English
Related papers

Related papers: MonoSKD: General Distillation Framework for Monocu…

200 papers

Self-supervised monocular depth prediction provides a cost-effective solution to obtain the 3D location of each pixel. However, the existing approaches usually lead to unsatisfactory accuracy, which is critical for autonomous robots. In…

Computer Vision and Pattern Recognition · Computer Science 2021-11-30 Ziyue Feng , Longlong Jing , Peng Yin , Yingli Tian , Bing Li

Knowledge distillation (KD) is an effective method for compressing models in object detection tasks. Due to limited computational capability, UAV-based object detection (UAV-OD) widely adopt the KD technique to obtain lightweight detectors.…

Computer Vision and Pattern Recognition · Computer Science 2024-08-22 Liang Yao , Fan Liu , Chuanyi Zhang , Zhiquan Ou , Ting Wu

Object detection in 3D with stereo cameras is an important problem in computer vision, and is particularly crucial in low-cost autonomous mobile robots without LiDARs. Nowadays, most of the best-performing frameworks for stereo 3D object…

Computer Vision and Pattern Recognition · Computer Science 2021-03-18 Yuxuan Liu , Lujia Wang , Ming Liu

We present a method for single image 3D cuboid object detection and multi-view object SLAM in both static and dynamic environments, and demonstrate that the two parts can improve each other. Firstly for single image object detection, we…

Robotics · Computer Science 2019-04-08 Shichao Yang , Sebastian Scherer

Recent advances in generalizable 3D Gaussian Splatting have demonstrated promising results in real-time high-fidelity rendering without per-scene optimization, yet existing approaches still struggle to handle unfamiliar visual content…

Computer Vision and Pattern Recognition · Computer Science 2025-05-22 Yifan Liu , Keyu Fan , Weihao Yu , Chenxin Li , Hao Lu , Yixuan Yuan

As an inherently ill-posed problem, depth estimation from single images is the most challenging part of monocular 3D object detection (M3OD). Many existing methods rely on preconceived assumptions to bridge the missing spatial information…

Computer Vision and Pattern Recognition · Computer Science 2022-05-20 Zhuoling Li , Zhan Qu , Yang Zhou , Jianzhuang Liu , Haoqian Wang , Lihui Jiang

3D object detection often involves complicated training and testing pipelines, which require substantial domain knowledge about individual datasets. Inspired by recent non-maximum suppression-free 2D object detection models, we propose a 3D…

Computer Vision and Pattern Recognition · Computer Science 2021-10-14 Yue Wang , Justin Solomon

Monocular 3D object detection is of great significance for autonomous driving but remains challenging. The core challenge is to predict the distance of objects in the absence of explicit depth information. Unlike regressing the distance as…

Computer Vision and Pattern Recognition · Computer Science 2022-06-30 Xuepeng Shi , Qi Ye , Xiaozhi Chen , Chuangrong Chen , Zhixiang Chen , Tae-Kyun Kim

A key contributor to recent progress in 3D detection from single images is monocular depth estimation. Existing methods focus on how to leverage depth explicitly, by generating pseudo-pointclouds or providing attention cues for image…

Computer Vision and Pattern Recognition · Computer Science 2022-10-07 Dennis Park , Jie Li , Dian Chen , Vitor Guizilini , Adrien Gaidon

We propose a semi-supervised learning framework for monocular depth estimation. Compared to existing semi-supervised learning methods, which inherit limitations of both sparse supervised and unsupervised loss functions, we achieve the…

Computer Vision and Pattern Recognition · Computer Science 2022-03-21 Jongbeom Baek , Gyeongnyeon Kim , Seungryong Kim

The main challenge of monocular 3D object detection is the accurate localization of 3D center. Motivated by a new and strong observation that this challenge can be remedied by a 3D-space local-grid search scheme in an ideal case, we propose…

Computer Vision and Pattern Recognition · Computer Science 2023-04-05 Xianpeng Liu , Ce Zheng , Kelvin Cheng , Nan Xue , Guo-Jun Qi , Tianfu Wu

Recent foundation models demonstrate strong generalization capabilities in monocular depth estimation. However, directly applying these models to Full Surround Monocular Depth Estimation (FSMDE) presents two major challenges: (1) high…

Computer Vision and Pattern Recognition · Computer Science 2025-12-10 Kyumin Hwang , Wonhyeok Choi , Kiljoon Han , Wonjoon Choi , Minwoo Choi , Yongcheon Na , Minwoo Park , Sunghoon Im

In this paper, we propose the first self-distillation framework for general object detection, termed LGD (Label-Guided self-Distillation). Previous studies rely on a strong pretrained teacher to provide instructive knowledge that could be…

Computer Vision and Pattern Recognition · Computer Science 2022-04-26 Peizhen Zhang , Zijian Kang , Tong Yang , Xiangyu Zhang , Nanning Zheng , Jian Sun

Multi-label image classification is a fundamental but challenging task towards general visual understanding. Existing methods found the region-level cues (e.g., features from RoIs) can facilitate multi-label classification. Nevertheless,…

Computer Vision and Pattern Recognition · Computer Science 2019-02-22 Yongcheng Liu , Lu Sheng , Jing Shao , Junjie Yan , Shiming Xiang , Chunhong Pan

Autonomous driving perception tasks rely heavily on cameras as the primary sensor for Object Detection, Semantic Segmentation, Instance Segmentation, and Object Tracking. However, RGB images captured by cameras lack depth information, which…

Computer Vision and Pattern Recognition · Computer Science 2023-08-02 Marcelo Eduardo Pederiva , José Mario De Martino , Alessandro Zimmer

Current research is primarily dedicated to advancing the accuracy of camera-only 3D object detectors (apprentice) through the knowledge transferred from LiDAR- or multi-modal-based counterparts (expert). However, the presence of the domain…

Computer Vision and Pattern Recognition · Computer Science 2023-10-25 Linyan Huang , Zhiqi Li , Chonghao Sima , Wenhai Wang , Jingdong Wang , Yu Qiao , Hongyang Li

We tackle the problem of monocular 3D object detection across different sensors, environments, and camera setups. In this paper, we introduce a novel unsupervised domain adaptation approach, MonoCT, that generates highly accurate pseudo…

Computer Vision and Pattern Recognition · Computer Science 2025-03-19 Johannes Meier , Louis Inchingolo , Oussema Dhaouadi , Yan Xia , Jacques Kaiser , Daniel Cremers

In this paper, we propose the LiDAR Distillation to bridge the domain gap induced by different LiDAR beams for 3D object detection. In many real-world applications, the LiDAR points used by mass-produced robots and vehicles usually have…

Computer Vision and Pattern Recognition · Computer Science 2022-08-16 Yi Wei , Zibu Wei , Yongming Rao , Jiaxin Li , Jie Zhou , Jiwen Lu

Existing monocular 3D detectors typically tame the pronounced nonlinear regression of 3D bounding box through decoupled prediction paradigm, which employs multiple branches to estimate geometric center, depth, dimensions, and rotation angle…

Computer Vision and Pattern Recognition · Computer Science 2026-03-11 Yifan Wang , Yian Zhao , Fanqi Pu , Xiaochen Yang , Yang Tang , Xi Chen , Wenming Yang

Conventional self-supervised monocular depth prediction methods are based on a static environment assumption, which leads to accuracy degradation in dynamic scenes due to the mismatch and occlusion problems introduced by object motions.…

Computer Vision and Pattern Recognition · Computer Science 2022-07-26 Ziyue Feng , Liang Yang , Longlong Jing , Haiyan Wang , YingLi Tian , Bing Li