53 citations · 294 across the 21 of their papers we have counts for
21 papers
Self-Supervised 3D Scene Flow Estimation and Motion Prediction using Local Rigidity Prior
Ruibo Li, Chi Zhang, Zhe Wang +2
In this article, we investigate self-supervised 3D scene flow estimation and class-agnostic motion prediction on point clouds. A realistic scene can be well modeled as a collection…
Robust Geometry-Preserving Depth Estimation Using Differentiable Rendering
Chi Zhang, Wei Yin, Gang Yu +5
In this study, we address the challenge of 3D scene structure recovery from monocular depth estimation. While traditional depth estimation methods leverage labeled datasets to dire…
DPF-Net: Combining Explicit Shape Priors in Deformable Primitive Field for Unsupervised Structural Reconstruction of 3D Objects
Qingyao Shuai, Chi Zhang, Kaizhi Yang +1
Unsupervised methods for reconstructing structures face significant challenges in capturing the geometric details with consistent structures among diverse shapes of the same catego…
IT3D: Improved Text-to-3D Generation with Explicit View Synthesis
Yiwen Chen, Chi Zhang, Xiaofeng Yang +4
Recent strides in Text-to-3D techniques have been propelled by distilling knowledge from powerful large text-to-image diffusion models (LDMs). Nonetheless, existing Text-to-3D appr…
StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data
Yanda Li, Chi Zhang, Gang Yu +6
The remarkable multimodal capabilities demonstrated by OpenAI's GPT-4 have sparked significant interest in the development of multimodal Large Language Models (LLMs). A primary res…
Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image
Wei Yin, Chi Zhang, Hao Chen +5
Reconstructing accurate 3D scenes from images is a long-standing vision task. Due to the ill-posedness of the single-image reconstruction problem, most well-established methods are…
StyleAvatar3D: Leveraging Image-Text Diffusion Models for High-Fidelity 3D Avatar Generation
Chi Zhang, Yiwen Chen, Yijun Fu +7
The recent advancements in image-text diffusion models have stimulated research interest in large-scale 3D generative models. Nevertheless, the limited availability of diverse 3D r…
Semantics-Preserving Sketch Embedding for Face Generation
Binxin Yang, Xuejin Chen, Chaoqun Wang +3
With recent advances in image-to-image translation tasks, remarkable progress has been witnessed in generating face images from sketches. However, existing methods frequently fail…
CRCNet: Few-shot Segmentation with Cross-Reference and Region-Global Conditional Networks
Weide Liu, Chi Zhang, Guosheng Lin +1
Few-shot segmentation aims to learn a segmentation model that can be generalized to novel classes with only a few training images. In this paper, we propose a Cross-Reference and L…
Few-shot Open-set Recognition Using Background as Unknowns
Nan Song, Chi Zhang, Guosheng Lin
Few-shot open-set recognition aims to classify both seen and novel images given only limited training data of seen classes. The challenge of this task is that the model is required…
Automatic Generation of Product-Image Sequence in E-commerce
Xiaochuan Fan, Chi Zhang, Yong Yang +6
Product images are essential for providing desirable user experience in an e-commerce platform. For a platform with billions of products, it is extremely time-costly and labor-expe…
Efficient Few-Shot Object Detection via Knowledge Inheritance
Ze Yang, Chi Zhang, Ruibo Li +2
Few-shot object detection (FSOD), which aims at learning a generic detector that can adapt to unseen tasks with scarce training samples, has witnessed consistent improvement recent…
Few-Shot Incremental Learning with Continually Evolved Classifiers
Chi Zhang, Nan Song, Guosheng Lin +3
Few-shot class-incremental learning (FSCIL) aims to design machine learning algorithms that can continually learn new concepts from a few data points, without forgetting knowledge…
CycleSegNet: Object Co-segmentation with Cycle Refinement and Region Correspondence
Chi Zhang, Guankai Li, Guosheng Lin +2
Image co-segmentation is an active computer vision task that aims to segment the common objects from a set of images. Recently, researchers design various learning-based algorithms…
Compositional Prototype Network with Multi-view Comparision for Few-Shot Point Cloud Semantic Segmentation
Xiaoyu Chen, Chi Zhang, Guosheng Lin +1
Point cloud segmentation is a fundamental visual understanding task in 3D vision. A fully supervised point cloud segmentation network often requires a large amount of data with poi…
Open Set Recognition with Conditional Probabilistic Generative Models
Xin Sun, Chi Zhang, Guosheng Lin +1
Deep neural networks have made breakthroughs in a wide range of visual understanding tasks. A typical challenge that hinders their real-world applications is that unknown samples m…
CRNet: Cross-Reference Networks for Few-Shot Segmentation
Weide Liu, Chi Zhang, Guosheng Lin +1
Over the past few years, state-of-the-art image segmentation algorithms are based on deep convolutional neural networks. To render a deep network with the ability to understand a c…
Conditional Gaussian Distribution Learning for Open Set Recognition
Xin Sun, Zhenning Yang, Chi Zhang +2
Deep neural networks have achieved state-of-the-art performance in a wide range of recognition/classification tasks. However, when applying deep learning to real-world applications…
DeepEMD: Differentiable Earth Mover's Distance for Few-Shot Learning
Chi Zhang, Yujun Cai, Guosheng Lin +1
In this work, we develop methods for few-shot image classification from a new perspective of optimal matching between image regions. We employ the Earth Mover's Distance (EMD) as a…
CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learning
Chi Zhang, Guosheng Lin, Fayao Liu +2
Recent progress in semantic segmentation is driven by deep Convolutional Neural Networks and large-scale labeled image datasets. However, data labeling for pixel-wise segmentation…
Efficient Eye Typing with 9-direction Gaze Estimation
Chi Zhang, Rui Yao, Jinpeng Cai
Vision based text entry systems aim to help disabled people achieve text communication using eye movement. Most previous methods have employed an existing eye tracker to predict ga…