English
Related papers

Related papers: MSTA3D: Multi-scale Twin-attention for 3D Instance…

200 papers

3D instance segmentation methods typically rely on high-quality point clouds or posed RGB-D scans, requiring complex multi-stage processing pipelines, and are highly sensitive to reconstruction noise. While recent feed-forward transformers…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Jinyuan Qu , Hongyang Li , Lei Zhang

In this paper, we present SegDINO3D, a novel Transformer encoder-decoder framework for 3D instance segmentation. As 3D training data is generally not as sufficient as 2D training images, SegDINO3D is designed to fully leverage 2D…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Jinyuan Qu , Hongyang Li , Xingyu Chen , Shilong Liu , Yukai Shi , Tianhe Ren , Ruitao Jing , Lei Zhang

We present a novel 3D instance segmentation framework for Multi-View Stereo (MVS) buildings in urban scenes. Unlike existing works focusing on semantic segmentation of urban scenes, the emphasis of this work lies in detecting and segmenting…

Computer Vision and Pattern Recognition · Computer Science 2022-08-10 Jiazhou Chen , Yanghui Xu , Shufang Lu , Ronghua Liang , Liangliang Nan

Due to the few annotated labels of 3D point clouds, how to learn discriminative features of point clouds to segment object instances is a challenging problem. In this paper, we propose a simple yet effective 3D instance segmentation…

Computer Vision and Pattern Recognition · Computer Science 2022-10-12 Linghua Tang , Le Hui , Jin Xie

Deep learning techniques have become the to-go models for most vision-related tasks on 2D images. However, their power has not been fully realised on several tasks in 3D space, e.g., 3D scene understanding. In this work, we jointly address…

Computer Vision and Pattern Recognition · Computer Science 2019-04-08 Quang-Hieu Pham , Duc Thanh Nguyen , Binh-Son Hua , Gemma Roig , Sai-Kit Yeung

Despite rapid progress in scene segmentation in recent years, 3D segmentation methods are still limited when there is severe occlusion. The key challenge is estimating the segment boundaries of (partially) occluded objects, which are…

Robotics · Computer Science 2021-04-02 Andrew Price , Kun Huang , Dmitry Berenson

3D instance segmentation plays a crucial role in comprehending 3D scenes. Despite recent advancements in this field, existing approaches exhibit certain limitations. These methods often rely on fixed instance positions obtained from sampled…

Computer Vision and Pattern Recognition · Computer Science 2023-12-12 Mengnan Zhao , Lihe Zhang , Yuqiu Kong , Baocai Yin

3D object detection in point cloud data remains a challenging task due to the sparsity and lack of global structure inherent in the input. In this work, we propose a novel Multi-Scale Attention (MSA) mechanism integrated into the 3DETR…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Mustaqeem Khan , Aidana Nurakhmetova , Wail Gueaieb , Abdulmotaleb El Saddik

Depth completion plays a vital role in 3D perception systems, especially in scenarios where sparse depth data must be densified for tasks such as autonomous driving, robotics, and augmented reality. While many existing approaches rely on…

Computer Vision and Pattern Recognition · Computer Science 2025-12-10 Abdul Haseeb Nizamani , Dandi Zhou , Xinhai Sun

Unsupervised domain adaptation for LiDAR-based 3D object detection (3D UDA) based on the teacher-student architecture with pseudo labels has achieved notable improvements in recent years. Although it is quite popular to collect point clouds…

Computer Vision and Pattern Recognition · Computer Science 2025-11-12 Shenao Zhao , Pengpeng Liang , Zhoufan Yang

Recent advances in self-supervised learning (SSL) for point clouds have substantially improved 3D scene understanding without human annotations. Existing approaches emphasize semantic awareness by enforcing feature consistency across…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Bin Yang , Mohamed Abdelsamad , Miao Zhang , Alexandru Paul Condurache

State-of-the-art transformer-based video instance segmentation (VIS) approaches typically utilize either single-scale spatio-temporal features or per-frame multi-scale features during the attention computations. We argue that such an…

Computer Vision and Pattern Recognition · Computer Science 2022-03-25 Omkar Thawakar , Sanath Narayan , Jiale Cao , Hisham Cholakkal , Rao Muhammad Anwer , Muhammad Haris Khan , Salman Khan , Michael Felsberg , Fahad Shahbaz Khan

We propose an approach to instance segmentation from 3D point clouds based on dynamic convolution. This enables it to adapt, at inference, to varying feature and object scales. Doing so avoids some pitfalls of bottom up approaches,…

Computer Vision and Pattern Recognition · Computer Science 2022-10-17 Tong He , Chunhua Shen , Anton van den Hengel

Detecting objects from LiDAR point clouds is of tremendous significance in autonomous driving. In spite of good progress, accurate and reliable 3D detection is yet to be achieved due to the sparsity and irregularity of LiDAR point clouds.…

Computer Vision and Pattern Recognition · Computer Science 2022-03-21 Shengheng Deng , Zhihao Liang , Lin Sun , Kui Jia

We introduce Multi-Source 3D (MS3D), a new self-training pipeline for unsupervised domain adaptation in 3D object detection. Despite the remarkable accuracy of 3D detectors, they often overfit to specific domain biases, leading to…

Computer Vision and Pattern Recognition · Computer Science 2023-05-10 Darren Tsai , Julie Stephany Berrio , Mao Shan , Eduardo Nebot , Stewart Worrall

Large-scale datasets with point-wise semantic and instance labels are crucial to 3D instance segmentation but also expensive. To leverage unlabeled data, previous semi-supervised 3D instance segmentation approaches have explored…

Computer Vision and Pattern Recognition · Computer Science 2024-06-25 Yizheng Wu , Zhiyu Pan , Kewei Wang , Xingyi Li , Jiahao Cui , Liwen Xiao , Guosheng Lin , Zhiguo Cao

Instance segmentation is an important task for scene understanding. Compared to the fully-developed 2D, 3D instance segmentation for point clouds have much room to improve. In this paper, we present PointGroup, a new end-to-end bottom-up…

Computer Vision and Pattern Recognition · Computer Science 2020-04-06 Li Jiang , Hengshuang Zhao , Shaoshuai Shi , Shu Liu , Chi-Wing Fu , Jiaya Jia

3D instance segmentation is crucial for applications demanding comprehensive 3D scene understanding. In this paper, we introduce a novel method that simultaneously learns coefficients and prototypes. Employing an overcomplete sampling…

Computer Vision and Pattern Recognition · Computer Science 2024-07-11 Remco Royen , Leon Denis , Adrian Munteanu

Instance segmentation in point clouds is one of the most fine-grained ways to understand the 3D scene. Due to its close relationship to semantic segmentation, many works approach these two tasks simultaneously and leverage the benefits of…

Computer Vision and Pattern Recognition · Computer Science 2020-03-12 Guangnan Wu , Zhiyi Pan , Peng Jiang , Changhe Tu

Although transformer is preferred in natural language processing, some studies has only been applied to the field of medical imaging in recent years. For its long-term dependency, the transformer is expected to contribute to unconventional…

Image and Video Processing · Electrical Eng. & Systems 2024-09-17 Jing Xu