Search Results for author:
Found 12 papers, 1 papers with code
MVQ:Towards Efficient DNN Compression and Acceleration with Masked Vector Quantization
Only distances between the unpruned weights and the codewords are computed, which are then used to update the codewords.
Efficiency Meets Fidelity: A Novel Quantization Framework for Stable Diffusion
Based on this pipeline, we further introduce a mix-precision quantization strategy, multi-timestep activation quantization, and time information precalculation techniques to ensure high-fidelity generation in comparison to floating-point models.
Canonic Signed Spike Coding for Efficient Spiking Neural Networks
The conversion of Artificial Neural Networks (ANNs) to SNNs is the most widely used training method, which ensures that the resulting SNNs perform comparably to ANNs on large-scale datasets.
WaveIPT: Joint Attention and Flow Alignment in the Wavelet domain for Pose Transfer
To leverage the advantages of both attention and flow simultaneously, we propose Wavelet-aware Image-based Pose Transfer (WaveIPT) to fuse the attention and flow in the wavelet domain.
Thermal Infrared Image Inpainting via Edge-Aware Guidance
In this paper, we propose a novel task -- Thermal Infrared Image Inpainting, which aims to reconstruct missing regions of TIR images.
FDA-GAN: Flow-based Dual Attention GAN for Human Pose Transfer
Human pose transfer aims at transferring the appearance of the source person to the target pose.
GLocal: Global Graph Reasoning and Local Structure Transfer for Person Image Generation
In this paper, we focus on person image generation, namely, generating person image under various conditions, e. g., corrupted texture or different pose.
A Reconfigurable Convolution-in-Pixel CMOS Image Sensor Architecture
The separation of the data capture and analysis in modern vision systems has led to a massive amount of data transfer between the end devices and cloud computers, resulting in long latency, slow response, and high power consumption.
C2F-FWN: Coarse-to-Fine Flow Warping Network for Spatial-Temporal Consistent Motion Transfer
Although existing GAN-based HVMT methods have achieved great success, they either fail to preserve appearance details due to the loss of spatial consistency between synthesized and exemplary images, or generate incoherent video results due to the lack of temporal consistency among video frames.
A Foreground-background Parallel Compression with Residual Encoding for Surveillance Video
In this paper, we propose a video compression method that extracts and compresses the foreground and background of the video separately.
A GAN-based Tunable Image Compression System
The method of importance map has been widely adopted in DNN-based lossy image compression to achieve bit allocation according to the importance of image contents.
GAC-GAN: A General Method for Appearance-Controllable Human Video Motion Transfer
Therefore, each trained model can only generate videos with a specific scene appearance, new models are required to be trained to generate new appearances.
