94 citations · 186 across the 24 of their papers we have counts for
26 papers
ParaLin++: Accelerating Parallel Diffusion Integrator via Intrinsic Partially Linear Structure
Jianrong Lu, Zhiyu Zhu, Hui Liu +1
Training-free few-step samplers are often described as nearly quality-lossless under conventional FID/CLIP-style evaluation. It remains unclear whether that conclusion transfers to…
Diffusion Image Generation with Explicit Modeling of Data Manifold Geometry
Duoduo Xue, Zhiyu Zhu, Junhui Hou
Image generative models aim to sample data points from the underlying data manifold, a task that requires learning and decoding a dense, low-dimensional, and compact parameterizati…
Scaling Dense Event-Stream Pretraining from Visual Foundation Models
Zhiwen Chen, Junhui Hou, Zhiyu Zhu +2
Learning versatile, fine-grained representations from irregular event streams is pivotal yet nontrivial, primarily due to the heavy annotation that hinders scalability in dataset s…
Optimizing Multi-Modality Trackers via Significance-Regularized Tuning
Zhiwen Chen, Jinjian Wu, Zhiyu Zhu +3
This paper tackles the critical challenge of optimizing multi-modality trackers by effectively adapting pre-trained models for RGB data. Existing fine-tuning paradigms oscillate be…
Acc3D: Accelerating Single Image to 3D Diffusion Models via Edge Consistency Guided Score Distillation
Kendong Liu, Zhiyu Zhu, Hui Liu +1
We present Acc3D to tackle the challenge of accelerating the diffusion process to generate 3D models from single images. To derive high-quality reconstructions through few-step inf…
ResFlow: Fine-tuning Residual Optical Flow for Event-based High Temporal Resolution Motion Estimation
Qianang Zhou, Zhiyu Zhu, Junhui Hou +3
Event cameras hold significant promise for high-temporal-resolution (HTR) motion estimation. However, estimating event-based HTR optical flow faces two key challenges: the absence…
PrefPaint: Aligning Image Inpainting Diffusion Model with Human Preference
Kendong Liu, Zhiyu Zhu, Chuanhao Li +3
In this paper, we make the first attempt to align diffusion models for image inpainting with human aesthetic standards via a reinforcement learning framework, significantly improvi…
E-Motion: Future Motion Simulation via Event Sequence Diffusion
Song Wu, Zhiyu Zhu, Junhui Hou +2
Forecasting a typical object's future motion is a critical task for interpreting and interacting with dynamic environments in computer vision. Event-based sensors, which could capt…
Learning Efficient and Effective Trajectories for Differential Equation-based Image Restoration
Zhiyu Zhu, Jinhui Hou, Hui Liu +2
The differential equation-based image restoration approach aims to establish learnable trajectories connecting high-quality images to a tractable distribution, e.g., low-quality im…
NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizer
Meng You, Zhiyu Zhu, Hui Liu +1
By harnessing the potent generative capabilities of pre-trained large video diffusion models, we propose NVS-Solver, a new novel view synthesis (NVS) paradigm that operates \textit…
Modeling State Shifting via Local-Global Distillation for Event-Frame Gaze Tracking
Jiading Li, Zhiyu Zhu, Jinhui Hou +2
This paper tackles the problem of passive gaze estimation using both event and frame data. Considering the inherently different physiological structures, it is intractable to accur…
Segment Any Events via Weighted Adaptation of Pivotal Tokens
Zhiwen Chen, Zhiyu Zhu, Yifan Zhang +3
In this paper, we delve into the nuanced challenge of tailoring the Segment Anything Models (SAMs) for integration with event data, with the overarching objective of attaining robu…
Global Structure-Aware Diffusion Process for Low-Light Image Enhancement
Jinhui Hou, Zhiyu Zhu, Junhui Hou +3
This paper studies a diffusion-based framework to address the low-light image enhancement problem. To harness the capabilities of diffusion models, we delve into this intricate pro…
Cross-modal Orthogonal High-rank Augmentation for RGB-Event Transformer-trackers
Zhiyu Zhu, Junhui Hou, Dapeng Oliver Wu
This paper addresses the problem of cross-modal object tracking from RGB videos and event data. Rather than constructing a complex cross-modal fusion network, we explore the great…
Spatial-Temporal Graph Enhanced DETR Towards Multi-Frame 3D Object Detection
Yifan Zhang, Zhiyu Zhu, Junhui Hou +1
The Detection Transformer (DETR) has revolutionized the design of CNN-based object detection systems, showcasing impressive performance. However, its potential in the domain of mul…
Deep Diversity-Enhanced Feature Representation of Hyperspectral Images
Jinhui Hou, Zhiyu Zhu, Junhui Hou +3
In this paper, we study the problem of efficiently and effectively embedding the high-dimensional spatio-spectral information of hyperspectral (HS) images, guided by feature divers…
Rank-Enhanced Low-Dimensional Convolution Set for Hyperspectral Image Denoising
Jinhui Hou, Zhiyu Zhu, Hui Liu +1
This paper tackles the challenging problem of hyperspectral (HS) image denoising. Unlike existing deep learning-based methods usually adopting complicated network architectures or…
GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimation
Yifan Zhang, Qijian Zhang, Zhiyu Zhu +2
The inherent ambiguity in ground-truth annotations of 3D bounding boxes, caused by occlusions, signal missing, or manual annotation errors, can confuse deep 3D object detectors dur…
Deep Posterior Distribution-based Embedding for Hyperspectral Image Super-resolution
Jinhui Hou, Zhiyu Zhu, Junhui Hou +3
In this paper, we investigate the problem of hyperspectral (HS) image spatial super-resolution via deep learning. Particularly, we focus on how to embed the high-dimensional spatia…
Semantic-embedded Unsupervised Spectral Reconstruction from Single RGB Images in the Wild
Zhiyu Zhu, Hui Liu, Junhui Hou +2
This paper investigates the problem of reconstructing hyperspectral (HS) images from single RGB images captured by commercial cameras, \textbf{without} using paired HS and RGB imag…
Deep Amended Gradient Descent for Efficient Spectral Reconstruction from Single RGB Images
Zhiyu Zhu, Hui Liu, Junhui Hou +2
This paper investigates the problem of recovering hyperspectral (HS) images from single RGB images. To tackle such a severely ill-posed problem, we propose a physically-interpretab…
CorrNet3D: Unsupervised End-to-end Learning of Dense Correspondence for 3D Point Clouds
Yiming Zeng, Yue Qian, Zhiyu Zhu +3
Motivated by the intuition that one can transform two aligned point clouds to each other more easily and meaningfully than a misaligned pair, we propose CorrNet3D -- the first unsu…
Deep Selective Combinatorial Embedding and Consistency Regularization for Light Field Super-resolution
Jing Jin, Junhui Hou, Zhiyu Zhu +2
Light field (LF) images acquired by hand-held devices usually suffer from low spatial resolution as the limited detector resolution has to be shared with the angular dimension. LF…
Hyperspectral Image Super-resolution via Deep Progressive Zero-centric Residual Learning
Zhiyu Zhu, Junhui Hou, Jie Chen +2
This paper explores the problem of hyperspectral image (HSI) super-resolution that merges a low resolution HSI (LR-HSI) and a high resolution multispectral image (HR-MSI). The cros…