11 papers
CustomTex: High-fidelity Indoor Scene Texturing via Multi-Reference Customization
Weilin Chen, Jiahao Rao, Wenhao Wang +3
The creation of high-fidelity, customizable 3D indoor scene textures remains a significant challenge. While text-driven methods offer flexibility, they lack the precision for fine-…
FlashWorld: High-quality 3D Scene Generation within Seconds
Xinyang Li, Tengfei Wang, Zixiao Gu +3
We propose FlashWorld, a generative model that produces 3D scenes from a single image or text prompt in seconds, 10~100 faster than previous works while possessing superior…
XSpecMesh: Quality-Preserving Auto-Regressive Mesh Generation Acceleration via Multi-Head Speculative Decoding
Dian Chen, Yansong Qu, Xinyang Li +2
Current auto-regressive models can generate high-quality, topologically precise meshes; however, they necessitate thousands-or even tens of thousands-of next-token predictions duri…
DeOcc-1-to-3: 3D De-Occlusion from a Single Image via Self-Supervised Multi-View Diffusion
Yansong Qu, Shaohui Dai, Xinyang Li +4
Reconstructing 3D objects from a single image remains challenging, especially under real-world occlusions. While recent diffusion-based view synthesis models can generate consisten…
Drag Your Gaussian: Effective Drag-Based Editing with Score Distillation for 3D Gaussian Splatting
Yansong Qu, Dian Chen, Xinyang Li +4
Recent advancements in 3D scene editing have been propelled by the rapid development of generative models. Existing methods typically utilize generative models to perform text-guid…
SynergyAmodal: Deocclude Anything with Text Control
Xinyang Li, Chengjie Yi, Jiawei Lai +4
Image deocclusion (or amodal completion) aims to recover the invisible regions (\ie, shape and appearance) of occluded instances in images. Despite recent advances, the scarcity of…