{"ID":2843378,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.08203","arxiv_id":"2511.08203","title":"Twist and Compute: The Cost of Pose in 3D Generative Diffusion","abstract":"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?","short_abstract":"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 H...","url_abs":"https://arxiv.org/abs/2511.08203","url_pdf":"https://arxiv.org/pdf/2511.08203v1","authors":"[\"Kyle Fogarty\",\"Jack Foster\",\"Boqiao Zhang\",\"Jing Yang\",\"Cengiz Öztireli\"]","published":"2025-11-11T13:08:28Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\",\"Convolutional Neural Network\"]","has_code":false}