In this work, we aim to address the challenge of long-range memory in panoramic world models by exploiting the rotation-equivariant property of omnidirectional representations, where rotation can be treated as an implicit geometric transformation.Building on this insight, we prop…
Canvas360 is a two-stage framework for in-context panoramic generation that combines geometry-aware pretraining with fine-tuning, featuring a large-scale dataset and novel modeling techniques for improved geometric consistency and global coherence.
arXiv cs.CV
TIER_1English(EN)·Haoyuan Li, Dizhe Zhang, Yuemei Zhou, Xiangkai Zhang, Haoran Feng, Xiaofan Lin, Wenjie Jiang, Bo Du, Ming-Hsuan Yang, Lu Qi·
arXiv:2607.09661v1 Announce Type: new Abstract: In this work, we aim to address the challenge of long-range memory in panoramic world models by exploiting the rotation-equivariant property of omnidirectional representations, where rotation can be treated as an implicit geometric …
In this work, we aim to address the challenge of long-range memory in panoramic world models by exploiting the rotation-equivariant property of omnidirectional representations, where rotation can be treated as an implicit geometric transformation.Building on this insight, we prop…
arXiv:2607.08765v1 Announce Type: new Abstract: In this work, we present Canvas360, a two-stage framework for in-context panoramic generation that combines geometry-aware pretraining with downstream task-specific fine-tuning. To address the lack of large-scale, high-quality train…
In this work, we present Canvas360, a two-stage framework for in-context panoramic generation that combines geometry-aware pretraining with downstream task-specific fine-tuning. To address the lack of large-scale, high-quality training data tailored to in-context panoramic tasks,…
