Adverse weather conditions, particularly heavy snowfall, pose significant challenges to both human drivers and autonomous vehicles. Traditional image-based desnowing methods often introduce hallucination artifacts as they rely solely on spatial information, while video-based approaches require high frame rates and suffer from alignment artifacts at lower frame rates. Camera parameters, such as exposure time, also influence the appearance of snowflakes, making the problem difficult to solve and heavily dependent on network generalization. In this paper, we propose to address the challenge of desnowing by using event cameras, which offer compressed visual information with submillisecond latency, making them ideal for desnowing images, even in the presence of ego-motion. Our method leverages the fact that snowflake occlusions appear with a very distinctive streak signature in the spatiotemporal representation of event data. We design an attention-based module that focuses on events along these streaks to determine when a background point was occluded and use this information to recover its original intensity. We benchmark our method on DSEC-Snow, a new dataset created using a green-screen technique that overlays pre-recorded snowfall data onto the existing DSEC driving dataset, resulting in precise ground truth and synchronized image and event streams. Our approach outperforms state-of-the-art desnowing methods by 3 dB in PSNR for image reconstruction. Moreover, we show that off-the-shelf computer vision algorithms can be applied to our reconstructions for tasks such as depth estimation and optical flow, achieving a 20% performance improvement over other desnowing methods. Our work represents a crucial step towards enhancing the reliability and safety of vision systems in challenging winter conditions, paving the way for more robust, all-weather-capable applications.

Imitation learning with a privileged teacher has proven effective for learning complex control behaviors from high-dimensional inputs, such as images. In this framework, a teacher is trained with privileged task information, while a student tries to predict the actions of the teacher with more limited observations, e.g., in a robot navigation task, the teacher might have access to distances to nearby obstacles, while the student only receives visual observations of the scene. However, privileged imitation learning faces a key challenge: the student might be unable to imitate the teacher's behavior due to partial observability. This problem arises because the teacher is trained without considering if the student is capable of imitating the learned behavior. To address this teacher-student asymmetry, we propose a framework for joint training of the teacher and student policies, encouraging the teacher to learn behaviors that can be imitated by the student despite the latters' limited access to information and its partial observability. Based on the performance bound in imitation learning, we add (i) the approximated action difference between teacher and student as a penalty term to the reward function of the teacher, and (ii) a supervised teacher-student alignment step. We motivate our method with a maze navigation task and demonstrate its effectiveness on complex vision-based quadrotor flight and manipulation tasks.

Reinforcement learning (RL) has achieved outstanding success in complex robot control tasks, such as drone racing, where the RL agents have outperformed human champions in a known racing track. However, these agents fail in unseen track configurations, always requiring complete retraining when presented with new track layouts. This work aims to develop RL agents that generalize effectively to novel track configurations without retraining. The naïve solution of training directly on a diverse set of track layouts can overburden the agent, resulting in suboptimal policy learning as the increased complexity of the environment impairs the agent's ability to learn to fly. To enhance the generalizability of the RL agent, we propose an adaptive environment-shaping framework that dynamically adjusts the training environment based on the agent's performance. We achieve this by leveraging a secondary RL policy to design environments that strike a balance between being challenging and achievable, allowing the agent to adapt and improve progressively. Using our adaptive environment shaping, one single racing policy efficiently learns to race in diverse challenging tracks. Experimental results validated in both simulation and the real world show that our method enables drones to successfully fly complex and unseen race tracks, outperforming existing environment-shaping techniques. Website: http://rpg.ifi.uzh.ch/env_as_policy.

Because of their high temporal resolution, increased resilience to motion blur, and very sparse output, event cameras have been shown to be ideal for low-latency and low-bandwidth feature tracking, even in challenging scenarios. Existing feature tracking methods for event cameras are either handcrafted or derived from first principles but require extensive parameter tuning, are sensitive to noise, and do not generalize to different scenarios due to unmodeled effects. To tackle these deficiencies, we introduce the first data-driven feature tracker for event cameras, which leverages low-latency events to track features detected in an intensity frame. We achieve robust performance via a novel frame attention module, which shares information across feature tracks. Our tracker is designed to operate in two distinct configurations: solely with events or in a hybrid mode incorporating both events and frames. The hybrid model offers two setups: an aligned configuration where the event and frame cameras share the same viewpoint, and a hybrid stereo configuration where the event camera and the standard camera are positioned side-by-side. This side-by-side arrangement is particularly valuable as it provides depth information for each feature track, enhancing its utility in applications such as visual odometry and simultaneous localization and mapping.

In Reinforcement Learning, the trade-off between exploration and exploitation poses a complex challenge for achieving efficient learning from limited samples. While recent works have been effective in leveraging past experiences for policy updates, they often overlook the potential of reusing past experiences for data collection. Independent of the underlying RL algorithm, we introduce the concept of a Contrastive Initial State Buffer, which strategically selects states from past experiences and uses them to initialize the agent in the environment in order to guide it toward more informative states. We validate our approach on two complex robotic tasks without relying on any prior information about the environment: (i) locomotion of a quadruped robot traversing challenging terrains and (ii) a quadcopter drone racing through a track. The experimental results show that our initial state buffer achieves higher task performance than the nominal baseline while also speeding up training convergence.

Vision Transformers (ViTs) have shown impressive performance in computer vision, but their high computational cost, quadratic in the number of tokens, limits their adoption in computation-constrained applications. However, this large number of tokens may not be necessary, as not all tokens are equally important. In this paper, we investigate token pruning to accelerate inference for object detection and instance segmentation, extending prior works from image classification. Through extensive experiments, we offer four insights for dense tasks: (i) tokens should not be completely pruned and discarded, but rather preserved in the feature maps for later use. (ii) reactivating previously pruned tokens can further enhance model performance. (iii) a dynamic pruning rate based on images is better than a fixed pruning rate. (iv) a lightweight, 2-layer MLP can effectively prune tokens, achieving accuracy comparable with complex gating networks with a simpler design. We assess the effects of these design decisions on the COCO dataset and introduce an approach that incorporates these findings, showing a reduction in performance decline from ∼1.5 mAP to ∼0.3 mAP in both boxes and masks, compared to existing token pruning methods. In relation to the dense counterpart that utilizes all tokens, our method realizes an increase in inference speed, achieving up to 34% faster performance for the entire network and 46% for the backbone. Code: https://github.com/uzh-rpg/svit/

Because of their high temporal resolution, increased resilience to motion blur, and very sparse output, event cameras have been shown to be ideal for low-latency and low-bandwidth feature tracking, even in challenging scenarios. Existing feature tracking methods for event cameras are either handcrafted or derived from first principles but require extensive parameter tuning, are sensitive to noise, and do not generalize to different scenarios due to unmodeled effects. To tackle these deficiencies, we introduce the first data-driven feature tracker for event cameras, which leverages low-latency events to track features detected in a grayscale frame. We achieve robust performance via a novel frame attention module, which shares information across feature tracks. By directly transferring zero-shot from synthetic to real data, our data-driven tracker outperforms existing approaches in relative feature age by up to 120 % while also achieving the lowest latency. This performance gap is further increased to 130 % by adapting our tracker to real data with a novel self-supervision strategy. Multimedia Material A video is available at https://youtu.be/dtkXvNXcWRY and code at https://github.com/uzh-rpg/deep_ev_tracker