24 papers
GenSplatCodec: Feed-Forward Gaussian Splatting Compression via One-Step Diffusion
Qiang Hu, Zhenlong Wu, Lei Huang +3
Feed-forward 3D Gaussian Splatting (3DGS) enables scalable scene reconstruction without per-scene optimization, yet produces dense Gaussians that are costly to store and transmit.…
DTI: Dynamic Trajectory Initialization for Generative Face Video Super-Resolution
Yingwei Tang, Chen Yan, Wendi Liu +2
As the most perceptually powerful Face Video Super-Resolution (FVSR) method, existing works in Generative FVSR (GFVSR) mainly exploit the generative prior of pretrained diffusion m…
TEASR: Training-Efficient Any-Step Diffusion Transformer for Real-World Image Super-Resolution
Xiang Gao, Chenxin Zhu, Yushun Fang +2
Diffusion models excel in Real-World Image Super-Resolution (Real-ISR) due to their powerful generative priors but suffer from slow iterative sampling. Although existing one-step d…
LL-Bench: Rethinking Low-Level Vision Evaluation in the Era of Large-Scale Generative Models
Lu Liu, Huiyu Duan, Chenxin Zhu +6
Large-scale generative models have demonstrated remarkable capabilities across image generation and editing tasks. However, their performance in low-level vision tasks, which requi…
COLLAR: Cascaded Object-Level Latent Refinement for High-Fidelity Conditional Generation
Xinlong Zhang, Jia Wei, Xiaoyu Zhang +3
Achieving high-fidelity object-level control in Diffusion Transformers remains a significant challenge despite the introduction of structural priors like depth and Canny maps. Curr…
GeoRect4D: Geometry-Compatible Generative Rectification for Dynamic Sparse-View 3D Reconstruction
Zhenlong Wu, Zihan Zheng, Xuanxuan Wang +7
Reconstructing dynamic 3D scenes from sparse multi-view videos is highly ill-posed, often leading to geometric collapse, trajectory drift, and floating artifacts. Recent attempts i…