English
Related papers

Related papers: Learning Direct Optimization for Scene Understandi…

200 papers

Despite recent advancements in computer vision research, object detection in aerial images still suffers from several challenges. One primary challenge to be mitigated is the presence of multiple types of variation in aerial images, for…

Computer Vision and Pattern Recognition · Computer Science 2025-05-30 Sungjune Park , Hyunjun Kim , Beomchan Park , Yong Man Ro

Imitation learning has proven to be a powerful tool for training complex visuomotor policies. However, current methods often require hundreds to thousands of expert demonstrations to handle high-dimensional visual observations. A key reason…

Robotics · Computer Science 2024-11-01 Zichen Jeff Cui , Hengkai Pan , Aadhithya Iyer , Siddhant Haldar , Lerrel Pinto

Global localization is essential for robot navigation, of which the first step is to retrieve a query from the map database. This problem is called place recognition. In recent years, LiDAR scan based place recognition has drawn attention…

Robotics · Computer Science 2021-01-14 Xuecheng Xu , Huan Yin , Zexi Chen , Yue Wang , Rong Xiong

A supervised machine learning algorithm, called locally adaptive discriminant analysis (LADA), has been developed to locate boundaries between identifiable image features that have varying intensities. LADA is an adaptation of image…

Person re-identification is an important technique towards automatic search of a person's presence in a surveillance video. Two fundamental problems are critical for person re-identification, feature representation and metric learning. An…

Computer Vision and Pattern Recognition · Computer Science 2015-05-07 Shengcai Liao , Yang Hu , Xiangyu Zhu , Stan Z. Li

Diffusion models emerged as a leading approach in text-to-image generation, producing high-quality images from textual descriptions. However, attempting to achieve detailed control to get a desired image solely through text remains a…

Computer Vision and Pattern Recognition · Computer Science 2026-02-12 Pablo Domingo-Gregorio , Javier Ruiz-Hidalgo

LiDAR representation learning aims to extract rich structural and semantic information from large-scale, readily available datasets, reducing reliance on costly human annotations. However, existing LiDAR representation strategies often…

Computer Vision and Pattern Recognition · Computer Science 2025-07-08 Xiang Xu , Lingdong Kong , Song Wang , Chuanwei Zhou , Qingshan Liu

Field robotics in perceptually-challenging environments require fast and accurate state estimation, but modern LiDAR sensors quickly overwhelm current odometry algorithms. To this end, this paper presents a lightweight frontend LiDAR…

Robotics · Computer Science 2022-01-10 Kenny Chen , Brett T. Lopez , Ali-akbar Agha-mohammadi , Ankur Mehta

Computer vision techniques play a central role in the perception stack of autonomous vehicles. Such methods are employed to perceive the vehicle surroundings given sensor data. 3D LiDAR sensors are commonly used to collect sparse 3D point…

Computer Vision and Pattern Recognition · Computer Science 2024-03-21 Lucas Nunes , Rodrigo Marcuzzi , Benedikt Mersch , Jens Behley , Cyrill Stachniss

Differentiable rendering aims to compute the derivative of the image rendering function with respect to the rendering parameters. This paper presents a novel algorithm for 6-DoF pose estimation through gradient-based optimization using a…

Computer Vision and Pattern Recognition · Computer Science 2022-12-27 Ramchander Rao Bhaskara , Roshan Thomas Eapen , Manoranjan Majji

Accurate lane localization and lane change detection are crucial in advanced driver assistance systems and autonomous driving systems for safer and more efficient trajectory planning. Conventional localization devices such as Global…

Computer Vision and Pattern Recognition · Computer Science 2019-11-12 Zhensong Wei , Chao Wang , Peng Hao , Matthew Barth

Popular representation learning methods encourage feature invariance under transformations applied at the input. However, in 3D perception tasks like object localization and segmentation, outputs are naturally equivariant to some…

Computer Vision and Pattern Recognition · Computer Science 2024-04-19 Deepti Hegde , Suhas Lohit , Kuan-Chuan Peng , Michael J. Jones , Vishal M. Patel

Accurately estimating the position of static objects, such as traffic lights, from the moving camera of a self-driving car is a challenging problem. In this work, we present a system that improves the localization of static objects by…

Computer Vision and Pattern Recognition · Computer Science 2021-01-05 Mohamed Chaabane , Lionel Gueguen , Ameni Trabelsi , Ross Beveridge , Stephen O'Hara

In recent years, deep generative models have gained significance due to their ability to synthesize natural-looking images with applications ranging from virtual reality to data augmentation for training computer vision models. While…

Computer Vision and Pattern Recognition · Computer Science 2020-06-08 Paul Sanzenbacher , Lars Mescheder , Andreas Geiger

While 2D object detection has improved significantly over the past, real world applications of computer vision often require an understanding of the 3D layout of a scene. Many recent approaches to 3D detection use LiDAR point clouds for…

Computer Vision and Pattern Recognition · Computer Science 2020-11-20 Jihao Andreas Lin , Jakob Brünker , Daniel Fährmann

Aggressive motions from agile flights or traversing irregular terrain induce motion distortion in LiDAR scans that can degrade state estimation and mapping. Some methods exist to mitigate this effect, but they are still too simplistic or…

Robotics · Computer Science 2023-03-08 Kenny Chen , Ryan Nemiroff , Brett T. Lopez

This paper presents a fully unsupervised deep change detection approach for mobile robots with 3D LiDAR. In unstructured environments, it is infeasible to define a closed set of semantic classes. Instead, semantic segmentation is…

Robotics · Computer Science 2024-05-01 Alexander Krawciw , Jordy Sehn , Timothy D. Barfoot

Dynamic scenes that contain both object motion and egomotion are a challenge for monocular visual odometry (VO). Another issue with monocular VO is the scale ambiguity, i.e. these methods cannot estimate scene depth and camera motion in…

Computer Vision and Pattern Recognition · Computer Science 2020-08-31 Hirak J Kashyap , Charless Fowlkes , Jeffrey L Krichmar

We consider the general class of time-homogeneous stochastic dynamical systems, both discrete and continuous, and study the problem of learning a representation of the state that faithfully captures its dynamics. This is instrumental to…

Machine Learning · Computer Science 2024-03-15 Vladimir R. Kostic , Pietro Novelli , Riccardo Grazzi , Karim Lounici , Massimiliano Pontil

Knowledge distillation has emerged as an effective strategy for compressing large language models' (LLMs) knowledge into smaller, more efficient student models. However, standard one-shot distillation methods often produce suboptimal…

Computation and Language · Computer Science 2025-04-04 Kushal Jain , Piyushi Goyal , Kumar Shridhar