Related papers: SePaint: Semantic Map Inpainting via Multinomial D…
Image inpainting is an ill-posed problem to recover missing or damaged image content based on incomplete images with masks. Previous works usually predict the auxiliary structures (e.g., edges, segmentation and contours) to help fill…
Accurate modeling of robot dynamics is essential for model-based control, yet remains challenging under distributional shifts and real-time constraints. In this work, we formulate system identification as an in-context meta-learning problem…
Localization is an essential task for mobile autonomous robotic systems that want to use pre-existing maps or create new ones in the context of SLAM. Today, many robotic platforms are equipped with high-accuracy 3D LiDAR sensors, which…
The ability to endow maps of indoor scenes with semantic information is an integral part of robotic agents which perform different tasks such as target driven navigation, object search or object rearrangement. The state-of-the-art methods…
Inpainting is a learned interpolation technique that is based on generative modeling and used to populate masked or missing pieces in an image; it has wide applications in picture editing and retouching. Recently, inpainting started being…
Diffusion models are now the undisputed state-of-the-art for image generation and image restoration. However, they require large amounts of computational power for training and inference. In this paper, we propose lightweight diffusion…
In order to operate in human environments, a robot's semantic perception has to overcome open-world challenges such as novel objects and domain gaps. Autonomous deployment to such environments therefore requires robots to update their…
Human perception is structured around objects which form the basis for our higher-level cognition and impressive systematic generalization abilities. Yet most work on representation learning focuses on feature learning without even…
Drivers' visual attention provides critical cues for anticipating latent hazards and directly shapes decision-making and control maneuvers, where its absence can compromise traffic safety. To emulate drivers' perception patterns and advance…
Denoising diffusion probabilistic models have recently received much research attention since they outperform alternative approaches, such as GANs, and currently provide state-of-the-art generative performance. The superior performance of…
Spurious features associated with class labels can lead image classifiers to rely on shortcuts that don't generalize well to new domains. This is especially problematic in medical settings, where biased models fail when applied to different…
This paper presents a distributed painting algorithm for painting a priori known rectangular region by swarm of autonomous mobile robots. We assume that the region is obstacle free and of rectangular in shape. The basic approach is to…
Radiance field methods, such as Neural Radiance Field or 3D Gaussian Splatting, have emerged as seminal 3D representations for synthesizing realistic novel views. For practical applications, there is ongoing research on flexible scene…
Precise and accurate predictions over boundary areas are essential for semantic segmentation. However, the commonly-used convolutional operators tend to smooth and blur local detail cues, making it difficult for deep models to generate…
Facial Image inpainting aim is to restore the missing or corrupted regions in face images while preserving identity, structural consistency and photorealistic image quality, a task specifically created for photo restoration. Though there…
In web data, product images are central to boosting user engagement and advertising efficacy on e-commerce platforms, yet the intrusive elements such as watermarks and promotional text remain major obstacles to delivering clear and…
Robots deployed in real-world environments, such as homes, must not only navigate safely but also understand their surroundings and adapt to changes in the environment. To perform tasks efficiently, they must build and maintain a semantic…
Online scene perception and topology reasoning are critical for autonomous vehicles to understand their driving environments, particularly for mapless driving systems that endeavor to reduce reliance on costly High-Definition (HD) maps.…
Autonomous navigation and exploration in unmapped environments remains a significant challenge in robotics due to the difficulty robots face in making commonsense inference of unobserved geometries. Recent advancements have demonstrated…
Awareness of the road scene is an essential component for both autonomous vehicles and Advances Driver Assistance Systems and is gaining importance both for the academia and car companies. This paper presents a way to learn a semantic-aware…