8 papers
Enhancing In-context Panoramic Generation via Geometric-aware Pretraining
Haoran Feng, Ruiyang Zhang, Longyi Zhang +2
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…
PanoWorld: Real-World Panoramic Generation
Haoyuan Li, Dizhe Zhang, Yuemei Zhou +7
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, whe…
SegviGen: Repurposing 3D Generative Model for Part Segmentation
Lin Li, Haoran Feng, Zehuan Huang +8
We introduce SegviGen, a framework that repurposes native 3D generative models for 3D part segmentation. Existing pipelines either lift strong 2D priors into 3D via distillation or…
Repurposing 3D Generative Model for Autoregressive Layout Generation
Haoran Feng, Yifan Niu, Zehuan Huang +4
We introduce LaviGen, a framework that repurposes 3D generative models for 3D layout generation. Unlike previous methods that infer object layouts from textual descriptions, LaviGe…
DiT360: High-Fidelity Panoramic Image Generation via Hybrid Training
Haoran Feng, Dizhe Zhang, Xiangtai Li +2
In this work, we propose DiT360, a DiT-based framework that performs hybrid training on perspective and panoramic data for panoramic image generation. For the issues of maintaining…
VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space
Lin Li, Zehuan Huang, Haoran Feng +4
3D local editing of specified regions is crucial for game industry and robot interaction. Recent methods typically edit rendered multi-view images and then reconstruct 3D models, b…