Related papers: Uplifting Table Tennis: A Robust, Real-World Appli…

While LLMs excel at single-turn generation, they struggle with long-horizon, multi-turn interactions. Offline reinforcement learning (RL) offers a scalable approach, yet its performance hinges on the availability and quality of multi-turn…

Data augmentation has emerged as a powerful technique in machine learning, strengthening model robustness while mitigating overfitting and under-fitting issues by generating diverse synthetic data. Nevertheless, despite its success in other…

Musculoskeletal robots provide superior advantages in flexibility and dexterity, positioning them as a promising frontier towards embodied intelligence. However, current research is largely confined to relative simple tasks, restricting the…

To approach the level of advanced human players in table tennis with robots, generating varied ball trajectories in a reproducible and controlled manner is essential. Current ball launchers used in robot table tennis either do not provide…

This paper presents TubeBEND, a real-world dataset comprising 318 rotary tube bending processes, which were collected and sorted by experts from various fields to evaluate machine learning and signal analysis methods. The dataset addresses…

To date, little attention has been given to multi-view 3D human mesh estimation, despite real-life applicability (e.g., motion capture, sport analysis) and robustness to single-view ambiguities. Existing solutions typically suffer from poor…

Single-view 3D shape retrieval is a challenging task that is increasingly important with the growth of available 3D data. Prior work that has studied this task has not focused on evaluating how realistic occlusions impact performance, and…

High-quality novel view synthesis (NVS) from real-world videos is crucial for applications such as cultural heritage preservation, digital twins, and immersive media. However, real-world videos typically contain long sequences with…

Multi-view 3D reconstruction remains a core challenge in computer vision. Recent methods, such as DUST3R and its successors, directly regress pointmaps from image pairs without relying on known scene geometry or camera parameters. However,…

Creating deformable 3D content has gained increasing attention with the rise of text-to-image and image-to-video generative models. While these models provide rich semantic priors for appearance, they struggle to capture the physical…

The great advances of learning-based approaches in image processing and computer vision are largely based on deeply nested networks that compose linear transfer functions with suitable non-linearities. Interestingly, the most frequently…

This paper tackles the challenging task of 3D visual grounding-locating a specific object in a 3D point cloud scene based on text descriptions. Existing methods fall into two categories: top-down and bottom-up methods. Top-down methods rely…

Training data is a critical requirement for machine learning tasks, and labeled training data can be expensive to acquire, often requiring manual or semi-automated data collection pipelines. For tracking applications, the data collection…

Keypoint-based representation has proven advantageous in various visual and robotic tasks. However, the existing 2D and 3D methods for detecting keypoints mainly rely on geometric consistency to achieve spatial alignment, neglecting…

Confronting the critical challenge of insufficient training data in the field of complex image recognition, this paper introduces a novel 3D viewpoint augmentation technique specifically tailored for wine label recognition. This method…

Deep learning-based food image classification enables precise identification of food categories, further facilitating accurate nutritional analysis. However, real-world food images often show a skewed distribution, with some food types…

Datasets are essential to train and evaluate computer vision models used for traffic analysis and to enhance road safety. Existing real datasets fit real-world scenarios, capturing authentic road object behaviors, however, they typically…

The spinal angle is an important indicator of body balance. It is important to restore the 3D shape of the human body and estimate the spine center line. Existing mul-ti-image-based body restoration methods require expensive equipment and…

We propose a learning-based method to reconstruct the local terrain for locomotion with a mobile robot traversing urban environments. Using a stream of depth measurements from the onboard cameras and the robot's trajectory, the algorithm…

3D pose estimation is an invaluable task in computer vision with various practical applications. Especially, 3D pose estimation for multi-person from a monocular video (3DMPPE) is particularly challenging and is still largely uncharted, far…