English
Related papers

Related papers: Regularizing Self-supervised 3D Scene Flows with S…

200 papers

In point clouds, noise directly perturbs point coordinates that encode both spatial location and geometry, making one-to-one correspondence construction more challenging than in images. Existing methods impose statistical mappings across…

Computer Vision and Pattern Recognition · Computer Science 2026-05-27 Chengwei Zhang , Xueyi Zhang , Tao Jiang , Xinhao Xu , Wenjie Li , Fubo Zhang , Longyong Chen

Low-resolution point clouds are challenging for object detection methods due to their sparsity. Densifying the present point cloud by concatenating it with its predecessors is a popular solution to this challenge. Such concatenation is…

Computer Vision and Pattern Recognition · Computer Science 2023-05-05 Minh-Quan Dao , Vincent Frémont , Elwan Héry

Learning 3D scene geometry and semantics from images is a core challenge in computer vision and a key capability for autonomous driving. Since large-scale 3D annotation is prohibitively expensive, recent work explores self-supervised…

Computer Vision and Pattern Recognition · Computer Science 2025-11-24 Adam Lilja , Ji Lan , Junsheng Fu , Lars Hammarstrand

In this paper, we propose a novel self-supervised motion estimator for LiDAR-based autonomous driving via BEV representation. Different from usually adopted self-supervised strategies for data-level structure consistency, we predict scene…

Computer Vision and Pattern Recognition · Computer Science 2023-04-26 Xiangze Jia , Hui Zhou , Xinge Zhu , Yandong Guo , Ji Zhang , Yuexin Ma

Contemporary deep neural networks offer state-of-the-art results when applied to visual reasoning, e.g., in the context of 3D point cloud data. Point clouds are important datatype for precise modeling of three-dimensional environments, but…

Machine Learning · Computer Science 2022-05-23 Maciej Zamorski , Michał Stypułkowski , Konrad Karanowski , Tomasz Trzciński , Maciej Zięba

In a constant evolving world, change detection is of prime importance to keep updated maps. To better sense areas with complex geometry (urban areas in particular), considering 3D data appears to be an interesting alternative to classical…

Computer Vision and Pattern Recognition · Computer Science 2024-10-28 Iris de Gélis , Sébastien Lefèvre , Thomas Corpetti

Scene understanding has been of high interest in computer vision. It encompasses not only identifying objects in a scene, but also their relationships within the given context. With this goal, a recent line of works tackles 3D semantic…

Computer Vision and Pattern Recognition · Computer Science 2020-04-09 Johanna Wald , Helisa Dhamo , Nassir Navab , Federico Tombari

In this paper, we focus on unsupervised representation learning for clustering of images. Recent advances in deep clustering and unsupervised representation learning are based on the idea that different views of an input image (generated…

Computer Vision and Pattern Recognition · Computer Science 2022-04-26 Aniket Anand Deshmukh , Jayanth Reddy Regatti , Eren Manavoglu , Urun Dogan

Semantic segmentation of raw 3D point clouds is an essential component in 3D scene analysis, but it poses several challenges, primarily due to the non-Euclidean nature of 3D point clouds. Although, several deep learning based approaches…

Computer Vision and Pattern Recognition · Computer Science 2020-12-01 Saqib Ali Khan , Yilei Shi , Muhammad Shahzad , Xiao Xiang Zhu

Recent advances in 3D representations, such as Neural Radiance Fields and 3D Gaussian Splatting, have greatly improved realistic scene modeling and novel-view synthesis. However, achieving controllable and consistent editing in dynamic 3D…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Kai He , Chin-Hsuan Wu , Igor Gilitschenski

Large models have shown generalization across datasets for many low-level vision tasks, like depth estimation, but no such general models exist for scene flow. Even though scene flow has wide potential use, it is not used in practice…

Computer Vision and Pattern Recognition · Computer Science 2025-01-22 Yiqing Liang , Abhishek Badki , Hang Su , James Tompkin , Orazio Gallo

3D Gaussian Splatting (3DGS) is a powerful alternative to Neural Radiance Fields (NeRF), excelling in complex scene reconstruction and efficient rendering. However, it relies on high-quality point clouds from Structure-from-Motion (SfM),…

Computer Vision and Pattern Recognition · Computer Science 2025-07-01 Ziao Liu , Zhenjia Li , Yifeng Shi , Xiangang Li

Consistency models imitate the multi-step sampling of score-based diffusion in a single forward pass of a neural network. They can be learned in two ways: consistency distillation and consistency training. The former relies on the true…

Machine Learning · Computer Science 2025-07-03 Thibaut Issenhuth , Sangchul Lee , Ludovic Dos Santos , Jean-Yves Franceschi , Chansoo Kim , Alain Rakotomamonjy

Recent self-supervised clustering-based pre-training techniques like DINO and Cribo have shown impressive results for downstream detection and segmentation tasks. However, real-world applications such as autonomous driving face challenges…

Computer Vision and Pattern Recognition · Computer Science 2025-01-27 Maciej K. Wozniak , Hariprasath Govindarajan , Marvin Klingner , Camille Maurice , B Ravi Kiran , Senthil Yogamani

Robots can acquire complex manipulation skills by learning policies from expert demonstrations, which is often known as vision-based imitation learning. Generating policies based on diffusion and flow matching models has been shown to be…

Robotics · Computer Science 2024-12-17 Qinglun Zhang , Zhen Liu , Haoqiang Fan , Guanghui Liu , Bing Zeng , Shuaicheng Liu

Novel view synthesis of dynamic scenes is becoming important in various applications, including augmented and virtual reality. We propose a novel 4D Gaussian Splatting (4DGS) algorithm for dynamic scenes from casually recorded monocular…

Computer Vision and Pattern Recognition · Computer Science 2024-11-14 Mijeong Kim , Jongwoo Lim , Bohyung Han

Reliable 3D dynamic perception requires models that can anticipate motion beyond predefined categories, yet progress is hindered by the scarcity of dense, high-quality motion annotations. While self-supervision on unlabeled real data offers…

Computer Vision and Pattern Recognition · Computer Science 2026-04-13 Qingwen Zhang , Xiaomeng Zhu , Chenhan Jiang , Patric Jensfelt

Depth perception is considered an invaluable source of information in the context of 3D mapping and various robotics applications. However, point cloud maps acquired using consumer-level light detection and ranging sensors (lidars) still…

Robotics · Computer Science 2024-05-24 Ruslan Agishev , Tomáš Pětříček , Karel Zimmermann

The perception of motion behavior in a dynamic environment holds significant importance for autonomous driving systems, wherein class-agnostic motion prediction methods directly predict the motion of the entire point cloud. While most…

Computer Vision and Pattern Recognition · Computer Science 2024-03-22 Kewei Wang , Yizheng Wu , Jun Cen , Zhiyu Pan , Xingyi Li , Zhe Wang , Zhiguo Cao , Guosheng Lin

Point clouds obtained from 3D scans are typically sparse, irregular, and noisy, and required to be consolidated. In this paper, we present the first deep learning based edge-aware technique to facilitate the consolidation of point clouds.…

Computer Vision and Pattern Recognition · Computer Science 2018-07-18 Lequan Yu , Xianzhi Li , Chi-Wing Fu , Daniel Cohen-Or , Pheng-Ann Heng