Related papers: OccFeat: Self-supervised Occupancy Feature Predict…

3D scene flow estimation is a vital tool in perceiving our environment given depth or range sensors. Unlike optical flow, the data is usually sparse and in most cases partially occluded in between two temporal samplings. Here we propose a…

Identifying oculomotor behaviors relevant for eye-tracking applications is a critical but often challenging task. Aiming to automatically learn and extract knowledge from existing eye-tracking data, we develop a novel method that creates…

Bird's-eye-view (BEV) grid is a common representation for the perception of road components, e.g., drivable area, in autonomous driving. Most existing approaches rely on cameras only to perform segmentation in BEV space, which is…

Recent deep learning models achieve impressive results on 3D scene analysis tasks by operating directly on unstructured point clouds. A lot of progress was made in the field of object classification and semantic segmentation. However, the…

Ego-motion estimation is vital for drones when flying in GPS-denied environments. Vision-based methods struggle when flight speed increases and close-by objects lead to difficult visual conditions with considerable motion blur and large…

In this paper, we study the task of facial expression recognition under strong occlusion. We are particularly interested in cases where 50% of the face is occluded, e.g. when the subject wears a Virtual Reality (VR) headset. While previous…

Pre-training techniques play a crucial role in deep learning, enhancing models' performance across a variety of tasks. By initially training on large datasets and subsequently fine-tuning on task-specific data, pre-training provides a solid…

3D occupancy, an advanced perception technology for driving scenarios, represents the entire scene without distinguishing between foreground and background by quantifying the physical space into a grid map. The widely adopted…

In the landscape of autonomous driving, Bird's-Eye-View (BEV) representation has recently garnered substantial academic attention, serving as a transformative framework for the fusion of multi-modal sensor inputs. This BEV paradigm…

Self-supervised learning, a.k.a., pretraining, is important in natural language processing. Most of the pretraining methods first randomly mask some positions in a sentence and then train a model to recover the tokens at the masked…

3D semantic occupancy prediction requires accurate 2D-to-3D feature lifting, yet current methods restrict camera geometry to initial projections. Subsequent operations like offset learning, attention weighting, and cross-camera aggregation…

Determining accurate bird's eye view (BEV) positions of objects and tracks in a scene is vital for various perception tasks including object interactions mapping, scenario extraction etc., however, the level of supervision required to…

Visual bird's eye view (BEV) perception, due to its excellent perceptual capabilities, is progressively replacing costly LiDAR-based perception systems, especially in the realm of urban intelligent driving. However, this type of perception…

3D semantic occupancy prediction is a pivotal task in autonomous driving, providing a dense and fine-grained understanding of the surrounding environment, yet single-modality methods face trade-offs between camera semantics and LiDAR…

Trajectory prediction is, naturally, a key task for vehicle autonomy. While the number of traffic rules is limited, the combinations and uncertainties associated with each agent's behaviour in real-world scenarios are nearly impossible to…

Bird's-eye-view (BEV) grid is a typical representation of the perception of road components, e.g., drivable area, in autonomous driving. Most existing approaches rely on cameras only to perform segmentation in BEV space, which is…

Vision-based perception for autonomous driving requires an explicit modeling of a 3D space, where 2D latent representations are mapped and subsequent 3D operators are applied. However, operating on dense latent spaces introduces a cubic…

Optical coherence tomography (OCT) is a commonly-used method of extracting high resolution retinal information. Moreover there is an increasing demand for the automated retinal layer segmentation which facilitates the retinal disease…

3D occupancy prediction holds significant promise in the fields of robot perception and autonomous driving, which quantifies 3D scenes into grid cells with semantic labels. Recent works mainly utilize complete occupancy labels in 3D voxel…

3D object detection in Bird's-Eye-View (BEV) space has recently emerged as a prevalent approach in the field of autonomous driving. Despite the demonstrated improvements in accuracy and velocity estimation compared to perspective view…