Related papers: Collision Replay: What Does Bumping Into Things Te…
This paper introduces a novel benchmark to study the impact and relationship of built environment elements on pedestrian collision prediction, intending to enhance environmental awareness in autonomous driving systems to prevent pedestrian…
While deep neural networks have led to human-level performance on computer vision tasks, they have yet to demonstrate similar gains for holistic scene understanding. In particular, 3D context has been shown to be an extremely important cue…
In autonomous driving applications a critical challenge is to identify action to take to avoid an obstacle on collision course. For example, when a heavy object is suddenly encountered it is critical to stop the vehicle or change the lane…
The common pipeline in autonomous driving systems is highly modular and includes a perception component which extracts lists of surrounding objects and passes these lists to a high-level decision component. In this case, leveraging the…
We present a lightweight network that infers grouping and boundaries, including curves, corners and junctions. It operates in a bottom-up fashion, analogous to classical methods for sub-pixel edge localization and edge-linking, but with a…
Consider scene understanding problems such as predicting where a person is probably reaching, or inferring the pose of 3D objects from depth images, or inferring the probable street crossings of pedestrians at a busy intersection. This…
In-context learning$\unicode{x2013}$the ability to configure a model's behavior with different prompts$\unicode{x2013}$has revolutionized the field of natural language processing, alleviating the need for task-specific models and paving the…
Dynamic scene understanding is an essential capability in robotics and VR/AR. In this paper we propose Co-Section, an optimization-based approach to 3D dynamic scene reconstruction, which infers hidden shape information from intersection…
Scene recognition is currently one of the top-challenging research fields in computer vision. This may be due to the ambiguity between classes: images of several scene classes may share similar objects, which causes confusion among them.…
Temporal correspondence - linking pixels or objects across frames - is a fundamental supervisory signal for the video models. For the panoptic understanding of dynamic scenes, we further extend this concept to every segment. Specifically,…
Forecasting the future traffic flow distribution in an area is an important issue for traffic management in an intelligent transportation system. The key challenge of traffic prediction is to capture spatial and temporal relations between…
Inverse rendering aims to estimate physical attributes of a scene, e.g., reflectance, geometry, and lighting, from image(s). Inverse rendering has been studied primarily for single objects or with methods that solve for only one of the…
Indoor scene synthesis involves automatically picking and placing furniture appropriately on a floor plan, so that the scene looks realistic and is functionally plausible. Such scenes can serve as homes for immersive 3D experiences, or be…
Spatial perception aims to estimate camera motion and scene structure from visual observations, a problem traditionally addressed through geometric modeling and physical consistency constraints. Recent learning-based methods have…
Image retrieval relies heavily on the quality of the data modeling and the distance measurement in the feature space. Building on the concept of image manifold, we first propose to represent the feature space of images, learned via neural…
Collision avoidance systems play a vital role in reducing the number of vehicle accidents and saving human lives. This paper extends the previous work using evolutionary neural networks for reactive collision avoidance. We are proposing a…
Machine understanding of complex images is a key goal of artificial intelligence. One challenge underlying this task is that visual scenes contain multiple inter-related objects, and that global context plays an important role in…
Sampling-based motion planning is a popular approach in robotics for finding paths in continuous configuration spaces. Checking collision with obstacles is the major computational bottleneck in this process. We propose new learning-based…
Neural reconstruction approaches are rapidly emerging as the preferred representation for 3D scenes, but their limited editability is still posing a challenge. In this work, we propose an approach for 3D scene inpainting -- the task of…
Temporal interpolation often plays a crucial role to learn meaningful representations in dynamic scenes. In this paper, we propose a novel method to train spatiotemporal neural radiance fields of dynamic scenes based on temporal…