English
Related papers

Related papers: Interpolation-Aware Padding for 3D Sparse Convolut…

200 papers

The high demand for computational and storage resources severely impede the deployment of deep convolutional neural networks (CNNs) in limited-resource devices. Recent CNN architectures have proposed reduced complexity versions (e.g.…

Computer Vision and Pattern Recognition · Computer Science 2019-10-17 Souvik Kundu , Saurav Prakash , Haleh Akrami , Peter A. Beerel , Keith M. Chugg

This paper presents a new deformable convolution-based video frame interpolation (VFI) method, using a coarse to fine 3D CNN to enhance the multi-flow prediction. This model first extracts spatio-temporal features at multiple scales using a…

Computer Vision and Pattern Recognition · Computer Science 2024-06-11 Duolikun Danier , Fan Zhang , David Bull

Deep convolutional neural networks (CNNs) have been intensively used for multi-class segmentation of data from different modalities and achieved state-of-the-art performances. However, a common problem when dealing with large, high…

Computer Vision and Pattern Recognition · Computer Science 2018-04-13 Chengjia Wang , Tom MacGillivray , Gillian Macnaught , Guang Yang , David Newby

Convolutional Neural Networks (CNNs) have emerged as a fundamental technology for machine learning. High performance and extreme energy efficiency are critical for deployments of CNNs in a wide range of situations, especially mobile…

Very deep convolutional neural networks (CNNs) have been firmly established as the primary methods for many computer vision tasks. However, most state-of-the-art CNNs are large, which results in high inference latency. Recently, depth-wise…

Computer Vision and Pattern Recognition · Computer Science 2025-01-07 Yihui He , Jianing Qian , Jianren Wang , Cindy X. Le , Congrui Hetang , Qi Lyu , Wenping Wang , Tianwei Yue

Reconstructing 3D objects from extremely sparse views is a long-standing and challenging problem. While recent techniques employ image diffusion models for generating plausible images at novel viewpoints or for distilling pre-trained…

Computer Vision and Pattern Recognition · Computer Science 2023-12-21 Zi-Xin Zou , Weihao Cheng , Yan-Pei Cao , Shi-Sheng Huang , Ying Shan , Song-Hai Zhang

The availability of large-scale annotated image datasets and recent advances in supervised deep learning methods enable the end-to-end derivation of representative image features that can impact a variety of image analysis problems. Such…

Computer Vision and Pattern Recognition · Computer Science 2020-06-23 Euijoon Ahn , Jinman Kim , Ashnil Kumar , Michael Fulham , Dagan Feng

Convolutional neural networks are designed for dense data, but vision data is often sparse (stereo depth, point clouds, pen stroke, etc.). We present a method to handle sparse depth data with optional dense RGB, and accomplish depth…

Computer Vision and Pattern Recognition · Computer Science 2018-09-03 Maximilian Jaritz , Raoul de Charette , Emilie Wirbel , Xavier Perrotton , Fawzi Nashashibi

Stable Diffusion (SD) has evolved DDPM (Denoising Diffusion Probabilistic Model) based image generation significantly by denoising in latent space instead of feature space. This popularized DDPM-based image generation as the cost and…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Md Abu Obaida Zishan , Jannatun Noor , Annajiat Alim Rasel

The convolutional neural network (CNN) is one of the most commonly used architectures for computer vision tasks. The key building block of a CNN is the convolutional kernel that aggregates information from the pixel neighborhood and shares…

Image and Video Processing · Electrical Eng. & Systems 2022-02-08 Tianyu Ma , Alan Q. Wang , Adrian V. Dalca , Mert R. Sabuncu

Transposed convolution is crucial for generating high-resolution outputs, yet has received little attention compared to convolution layers. In this work we revisit transposed convolution and introduce a novel layer that allows us to place…

Computer Vision and Pattern Recognition · Computer Science 2022-10-19 Stefano B. Blumberg , Daniele Raví , Mou-Cheng Xu , Matteo Figini , Iasonas Kokkinos , Daniel C. Alexander

There is an increasing interest in applying deep learning to 3D mesh segmentation. We observe that 1) existing feature-based techniques are often slow or sensitive to feature resizing, 2) there are minimal comparative studies and 3)…

Graphics · Computer Science 2018-02-09 David George , Xianghua Xie , Gary KL Tam

Pooling is a simple but essential layer in modern deep CNN architectures for feature aggregation and extraction. Typical CNN design focuses on the conv layers and activation functions, while leaving the pooling layers with fewer options. We…

Computer Vision and Pattern Recognition · Computer Science 2021-10-22 Bor-Shiun Wang , Jun-Wei Hsieh , Ming-Ching Chang , Ping-Yang Chen , Lipeng Ke , Siwei Lyu

Modern convolutional neural networks (CNNs) are workhorses for video and image processing, but fail to adapt to the computational complexity of input samples in a dynamic manner to minimize energy consumption. In this research, we propose…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Mohamed Mejri , Ashiqur Rasul , Abhijit Chatterjee

Convolutional neural networks (CNNs) have shown great capability of solving various artificial intelligence tasks. However, the increasing model size has raised challenges in employing them in resource-limited applications. In this work, we…

Computer Vision and Pattern Recognition · Computer Science 2018-09-06 Hongyang Gao , Zhengyang Wang , Shuiwang Ji

In convolutional neural networks (CNNs), downsampling operations are crucial to model performance. Although traditional downsampling methods (such as maximum pooling and cross-row convolution) perform well in feature aggregation, receptive…

Computer Vision and Pattern Recognition · Computer Science 2025-07-22 Wenbo Yue , Chang Li , Guoping Xu

We propose a new approach for 3D instance segmentation based on sparse convolution and point affinity prediction, which indicates the likelihood of two points belonging to the same instance. The proposed network, built upon submanifold…

Computer Vision and Pattern Recognition · Computer Science 2019-02-13 Chen Liu , Yasutaka Furukawa

Two major challenges of 3D LiDAR Panoptic Segmentation (PS) are that point clouds of an object are surface-aggregated and thus hard to model the long-range dependency especially for large instances, and that objects are too close to…

Computer Vision and Pattern Recognition · Computer Science 2022-01-19 Shuangjie Xu , Rui Wan , Maosheng Ye , Xiaoyi Zou , Tongyi Cao

Self-driving cars need to understand 3D scenes efficiently and accurately in order to drive safely. Given the limited hardware resources, existing 3D perception models are not able to recognize small instances (e.g., pedestrians, cyclists)…

Computer Vision and Pattern Recognition · Computer Science 2020-08-14 Haotian Tang , Zhijian Liu , Shengyu Zhao , Yujun Lin , Ji Lin , Hanrui Wang , Song Han

Normalizing flows are an essential alternative to GANs for generative modelling, which can be optimized directly on the maximum likelihood of the dataset. They also allow computation of the exact latent vector corresponding to an image…

Machine Learning · Computer Science 2021-08-10 Sandeep Nagar , Marius Dufraisse , Girish Varma