487 citations · 746 across the 15 of their papers we have counts for
15 papers
AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation
Zhen Li, Zuo-Liang Zhu, Ling-Hao Han +3
We present All-Pairs Multi-Field Transforms (AMT), a new network architecture for video frame interpolation. It is based on two essential designs. First, we build bidirectional cor…
Looking Through the Glass: Neural Surface Reconstruction Against High Specular Reflections
Jiaxiong Qiu, Peng-Tao Jiang, Yifan Zhu +3
Neural implicit methods have achieved high-quality 3D object surfaces under slight specular highlights. However, high specular reflections (HSR) often appear in front of target obj…
Advances in Deep Concealed Scene Understanding
Deng-Ping Fan, Ge-Peng Ji, Peng Xu +3
Concealed scene understanding (CSU) is a hot computer vision topic aiming to perceive objects exhibiting camouflage. The current boom in terms of techniques and applications warran…
SRFormerV2: Taking a Closer Look at Permuted Self-Attention for Image Super-Resolution
Yupeng Zhou, Zhen Li, Chun-Le Guo +3
Previous works have shown that increasing the window size for Transformer-based image super-resolution models (e.g., SwinIR) can significantly improve the model performance. Still,…
SLAN: Self-Locator Aided Network for Cross-Modal Understanding
Jiang-Tian Zhai, Qi Zhang, Tong Wu +4
Learning fine-grained interplay between vision and language allows to a more accurate understanding for VisionLanguage tasks. However, it remains challenging to extract key image r…
ClipCrop: Conditioned Cropping Driven by Vision-Language Model
Zhihang Zhong, Mingxi Cheng, Zhirong Wu +7
Image cropping has progressed tremendously under the data-driven paradigm. However, current approaches do not account for the intentions of the user, which is an issue especially w…
Dual Pyramid Generative Adversarial Networks for Semantic Image Synthesis
Shijie Li, Ming-Ming Cheng, Juergen Gall
The goal of semantic image synthesis is to generate photo-realistic images from semantic label maps. It is highly relevant for tasks like content generation and image editing. Curr…
GMA3D: Local-Global Attention Learning to Estimate Occluded Motions of Scene Flow
Zhiyang Lu, Ming Cheng
Scene flow represents the motion information of each point in the 3D point clouds. It is a vital downstream method applied to many tasks, such as motion segmentation and object tra…
SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation
Meng-Hao Guo, Cheng-Ze Lu, Qibin Hou +3
We present SegNeXt, a simple convolutional network architecture for semantic segmentation. Recent transformer-based models have dominated the field of semantic segmentation due to…
Designing An Illumination-Aware Network for Deep Image Relighting
Zuo-Liang Zhu, Zhen Li, Rui-Xun Zhang +2
Lighting is a determining factor in photography that affects the style, expression of emotion, and even quality of images. Creating or finding satisfying lighting conditions, in re…
RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks
Shanghua Gao, Zhong-Yu Li, Qi Han +2
Temporal/spatial receptive fields of models play an important role in sequential/spatial tasks. Large receptive fields facilitate long-term relations, while small receptive fields…
SERE: Exploring Feature Self-relation for Self-supervised Transformer
Zhong-Yu Li, Shanghua Gao, Ming-Ming Cheng
Learning representations with self-supervision for convolutional networks (CNN) has been validated to be effective for vision tasks. As an alternative to CNN, vision transformers (…
Interactive Style Transfer: All is Your Palette
Zheng Lin, Zhao Zhang, Kang-Rui Zhang +2
Neural style transfer (NST) can create impressive artworks by transferring reference style to content image. Current image-to-image NST methods are short of fine-grained controls,…
Visual Attention Network
Meng-Hao Guo, Cheng-Ze Lu, Zheng-Ning Liu +2
While originally designed for natural language processing tasks, the self-attention mechanism has recently taken various computer vision areas by storm. However, the 2D nature of i…
On the Connection between Local Attention and Dynamic Depth-wise Convolution
Qi Han, Zejia Fan, Qi Dai +4
Vision Transformer (ViT) attains state-of-the-art performance in visual recognition, and the variant, Local Vision Transformer, makes further improvements. The major component in L…