
- Easy3E: Feed-Forward 3D Asset Editing via Rectified Voxel FlowShimin Hu, Yuanyi Wei, Fei Zha, Yudong Guo 等CVPR 2026 · 被引用 7 次
它引用的顶会 Paper25
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh 等ICML 2021 · 被引用 47,906 次
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu 等ICLR 2022 · 被引用 18,833 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
- BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and GenerationJunnan Li, Dongxu Li, Caiming Xiong, Steven C. H. HoiICML 2022 · 被引用 6,549 次
- SDXL: Improving Latent Diffusion Models for High-Resolution Image SynthesisDustin Podell, Zion English, Kyle Lacey, Andreas Blattmann 等ICLR 2024 · 被引用 4,569 次
相关 Paper
- DreamCatalyst: Fast and High-Quality 3D Editing via Controlling Editability and Identity PreservationJiwook Kim, Seonho Lee, Jaeyo Shin, Jiho Choi 等ICLR 2025
- ATT3D: Amortized Text-to-3D Object SynthesisJonathan Lorraine, Kevin Xie, Xiaohui Zeng, Chen-Hsuan Lin 等ICCV 2023 · 被引用 100 次
- GaussianEditor: Editing 3D Gaussians Delicately with Text InstructionsJunjie Wang, Jiemin Fang, Xiaopeng Zhang, Lingxi Xie 等CVPR 2024 · 被引用 65 次
- EpiDiff: Enhancing Multi-View Synthesis via Localized Epipolar-Constrained DiffusionZehuan Huang, Hao Wen, Junting Dong, Yaohui Wang 等CVPR 2024
- Edit3D: Elevating 3D Scene Editing with Attention-Driven Multi-Turn InteractivityPeng Zhou, Dunbo Cai, Yujian Du, Runqing Zhang 等ACM MM 2024 · 被引用 3 次
