Related papers: ADAPT: Adaptive Dual-projection Architecture for P…
Effectively measuring the similarity between two human motions is necessary for several computer vision tasks such as gait analysis, person identi- fication and action retrieval. Nevertheless, we believe that traditional approaches such as…
The detector-free feature matching approaches are currently attracting great attention thanks to their excellent performance. However, these methods still struggle at large-scale and viewpoint variations, due to the geometric inconsistency…
Recent feed-forward 3D reconstruction methods, such as visual geometry transformers, have substantially advanced the traditional per-scene optimization paradigm by enabling effective multi-view reconstruction in a single forward pass.…
Modern-day autonomous robots need high-level map representations to perform sophisticated tasks. Recently, 3D scene graphs (3DSGs) have emerged as a promising alternative to traditional grid maps, blending efficient memory use and rich…
Reliable perception and efficient adaptation to novel conditions are priority skills for humanoids that function in dynamic environments. The vast advancements in latest computer vision research, brought by deep learning methods, are…
Traversing 3-D complex environments has always been a significant challenge for legged locomotion. Existing methods typically rely on external sensors such as vision and lidar to preemptively react to obstacles by acquiring environmental…
Capturing the interactions between humans and their environment in 3D is important for many applications in robotics, graphics, and vision. Recent works to reconstruct the 3D human and object from a single RGB image do not have consistent…
We introduce a high resolution spatially adaptive light source, or a projector, into a neural reflectance field that allows to both calibrate the projector and photo realistic light editing. The projected texture is fully differentiable…
Skeleton-based human action recognition has recently attracted increasing attention thanks to the accessibility and the popularity of 3D skeleton data. One of the key challenges in skeleton-based action recognition lies in the large view…
Assistive teleoperation enhances efficiency via shared control, yet inter-operator variability, stemming from diverse habits and expertise, induces highly heterogeneous trajectory distributions that undermine intent recognition stability.…
Three-dimensional (3D) object recognition is crucial for intelligent autonomous agents such as autonomous vehicles and robots alike to operate effectively in unstructured environments. Most state-of-art approaches rely on relatively dense…
Achieving robust humanoid hiking in complex, unstructured environments requires transitioning from reactive proprioception to proactive perception. However, integrating exteroception remains a significant challenge: mapping-based methods…
Multi-object tracking (MOT) in monocular videos is fundamentally challenged by occlusions and depth ambiguity, issues that conventional tracking-by-detection (TBD) methods struggle to resolve owing to a lack of geometric awareness. To…
Modern machine learning models typically represent inputs as fixed points in a high-dimensional embedding space. While this approach has been proven powerful for a wide range of downstream tasks, it fundamentally differs from the way humans…
Detecting visual relationships, i.e. <Subject, Predicate, Object> triplets, is a challenging Scene Understanding task approached in the past via linguistic priors or spatial information in a single feature branch. We introduce a new deeply…
Prompt learning has recently become a very efficient transfer learning paradigm for Contrastive Language Image Pretraining (CLIP) models. Compared with fine-tuning the entire encoder, prompt learning can obtain highly competitive results by…
Knowledge of terrain's physical properties inferred from color images can aid in making efficient robotic locomotion plans. However, unlike image classification, it is unintuitive for humans to label image patches with physical properties.…
Cooperative perception is the key approach to augment the perception of connected and automated vehicles (CAVs) toward safe autonomous driving. However, it is challenging to achieve real-time perception sharing for hundreds of CAVs in…
Despite the progress in legged robotic locomotion, autonomous navigation in unknown environments remains an open problem. Ideally, the navigation system utilizes the full potential of the robots' locomotion capabilities while operating…
As both legged robots and embedded compute have become more capable, researchers have started to focus on field deployment of these robots. Robust autonomy in unstructured environments requires perception of the world around the robot in…