11 papers
FVAR: Visual Autoregressive Modeling via Next Focus Prediction
Xiaofan Li, Chenming Wu, Yanpeng Sun +6
Visual autoregressive models achieve remarkable generation quality through next-scale predictions across multi-scale token pyramids. However, the conventional method uses uniform s…
FastVGGT: Training-Free Acceleration of Visual Geometry Transformer
You Shen, Zhipeng Zhang, Yansong Qu +4
Foundation models for 3D vision have recently demonstrated remarkable capabilities in 3D perception. However, scaling these models to long-sequence image inputs remains a significa…
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…
Generate Aligned Anomaly: Region-Guided Few-Shot Anomaly Image-Mask Pair Synthesis for Industrial Inspection
Yilin Lu, Jianghang Lin, Linhuang Xie +5
Anomaly inspection plays a vital role in industrial manufacturing, but the scarcity of anomaly samples significantly limits the effectiveness of existing methods in tasks such as l…
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…
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…