6 papers · 1 filter
A Frozen Pixel-Space Diffusion Model Can Guide Itself with Its Own Samples
Zixuan Fu, Chong Wang, Lanqing Guo +3
Pixel-space diffusion models aim to learn an end-to-end generator directly over raw pixels. This is challenging because a single model must capture both global structure and local…
RF4D:Neural Radar Fields for Novel View Synthesis in Outdoor Dynamic Scenes
Jiarui Zhang, Zhihao Li, Chong Wang +1
Neural fields (NFs) have achieved remarkable success in scene reconstruction and novel view synthesis. However, existing NF approaches that rely on RGB or LiDAR inputs often strugg…
Improving Flexible Image Tokenizers for Autoregressive Image Generation
Zixuan Fu, Lanqing Guo, Chong Wang +3
Flexible image tokenizers aim to represent an image using an ordered 1D variable-length token sequence. This flexible tokenization is typically achieved through nested dropout, whe…
Reconciling Stochastic and Deterministic Strategies for Zero-shot Image Restoration using Diffusion Model in Dual
Chong Wang, Lanqing Guo, Zixuan Fu +4
Plug-and-play (PnP) methods offer an iterative strategy for solving image restoration (IR) problems in a zero-shot manner, using a learned \textit{discriminative denoiser} as the i…
Single-Image Shadow Removal Using Deep Learning: A Comprehensive Survey
Laniqng Guo, Chong Wang, Yufei Wang +5
Shadow removal aims at restoring the image content within shadow regions, pursuing a uniform distribution of illumination that is consistent between shadow and non-shadow regions.…
Temporal As a Plugin: Unsupervised Video Denoising with Pre-Trained Image Denoisers
Zixuan Fu, Lanqing Guo, Chong Wang +3
Recent advancements in deep learning have shown impressive results in image and video denoising, leveraging extensive pairs of noisy and noise-free data for supervision. However, t…