paper-with-me

홈 › Papers

LightStereo: Channel Boost Is All Your Need for Efficient 2D Cost Aggregation

2024-06-28 · Xianda Guo, Chenming Zhang, Youmin Zhang, Wenzhao Zheng, Dujun Nie, Matteo Poggi, Long Chen

We present LightStereo, a cutting-edge stereo-matching network crafted to accelerate the matching process. Departing from conventional methodologies that rely on aggregating computationally intensive 4D costs, LightStereo adopts the 3D cost volume as a lightweight alternative. While similar approaches have been explored previously, our breakthrough lies in enhancing performance through a dedicated focus on the channel dimension of the 3D cost volume, where the distribution of matching costs is encapsulated. Our exhaustive exploration has yielded plenty of strategies to amplify the capacity of the pivotal dimension, ensuring both precision and efficiency. We compare the proposed LightStereo with existing state-of-the-art methods across various benchmarks, which demonstrate its superior performance in speed, accuracy, and resource utilization. LightStereo achieves a competitive EPE metric in the SceneFlow datasets while demanding a minimum of only 22 GFLOPs and 17 ms of runtime, and ranks 1st on KITTI 2015 among real-time models. Our comprehensive analysis reveals the effect of 2D cost aggregation for stereo matching, paving the way for real-world applications of efficient stereo systems. Code will be available at \url{https://github.com/XiandaGuo/OpenStereo}.

📄 PDF Abstract BibTeX arXiv:2406.19833

Code (1)

xiandaguo/openstereo 공식 구현 pytorch

Tasks

AllStereo Matching

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Follow-Your-Instruction: A Comprehensive MLLM Agent for World Data Synthesis

2025-08-07 · Kunyu Feng, Yue Ma, Xinhua Zhang, Boshi Liu 외 arxiv

With the growing demands of AI-generated content (AIGC), the need for high-quality, diverse, and scalable data has become increasingly crucial. However, collecting large-scale real-world data remains costly and time-cons…

Dynamic Channel Pruning: Feature Boosting and Suppression

2018-10-12 · ICLR 2019 5 · Xitong Gao, Yiren Zhao, Łukasz Dudziak, Robert Mullins 외

Making deep convolutional neural networks more accurate typically comes at the cost of increased computational and memory resources. In this paper, we reduce this cost by exploiting the fact that the importance of featur…

Model CompressionNetwork Pruning

Can Your Face Detector Do Anti-spoofing? Face Presentation Attack Detection with a Multi-Channel Face Detector

2020-06-30 · Anjith George, Sebastien Marcel

In a typical face recognition pipeline, the task of the face detector is to localize the face region. However, the face detector localizes regions that look like a face, irrespective of the liveliness of the face, which …

Face Presentation Attack DetectionFace Recognitionobject-detectionObject Detection

Group Fisher Pruning for Practical Network Compression

2021-08-02 · Liyang Liu, Shilong Zhang, Zhanghui Kuang, Aojun Zhou 외

Network compression has been widely studied since it is able to reduce the memory and computation cost during inference. However, previous methods seldom deal with complicated structures like residual connections, group/…

image-classificationImage ClassificationNetwork Pruningobject-detection+1

YourMT3+: Multi-instrument Music Transcription with Enhanced Transformer Architectures and Cross-dataset Stem Augmentation

2024-07-05 · Sungkyun Chang, Emmanouil Benetos, Holger Kirchhoff, Simon Dixon

Multi-instrument music transcription aims to convert polyphonic music recordings into musical scores assigned to each instrument. This task is challenging for modeling as it requires simultaneously identifying multiple i…

Drum TranscriptionDrum Transcription in Music (DTM)Mixture-of-ExpertsMulti-instrument Music Transcription+2