用旋转对齐解决单图生成3D角色的视角难题，支持高分辨率可控生成。
Rotate Your Character: Revisiting Video Diffusion Models for High-Quality 3D Character Generation
- 通过姿态归一化将复杂姿态转为标准姿势，保证视角一致。
- 实现1024x1024分辨率的完整视角轨道视频生成。
- 支持最多4张输入图，适合多种实际创作场景。
从单张图像生成高质量3D角色仍是数字内容创作中的重大挑战，尤其在复杂身体姿态和自遮挡情况下。本文提出RCM（Rotate your Character Model），一种专用于高保真新视角合成（NVS）与3D角色生成的图像到视频扩散框架。相比现有基于扩散的方法，RCM具备四大优势：（1）将任意复杂姿态的角色转换为标准姿态，实现完整视域轨道的一致新视角合成；（2）支持1024x1024分辨率的高分辨率轨道视频生成；（3）可根据初始相机位姿控制观察位置；（4）支持最多4张输入图像的多视图条件输入，适应多样用户需求。大量实验表明，RCM在新视角合成与3D生成质量上均优于当前最优方法。
原文摘要 · Abstract (English)
Generating high-quality 3D characters from single images remains a significant challenge in digital content creation, particularly due to complex body poses and self-occlusion. In this paper, we present RCM (Rotate your Character Model), an advanced image-to-video diffusion framework tailored for high-quality novel view synthesis (NVS) and 3D character generation. Compared to existing diffusion-based approaches, RCM offers several key advantages: (1) transferring characters with any complex poses into a canonical pose, enabling consistent novel view synthesis across the entire viewing orbit, (2) high-resolution orbital video generation at 1024x1024 resolution, (3) controllable observation positions given different initial camera poses, and (4) multi-view conditioning supporting up to 4 input images, accommodating diverse user scenarios. Extensive experiments demonstrate that RCM outperforms state-of-the-art methods in both novel view synthesis and 3D generation quality.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。