2.4k citations · 3.5k across the 43 of their papers we have counts for
45 papers
RigNet++: Semantic Assisted Repetitive Image Guided Network for Depth Completion
Zhiqiang Yan, Xiang Li, Le Hui +3
Depth completion aims to recover dense depth maps from sparse ones, where color images are often used to facilitate this task. Recent depth methods primarily focus on image guided…
AltNeRF: Learning Robust Neural Radiance Field via Alternating Depth-Pose Optimization
Kun Wang, Zhiqiang Yan, Huang Tian +4
Neural Radiance Fields (NeRF) have shown promise in generating realistic novel views from sparse scene images. However, existing NeRF approaches often encounter challenges due to t…
Creative Birds: Self-Supervised Single-View 3D Style Transfer
Renke Wang, Guimin Que, Shuo Chen +3
In this paper, we propose a novel method for single-view 3D style transfer that generates a unique 3D object with both shape and texture transfer. Our focus lies primarily on birds…
Learnable Differencing Center for Nighttime Depth Perception
Zhiqiang Yan, Yupeng Zheng, Chongyi Li +2
Depth completion is the task of recovering dense depth maps from sparse ones, usually with the help of color images. Existing image-guided methods perform well on daytime depth per…
Variable Radiance Field for Real-World Category-Specific Reconstruction from Single Image
Kun Wang, Zhiqiang Yan, Zhenyu Zhang +3
Reconstructing category-specific objects using Neural Radiance Field (NeRF) from a single image is a promising yet challenging task. Existing approaches predominantly rely on proje…
Fine-Grained Visual Prompting
Lingfeng Yang, Yueze Wang, Xiang Li +2
Vision-Language Models (VLMs), such as CLIP, have demonstrated impressive zero-shot transfer capabilities in image-level visual perception. However, these models have shown limited…
Is Synthetic Data From Diffusion Models Ready for Knowledge Distillation?
Zheng Li, Yuxuan Li, Penghai Zhao +3
Diffusion models have recently achieved astonishing performance in generating high-fidelity photo-realistic images. Given their huge success, it is still unclear whether synthetic…
A Survey of Historical Learning: Learning Models with Learning History
Xiang Li, Ge Wu, Lingfeng Yang +3
New knowledge originates from the old. The various types of elements, deposited in the training history, are a large amount of wealth for improving learning deep models. In this su…
Large Selective Kernel Network for Remote Sensing Object Detection
Yuxuan Li, Qibin Hou, Zhaohui Zheng +3
Recent research on remote sensing object detection has largely focused on improving the representation of oriented bounding boxes but has overlooked the unique prior knowledge pres…
Non-aligned supervision for Real Image Dehazing
Junkai Fan, Fei Guo, Jianjun Qian +3
Removing haze from real-world images is challenging due to unpredictable weather conditions, resulting in the misalignment of hazy and clear image pairs. In this paper, we propose…
Recurrent Structure Attention Guidance for Depth Super-Resolution
Jiayi Yuan, Haobo Jiang, Xiang Li +3
Image guidance is an effective strategy for depth super-resolution. Generally, most existing methods employ hand-crafted operators to decompose the high-frequency (HF) and low-freq…
Structure Flow-Guided Network for Real Depth Super-Resolution
Jiayi Yuan, Haobo Jiang, Xiang Li +3
Real depth super-resolution (DSR), unlike synthetic settings, is a challenging task due to the structural distortion and the edge noise caused by the natural degradation in real-wo…
One-Stage Cascade Refinement Networks for Infrared Small Target Detection
Yimian Dai, Xiang Li, Fei Zhou +3
Single-frame InfraRed Small Target (SIRST) detection has been a challenging task due to a lack of inherent characteristics, imprecise bounding box regression, a scarcity of real-wo…
Curriculum Temperature for Knowledge Distillation
Zheng Li, Xiang Li, Lingfeng Yang +5
Most existing distillation methods ignore the flexible role of the temperature in the loss function and fix it as a hyper-parameter that can be decided by an inefficient grid searc…
DesNet: Decomposed Scale-Consistent Network for Unsupervised Depth Completion
Zhiqiang Yan, Kun Wang, Xiang Li +3
Unsupervised depth completion aims to recover dense depth from the sparse one without using the ground-truth annotation. Although depth measurement obtained from LiDAR is usually s…
Uniform Masking: Enabling MAE Pre-training for Pyramid-based Vision Transformers with Locality
Xiang Li, Wenhai Wang, Lingfeng Yang +1
Masked AutoEncoder (MAE) has recently led the trends of visual self-supervision area by an elegant asymmetric encoder-decoder design, which significantly optimizes both the pre-tra…
RecursiveMix: Mixed Learning with History
Lingfeng Yang, Xiang Li, Borui Zhao +2
Mix-based augmentation has been proven fundamental to the generalization of deep vision models. However, current augmentations only mix samples at the current data batch during tra…
Dynamic MLP for Fine-Grained Image Classification by Leveraging Geographical and Temporal Information
Lingfeng Yang, Xiang Li, Renjie Song +5
Fine-grained image classification is a challenging computer vision task where various species share similar visual appearances, resulting in misclassification if merely based on vi…
Multi-Modal Masked Pre-Training for Monocular Panoramic Depth Completion
Zhiqiang Yan, Xiang Li, Kun Wang +3
In this paper, we formulate a potentially valuable panoramic depth completion (PDC) task as panoramic 3D cameras often produce 360° depth with missing data in complex scenes. Its g…
Generative Dynamic Patch Attack
Xiang Li, Shihao Ji
Adversarial patch attack is a family of attack algorithms that perturb a part of image to fool a deep neural network model. Existing patch attacks mostly consider injecting adversa…
Student Helping Teacher: Teacher Evolution via Self-Knowledge Distillation
Zheng Li, Xiang Li, Lingfeng Yang +2
Knowledge distillation usually transfers the knowledge from a pre-trained cumbersome teacher network to a compact student network, which follows the classical teacher-teaching-stud…
Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the Dark
Kun Wang, Zhenyu Zhang, Zhiqiang Yan +4
Monocular depth estimation aims at predicting depth from a single image or video. Recently, self-supervised methods draw much attention since they are free of depth annotations and…
RigNet: Repetitive Image Guided Network for Depth Completion
Zhiqiang Yan, Kun Wang, Xiang Li +3
Depth completion deals with the problem of recovering dense depth maps from sparse ones, where color images are often used to facilitate this task. Recent approaches mainly focus o…
PVT v2: Improved Baselines with Pyramid Vision Transformer
Wenhai Wang, Enze Xie, Xiang Li +6
Transformer recently has presented encouraging progress in computer vision. In this work, we present new baselines by improving the original Pyramid Vision Transformer (PVT v1) by…