发现3D生成模型对视角有强依赖，旋转输入会显著降低效果。
Twist and Compute: The Cost of Pose in 3D Generative Diffusion
- 用2D旋转测试揭示主流3D生成模型存在视角偏见
- 旋转后性能下降，但加轻量CNN可恢复效果
- 提示应设计更对称的模块化架构，而非单纯堆规模
尽管大规模图像到3D生成模型取得了显著成果，但其归纳偏置仍不透明。我们识别出图像条件3D生成模型的一个重要局限：强烈的规范视图偏见。通过使用简单2D旋转的受控实验，我们发现当前最先进的Hunyuan3D 2.0模型在输入旋转时难以泛化，性能明显下降。我们证明，通过添加一个轻量级CNN来检测并校正输入方向，可恢复模型性能，且无需修改生成主干。这一发现提出一个重要开放问题：规模是否足够？还是应追求模块化、对称感知的设计？
原文摘要 · Abstract (English)
Despite their impressive results, large-scale image-to-3D generative models remain opaque in their inductive biases. We identify a significant limitation in image-conditioned 3D generative models: a strong canonical view bias. Through controlled experiments using simple 2D rotations, we show that the state-of-the-art Hunyuan3D 2.0 model can struggle to generalize across viewpoints, with performance degrading under rotated inputs. We show that this failure can be mitigated by a lightweight CNN that detects and corrects input orientation, restoring model performance without modifying the generative backbone. Our findings raise an important open question: Is scale enough, or should we pursue modular, symmetry-aware designs?
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。