Cornelia Fermüller

Bharatesh Chakravarthi, Aayush Atul Verma, Kostas Daniilidis et al.

Event-based vision, inspired by the human visual system, offers transformative capabilities such as low latency, high dynamic range, and reduced power consumption. This paper presents a comprehensive survey of event cameras, tracing their evolution over time. It introduces the fundamental principles of event cameras, compares them with traditional frame cameras, and highlights their unique characteristics and operational differences. The survey covers various event camera models from leading manufacturers, key technological milestones, and influential research contributions. It explores diverse application areas across different domains and discusses essential real-world and synthetic datasets for research advancement. Additionally, the role of event camera simulators in testing and development is discussed. This survey aims to consolidate the current state of event cameras and inspire further innovation in this rapidly evolving field. To support the research community, a GitHub page (https://github.com/chakravarthi589/Event-based-Vision_Resources) categorizes past and future research articles and consolidates valuable resources.

Levi Burner, Anton Mitrokhin, Cornelia Fermüller et al.

A new event camera dataset, EVIMO2, is introduced that improves on the popular EVIMO dataset by providing more data, from better cameras, in more complex scenarios. As with its predecessor, EVIMO2 provides labels in the form of per-pixel ground truth depth and segmentation as well as camera and object poses. All sequences use data from physical cameras and many sequences feature multiple independently moving objects. Typically, such labeled data is unavailable in physical event camera datasets. Thus, EVIMO2 will serve as a challenging benchmark for existing algorithms and rich training set for the development of new algorithms. In particular, EVIMO2 is suited for supporting research in motion and object segmentation, optical flow, structure from motion, and visual (inertial) odometry in both monocular or stereo configurations. EVIMO2 consists of 41 minutes of data from three 640$\times$480 event cameras, one 2080$\times$1552 classical color camera, inertial measurements from two six axis inertial measurement units, and millimeter accurate object poses from a Vicon motion capture system. The dataset's 173 sequences are arranged into three categories. 3.75 minutes of independently moving household objects, 22.55 minutes of static scenes, and 14.85 minutes of basic motions in shallow scenes. Some sequences were recorded in low-light conditions where conventional cameras fail. Depth and segmentation are provided at 60 Hz for the event cameras and 30 Hz for the classical camera. The masks can be regenerated using open-source code up to rates as high as 200 Hz. This technical report briefly describes EVIMO2. The full documentation is available online. Videos of individual sequences can be sampled on the download page.

Snehesh Shrestha, Cornelia Fermüller, Tianyu Huang et al.

Pose Estimation techniques rely on visual cues available through observations represented in the form of pixels. But the performance is bounded by the frame rate of the video and struggles from motion blur, occlusions, and temporal coherence. This issue is magnified when people are interacting with objects and instruments, for example playing the violin. Standard approaches for postprocessing use interpolation and smoothing functions to filter noise and fill gaps, but they cannot model highly non-linear motion. We present a method that leverages our understanding of the high degree of a causal relationship between the sound produced and the motion that produces them. We use the audio signature to refine and predict accurate human body pose motion models. We propose MAPnet (Music Assisted Pose network) for generating a fine grain motion model from sparse input pose sequences but continuous audio. To accelerate further research in this domain, we also open-source MAPdat, a new multi-modal dataset of 3D violin playing motion with music. We perform a comparison of different standard machine learning models and perform analysis on input modalities, sampling techniques, and audio and motion features. Experiments on MAPdat suggest multi-modal approaches like ours as a promising direction for tasks previously approached with visual methods only. Our results show both qualitatively and quantitatively how audio can be combined with visual observation to help improve any pose estimation methods.

Chahat Deep Singh, Riya Kumari, Cornelia Fermüller et al.

In the era of deep learning, data is the critical determining factor in the performance of neural network models. Generating large datasets suffers from various difficulties such as scalability, cost efficiency and photorealism. To avoid expensive and strenuous dataset collection and annotations, researchers have inclined towards computer-generated datasets. Although, a lack of photorealism and a limited amount of computer-aided data, has bounded the accuracy of network predictions. To this end, we present WorldGen -- an open source framework to autonomously generate countless structured and unstructured 3D photorealistic scenes such as city view, object collection, and object fragmentation along with its rich ground truth annotation data. WorldGen being a generative model gives the user full access and control to features such as texture, object structure, motion, camera and lens properties for better generalizability by diminishing the data bias in the network. We demonstrate the effectiveness of WorldGen by presenting an evaluation on deep optical flow. We hope such a tool can open doors for future research in a myriad of domains related to robotics and computer vision by reducing manual labor and the cost of acquiring rich and high-quality data.

Daniel Deniz, Cornelia Fermuller, Eduardo Ros et al.

Neuromorphic visual sensors are artificial retinas that output sequences of asynchronous events when brightness changes occur in the scene. These sensors offer many advantages including very high temporal resolution, no motion blur and smart data compression ideal for real-time processing. In this study, we introduce an event-based dataset on fine-grained manipulation actions and perform an experimental study on the use of transformers for action prediction with events. There is enormous interest in the fields of cognitive robotics and human-robot interaction on understanding and predicting human actions as early as possible. Early prediction allows anticipating complex stages for planning, enabling effective and real-time interaction. Our Transformer network uses events to predict manipulation actions as they occur, using online inference. The model succeeds at predicting actions early on, building up confidence over time and achieving state-of-the-art classification. Moreover, the attention-based transformer architecture allows us to study the role of the spatio-temporal patterns selected by the model. Our experiments show that the Transformer network captures action dynamic features outperforming video-based approaches and succeeding with scenarios where the differences between actions lie in very subtle cues. Finally, we release the new event dataset, which is the first in the literature for manipulation action recognition. Code will be available at https://github.com/DaniDeniz/EventVisionTransformer.

Jingxi Chen, Yixiao Zhang, Xiaoye Qian et al.

Images can be viewed as layered compositions, foreground objects over background, with potential occlusions. This layered representation enables independent editing of elements, offering greater flexibility for content creation. Despite the progress in large generative models, decomposing a single image into layers remains challenging due to limited methods and data. We observe a strong connection between layer decomposition and in/outpainting tasks, and propose adapting a diffusion-based inpainting model for layer decomposition using lightweight finetuning. To further preserve detail in the latent space, we introduce a novel multi-modal context fusion module with linear attention complexity. Our model is trained purely on a synthetic dataset constructed from open-source assets and achieves superior performance in object removal and occlusion recovery, unlocking new possibilities in downstream editing and creative applications.

Anthony Zador, Jean-Marc Fellous, Terrence Sejnowski et al. · uw

Neuroscience and Artificial Intelligence (AI) have made impressive progress in recent years but remain only loosely interconnected. Based on a workshop convened by the National Science Foundation in August 2025, we identify three fundamental capability gaps in current AI: the inability to interact with the physical world, inadequate learning that produces brittle systems, and unsustainable energy and data inefficiency. We describe the neuroscience principles that address each: co-design of body and controller, prediction through interaction, multi-scale learning with neuromodulatory control, hierarchical distributed architectures, and sparse event-driven computation. We present a research roadmap organized around these principles at near, mid, and long-term horizons. We argue that realizing this program requires a new generation of researchers trained across the boundary between neuroscience and engineering, and describe the institutional conditions: interdisciplinary training, hardware access, community standards, and ethics, needed to support them. We conclude that NeuroAI, neuroscience-informed artificial intelligence, has the potential to overcome limitations of current AI while deepening our understanding of biological neural computation.

Michael Maynord, Minghui Liu, Cornelia Fermüller et al.

Ultra-high field 7-tesla (7T) MRI improves visualization of multiple sclerosis (MS) white matter lesions (WML) but differs sufficiently in contrast and artifacts from 1.5-3T imaging - suggesting that widely used automated segmentation tools may not translate directly. We analyzed 7T FLAIR scans and generated reference WML masks from Lesion Segmentation Tool (LST) outputs followed by expert manual revision. As external comparators, we applied LST-LPA and the more recent LST-AI ensemble, both originally developed on lower-field data. We then trained 3D UNETR and SegFormer transformer-based models on 7T FLAIR at multiple resolutions (0.5x0.5x0.5^3, 1.0x1.0x1.0^3, and 1.5x1.5x2.0^3) and evaluated all methods using voxel-wise and lesion-wise metrics from the BraTS 2023 framework. On the held-out test set at native 0.5x0.5x0.5^3 resolution, 7T-trained transformers achieved competitive overlap with LST-AI while recovering additional small lesions that were missed by classical methods, at the cost of some boundary variability and occasional artifact-related false positives. On a held-out 7 T test set, our best transformer model (SegFormer) achieved a voxel-wise Dice of 0.61 and lesion-wise Dice of 0.20, improving on the classical LST-LPA tool (Dice 0.39, lesion-wise Dice 0.02). Performance decreased for models trained on downsampled images, underscoring the value of native 7T resolution for small-lesion detection. By releasing our 7T-trained models, we aim to provide a reproducible, ready-to-use resource for automated lesion quantification in ultra-high field MS research (https://github.com/maynord/7T-MS-lesion-segmentation).

Chethan M. Parameshwara, Gokul Hari, Cornelia Fermüller et al.

Current deep neural network approaches for camera pose estimation rely on scene structure for 3D motion estimation, but this decreases the robustness and thereby makes cross-dataset generalization difficult. In contrast, classical approaches to structure from motion estimate 3D motion utilizing optical flow and then compute depth. Their accuracy, however, depends strongly on the quality of the optical flow. To avoid this issue, direct methods have been proposed, which separate 3D motion from depth estimation but compute 3D motion using only image gradients in the form of normal flow. In this paper, we introduce a network NFlowNet, for normal flow estimation which is used to enforce robust and direct constraints. In particular, normal flow is used to estimate relative camera pose based on the cheirality (depth positivity) constraint. We achieve this by formulating the optimization problem as a differentiable cheirality layer, which allows for end-to-end learning of camera pose. We perform extensive qualitative and quantitative evaluation of the proposed DiffPoseNet's sensitivity to noise and its generalization across datasets. We compare our approach to existing state-of-the-art methods on KITTI, TartanAir, and TUM-RGBD datasets.

Amir-Hossein Shahidzadeh, Seong Jong Yoo, Pavan Mantripragada et al.

Tactile exploration plays a crucial role in understanding object structures for fundamental robotics tasks such as grasping and manipulation. However, efficiently exploring such objects using tactile sensors is challenging, primarily due to the large-scale unknown environments and limited sensing coverage of these sensors. To this end, we present AcTExplore, an active tactile exploration method driven by reinforcement learning for object reconstruction at scales that automatically explores the object surfaces in a limited number of steps. Through sufficient exploration, our algorithm incrementally collects tactile data and reconstructs 3D shapes of the objects as well, which can serve as a representation for higher-level downstream tasks. Our method achieves an average of 95.97% IoU coverage on unseen YCB objects while just being trained on primitive shapes. Project Webpage: https://prg.cs.umd.edu/AcTExplore

Peter Sutor, Dehao Yuan, Douglas Summers-Stay et al.

Hyperdimensional Computing affords simple, yet powerful operations to create long Hyperdimensional Vectors (hypervectors) that can efficiently encode information, be used for learning, and are dynamic enough to be modified on the fly. In this paper, we explore the notion of using binary hypervectors to directly encode the final, classifying output signals of neural networks in order to fuse differing networks together at the symbolic level. This allows multiple neural networks to work together to solve a problem, with little additional overhead. Output signals just before classification are encoded as hypervectors and bundled together through consensus summation to train a classification hypervector. This process can be performed iteratively and even on single neural networks by instead making a consensus of multiple classification hypervectors. We find that this outperforms the state of the art, or is on a par with it, while using very little overhead, as hypervector operations are extremely fast and efficient in comparison to the neural networks. This consensus process can learn online and even grow or lose models in real time. Hypervectors act as memories that can be stored, and even further bundled together over time, affording life long learning capabilities. Additionally, this consensus structure inherits the benefits of Hyperdimensional Computing, without sacrificing the performance of modern Machine Learning. This technique can be extrapolated to virtually any neural model, and requires little modification to employ - one simply requires recording the output signals of networks when presented with a testing example.

Eadom Dessalene, Michael Maynord, Cornelia Fermuller et al.

In this paper we introduce a rule-based, compositional, and hierarchical modeling of action using Therbligs as our atoms. Introducing these atoms provides us with a consistent, expressive, contact-centered representation of action. Over the atoms we introduce a differentiable method of rule-based reasoning to regularize for logical consistency. Our approach is complementary to other approaches in that the Therblig-based representations produced by our architecture augment rather than replace existing architectures' representations. We release the first Therblig-centered annotations over two popular video datasets - EPIC Kitchens 100 and 50-Salads. We also broadly demonstrate benefits to adopting Therblig representations through evaluation on the following tasks: action segmentation, action anticipation, and action recognition - observing an average 10.5\%/7.53\%/6.5\% relative improvement, respectively, over EPIC Kitchens and an average 8.9\%/6.63\%/4.8\% relative improvement, respectively, over 50 Salads. Code and data will be made publicly available.

Jingxi Chen, Botao He, Chahat Deep Singh et al.

One of the core activities of an active observer involves moving to secure a "better" view of the scene, where the definition of "better" is task-dependent. This paper focuses on the task of human pose estimation from videos capturing a person's activity. Self-occlusions within the scene can complicate or even prevent accurate human pose estimation. To address this, relocating the camera to a new vantage point is necessary to clarify the view, thereby improving 2D human pose estimation. This paper formalizes the process of achieving an improved viewpoint. Our proposed solution to this challenge comprises three main components: a NeRF-based Drone-View Data Generation Framework, an On-Drone Network for Camera View Error Estimation, and a Combined Planner for devising a feasible motion plan to reposition the camera based on the predicted errors for camera views. The Data Generation Framework utilizes NeRF-based methods to generate a comprehensive dataset of human poses and activities, enhancing the drone's adaptability in various scenarios. The Camera View Error Estimation Network is designed to evaluate the current human pose and identify the most promising next viewing angles for the drone, ensuring a reliable and precise pose estimation from those angles. Finally, the combined planner incorporates these angles while considering the drone's physical and environmental limitations, employing efficient algorithms to navigate safe and effective flight paths. This system represents a significant advancement in active 2D human pose estimation for an autonomous UAV agent, offering substantial potential for applications in aerial cinematography by improving the performance of autonomous human pose estimation and maintaining the operational safety and efficiency of UAVs.

Levi Burner, Nitin J. Sanket, Cornelia Fermüller et al.

Distance estimation from vision is fundamental for a myriad of robotic applications such as navigation, manipulation, and planning. Inspired by the mammal's visual system, which gazes at specific objects, we develop two novel constraints relating time-to-contact, acceleration, and distance that we call the $τ$-constraint and $Φ$-constraint. They allow an active (moving) camera to estimate depth efficiently and accurately while using only a small portion of the image. The constraints are applicable to range sensing, sensor fusion, and visual servoing. We successfully validate the proposed constraints with two experiments. The first applies both constraints in a trajectory estimation task with a monocular camera and an Inertial Measurement Unit (IMU). Our methods achieve 30-70% less average trajectory error while running 25$\times$ and 6.2$\times$ faster than the popular Visual-Inertial Odometry methods VINS-Mono and ROVIO respectively. The second experiment demonstrates that when the constraints are used for feedback with efference copies the resulting closed loop system's eigenvalues are invariant to scaling of the applied control signal. We believe these results indicate the $τ$ and $Φ$ constraint's potential as the basis of robust and efficient algorithms for a multitude of robotic applications.

Dehao Yuan, Furong Huang, Cornelia Fermüller et al.

We propose Hyper-Dimensional Function Encoding (HDFE). Given samples of a continuous object (e.g. a function), HDFE produces an explicit vector representation of the given object, invariant to the sample distribution and density. Sample distribution and density invariance enables HDFE to consistently encode continuous objects regardless of their sampling, and therefore allows neural networks to receive continuous objects as inputs for machine learning tasks, such as classification and regression. Besides, HDFE does not require any training and is proved to map the object into an organized embedding space, which facilitates the training of the downstream tasks. In addition, the encoding is decodable, which enables neural networks to regress continuous objects by regressing their encodings. Therefore, HDFE serves as an interface for processing continuous objects. We apply HDFE to function-to-function mapping, where vanilla HDFE achieves competitive performance as the state-of-the-art algorithm. We apply HDFE to point cloud surface normal estimation, where a simple replacement from PointNet to HDFE leads to immediate 12% and 15% error reductions in two benchmarks. In addition, by integrating HDFE into the PointNet-based SOTA network, we improve the SOTA baseline by 2.5% and 1.7% in the same benchmarks.

Eadom Dessalene, Michael Maynord, Cornelia Fermüller et al.

We introduce LEAP (illustrated in Figure 1), a novel method for generating video-grounded action programs through use of a Large Language Model (LLM). These action programs represent the motoric, perceptual, and structural aspects of action, and consist of sub-actions, pre- and post-conditions, and control flows. LEAP's action programs are centered on egocentric video and employ recent developments in LLMs both as a source for program knowledge and as an aggregator and assessor of multimodal video information. We apply LEAP over a majority (87\%) of the training set of the EPIC Kitchens dataset, and release the resulting action programs as a publicly available dataset here (https://drive.google.com/drive/folders/1Cpkw_TI1IIxXdzor0pOXG3rWJWuKU5Ex?usp=drive_link). We employ LEAP as a secondary source of supervision, using its action programs in a loss term applied to action recognition and anticipation networks. We demonstrate sizable improvements in performance in both tasks due to training with the LEAP dataset. Our method achieves 1st place on the EPIC Kitchens Action Recognition leaderboard as of November 17 among the networks restricted to RGB-input (see Supplementary Materials).

Matthew Evanusa, Cornelia Fermüller, Yiannis Aloimonos

Artificial Neural Networks has struggled to devise a way to incorporate working memory into neural networks. While the ``long term'' memory can be seen as the learned weights, the working memory consists likely more of dynamical activity, that is missing from feed-forward models. Current state of the art models such as transformers tend to ``solve'' this by ignoring working memory entirely and simply process the sequence as an entire piece of data; however this means the network cannot process the sequence in an online fashion, and leads to an immense explosion in memory requirements. Here, inspired by a combination of controls, reservoir computing, deep learning, and recurrent neural networks, we offer an alternative paradigm that combines the strength of recurrent networks, with the pattern matching capability of feed-forward neural networks, which we call the \textit{Maelstrom Networks} paradigm. This paradigm leaves the recurrent component - the \textit{Maelstrom} - unlearned, and offloads the learning to a powerful feed-forward network. This allows the network to leverage the strength of feed-forward training without unrolling the network, and allows for the memory to be implemented in new neuromorphic hardware. It endows a neural network with a sequential memory that takes advantage of the inductive bias that data is organized causally in the temporal domain, and imbues the network with a state that represents the agent's ``self'', moving through the environment. This could also lead the way to continual learning, with the network modularized and ``'protected'' from overwrites that come with new data. In addition to aiding in solving these performance problems that plague current non-temporal deep networks, this also could finally lead towards endowing artificial networks with a sense of ``self''.

Dehao Yuan, Cornelia Fermüller

This paper presents a real-time, asynchronous, event-based normal flow estimator. It follows the same algorithm as Learning Normal Flow Directly From Event Neighborhoods, but with a more optimized implementation. The original method treats event slices as 3D point clouds, encodes each event's local geometry into a fixed-length vector, and uses a multi-layer perceptron to predict normal flow. It constructs representations by multiplying an adjacency matrix with a feature matrix, resulting in quadratic time complexity with respect to the number of events. In contrast, we leverage the fact that event coordinates are integers and reformulate the representation step as a pooling operation. This achieves the same effect as the adjacency matrix but with much lower computational cost. As a result, our method supports real-time normal flow prediction on event cameras. Our estimator uses 1 GB of CUDA memory and runs at 4 million normal flows per second on an RTX 3070, or 6 million per second on an RTX A5000. We release the CUDA implementation along with a Python interface at https://github.com/dhyuan99/VecKM_flow_cpp.

Jiayi Wu, Xiaomin Lin, Shahriar Negahdaripour et al.

Tasks such as autonomous navigation, 3D reconstruction, and object recognition near the water surfaces are crucial in marine robotics applications. However, challenges arise due to dynamic disturbances, e.g., light reflections and refraction from the random air-water interface, irregular liquid flow, and similar factors, which can lead to potential failures in perception and navigation systems. Traditional computer vision algorithms struggle to differentiate between real and virtual image regions, significantly complicating tasks. A virtual image region is an apparent representation formed by the redirection of light rays, typically through reflection or refraction, creating the illusion of an object's presence without its actual physical location. This work proposes a novel approach for segmentation on real and virtual image regions, exploiting synthetic images combined with domain-invariant information, a Motion Entropy Kernel, and Epipolar Geometric Consistency. Our segmentation network does not need to be re-trained if the domain changes. We show this by deploying the same segmentation network in two different domains: simulation and the real world. By creating realistic synthetic images that mimic the complexities of the water surface, we provide fine-grained training data for our network (MARVIS) to discern between real and virtual images effectively. By motion & geometry-aware design choices and through comprehensive experimental analysis, we achieve state-of-the-art real-virtual image segmentation performance in unseen real world domain, achieving an IoU over 78% and a F1-Score over 86% while ensuring a small computational footprint. MARVIS offers over 43 FPS (8 FPS) inference rates on a single GPU (CPU core). Our code and dataset are available here https://github.com/jiayi-wu-umd/MARVIS.

Chethan M. Parameshwara, Nitin J. Sanket, Chahat Deep Singh et al.

Segmentation of moving objects in dynamic scenes is a key process in scene understanding for navigation tasks. Classical cameras suffer from motion blur in such scenarios rendering them effete. On the contrary, event cameras, because of their high temporal resolution and lack of motion blur, are tailor-made for this problem. We present an approach for monocular multi-motion segmentation, which combines bottom-up feature tracking and top-down motion compensation into a unified pipeline, which is the first of its kind to our knowledge. Using the events within a time-interval, our method segments the scene into multiple motions by splitting and merging. We further speed up our method by using the concept of motion propagation and cluster keyslices. The approach was successfully evaluated on both challenging real-world and synthetic scenarios from the EV-IMO, EED, and MOD datasets and outperformed the state-of-the-art detection rate by 12\%, achieving a new state-of-the-art average detection rate of 81.06%, 94.2% and 82.35% on the aforementioned datasets. To enable further research and systematic evaluation of multi-motion segmentation, we present and open-source a new dataset/benchmark called MOD++, which includes challenging sequences and extensive data stratification in-terms of camera and object motion, velocity magnitudes, direction, and rotational speeds.

Konstantinos Zampogiannis, Cornelia Fermuller, Yiannis Aloimonos

We introduce cilantro, an open-source C++ library for geometric and general-purpose point cloud data processing. The library provides functionality that covers low-level point cloud operations, spatial reasoning, various methods for point cloud segmentation and generic data clustering, flexible algorithms for robust or local geometric alignment, model fitting, as well as powerful visualization tools. To accommodate all kinds of workflows, cilantro is almost fully templated, and most of its generic algorithms operate in arbitrary data dimension. At the same time, the library is easy to use and highly expressive, promoting a clean and concise coding style. cilantro is highly optimized, has a minimal set of external dependencies, and supports rapid development of performant point cloud processing software in a wide variety of contexts.

Jingxi Chen, Brandon Y. Feng, Haoming Cai et al.

Video Frame Interpolation aims to recover realistic missing frames between observed frames, generating a high-frame-rate video from a low-frame-rate video. However, without additional guidance, the large motion between frames makes this problem ill-posed. Event-based Video Frame Interpolation (EVFI) addresses this challenge by using sparse, high-temporal-resolution event measurements as motion guidance. This guidance allows EVFI methods to significantly outperform frame-only methods. However, to date, EVFI methods have relied on a limited set of paired event-frame training data, severely limiting their performance and generalization capabilities. In this work, we overcome the limited data challenge by adapting pre-trained video diffusion models trained on internet-scale datasets to EVFI. We experimentally validate our approach on real-world EVFI datasets, including a new one that we introduce. Our method outperforms existing methods and generalizes across cameras far better than existing approaches.

Snehesh Shrestha, Yantian Zha, Saketh Banagiri et al.

Recent advancements in multimodal Human-Robot Interaction (HRI) datasets have highlighted the fusion of speech and gesture, expanding robots' capabilities to absorb explicit and implicit HRI insights. However, existing speech-gesture HRI datasets often focus on elementary tasks, like object pointing and pushing, revealing limitations in scaling to intricate domains and prioritizing human command data over robot behavior records. To bridge these gaps, we introduce NatSGD, a multimodal HRI dataset encompassing human commands through speech and gestures that are natural, synchronized with robot behavior demonstrations. NatSGD serves as a foundational resource at the intersection of machine learning and HRI research, and we demonstrate its effectiveness in training robots to understand tasks through multimodal human commands, emphasizing the significance of jointly considering speech and gestures. We have released our dataset, simulator, and code to facilitate future research in human-robot interaction system learning; access these resources at https://www.snehesh.com/natsgd/

Dehao Yuan, Levi Burner, Jiayi Wu et al.

Event-based motion field estimation is an important task. However, current optical flow methods face challenges: learning-based approaches, often frame-based and relying on CNNs, lack cross-domain transferability, while model-based methods, though more robust, are less accurate. To address the limitations of optical flow estimation, recent works have focused on normal flow, which can be more reliably measured in regions with limited texture or strong edges. However, existing normal flow estimators are predominantly model-based and suffer from high errors. In this paper, we propose a novel supervised point-based method for normal flow estimation that overcomes the limitations of existing event learning-based approaches. Using a local point cloud encoder, our method directly estimates per-event normal flow from raw events, offering multiple unique advantages: 1) It produces temporally and spatially sharp predictions. 2) It supports more diverse data augmentation, such as random rotation, to improve robustness across various domains. 3) It naturally supports uncertainty quantification via ensemble inference, which benefits downstream tasks. 4) It enables training and inference on undistorted data in normalized camera coordinates, improving transferability across cameras. Extensive experiments demonstrate our method achieves better and more consistent performance than state-of-the-art methods when transferred across different datasets. Leveraging this transferability, we train our model on the union of datasets and release it for public use. Finally, we introduce an egomotion solver based on a maximum-margin problem that uses normal flow and IMU to achieve strong performance in challenging scenarios.

Dehao Yuan, Cornelia Fermüller, Tahseen Rabbani et al.

We propose VecKM, a local point cloud geometry encoder that is descriptive and efficient to compute. VecKM leverages a unique approach by vectorizing a kernel mixture to represent the local point cloud. Such representation's descriptiveness is supported by two theorems that validate its ability to reconstruct and preserve the similarity of the local shape. Unlike existing encoders downsampling the local point cloud, VecKM constructs the local geometry encoding using all neighboring points, producing a more descriptive encoding. Moreover, VecKM is efficient to compute and scalable to large point cloud inputs: VecKM reduces the memory cost from $(n^2+nKd)$ to $(nd+np)$; and reduces the major runtime cost from computing $nK$ MLPs to $n$ MLPs, where $n$ is the size of the point cloud, $K$ is the neighborhood size, $d$ is the encoding dimension, and $p$ is a marginal factor. The efficiency is due to VecKM's unique factorizable property that eliminates the need of explicitly grouping points into neighbors. In the normal estimation task, VecKM demonstrates not only 100x faster inference speed but also highest accuracy and strongest robustness. In classification and segmentation tasks, integrating VecKM as a preprocessing module achieves consistently better performance than the PointNet, PointNet++, and point transformer baselines, and runs consistently faster by up to 10 times.

Minghui Liu, Tahseen Rabbani, Tony O'Halloran et al.

Transformer-based large language models (LLMs) use the key-value (KV) cache to significantly accelerate inference by storing the key and value embeddings of past tokens. However, this cache consumes significant GPU memory. In this work, we introduce HashEvict, an algorithm that uses locality-sensitive hashing (LSH) to compress the KV cache. HashEvict quickly locates tokens in the cache that are cosine dissimilar to the current query token. This is achieved by computing the Hamming distance between binarized Gaussian projections of the current token query and cached token keys, with a projection length much smaller than the embedding dimension. We maintain a lightweight binary structure in GPU memory to facilitate these calculations. Unlike existing compression strategies that compute attention to determine token retention, HashEvict makes these decisions pre-attention, thereby reducing computational costs. Additionally, HashEvict is dynamic - at every decoding step, the key and value of the current token replace the embeddings of a token expected to produce the lowest attention score. We demonstrate that HashEvict can compress the KV cache by 30%-70% while maintaining high performance across reasoning, multiple-choice, long-context retrieval and summarization tasks.

Jingxi Chen, Brandon Y. Feng, Haoming Cai et al.

This paper addresses the novel challenge of ``rewinding'' time from a single captured image to recover the fleeting moments missed just before the shutter button is pressed. This problem poses a significant challenge in computer vision and computational photography, as it requires predicting plausible pre-capture motion from a single static frame, an inherently ill-posed task due to the high degree of freedom in potential pixel movements. We overcome this challenge by leveraging the emerging technology of neuromorphic event cameras, which capture motion information with high temporal resolution, and integrating this data with advanced image-to-video diffusion models. Our proposed framework introduces an event motion adaptor conditioned on event camera data, guiding the diffusion model to generate videos that are visually coherent and physically grounded in the captured events. Through extensive experimentation, we demonstrate the capability of our approach to synthesize high-quality videos that effectively ``rewind'' time, showcasing the potential of combining event camera technology with generative models. Our work opens new avenues for research at the intersection of computer vision, computational photography, and generative modeling, offering a forward-thinking solution to capturing missed moments and enhancing future consumer cameras and smartphones. Please see the project page at https://timerewind.github.io/ for video results and code release.

Zhongqiang Ren, Bunyod Suvonov, Guofei Chen et al.

This paper investigates Path planning Among Movable Obstacles (PAMO), which seeks a minimum cost collision-free path among static obstacles from start to goal while allowing the robot to push away movable obstacles (i.e., objects) along its path when needed. To develop planners that are complete and optimal for PAMO, the planner has to search a giant state space involving both the location of the robot as well as the locations of the objects, which grows exponentially with respect to the number of objects. This paper leverages a simple yet under-explored idea that, only a small fraction of this giant state space needs to be searched during planning as guided by a heuristic, and most of the objects far away from the robot are intact, which thus leads to runtime efficient algorithms. Based on this idea, this paper introduces two PAMO formulations, i.e., bi-objective and resource constrained problems in an occupancy grid, and develops PAMO*, a planning method with completeness and solution optimality guarantees, to solve the two problems. We then further extend PAMO* to hybrid-state PAMO* to plan in continuous spaces with high-fidelity interaction between the robot and the objects. Our results show that, PAMO* can often find optimal solutions within a second in cluttered maps with up to 400 objects.

Amir-Hossein Shahidzadeh, Jiyue Zhu, Kezhou Chen et al.

Robust object pose estimation is essential for manipulation and interaction tasks in robotics, particularly in scenarios where visual data is limited or sensitive to lighting, occlusions, and appearances. Tactile sensors often offer limited and local contact information, making it challenging to reconstruct the pose from partial data. Our approach uses sensorimotor exploration to actively control a robot hand to interact with the object. We train with Reinforcement Learning (RL) to explore and collect tactile data. The collected 3D point clouds are used to iteratively refine the object's shape and pose. In our setup, one hand holds the object steady while the other performs active exploration. We show that our method can actively explore an object's surface to identify critical pose features without prior knowledge of the object's geometry. Supplementary material and more demonstrations will be provided at https://amirshahid.github.io/BimanualTactilePose .

Jiayi Wu, Tianfu Wang, Md Abu Bakr Siddique et al.

Underwater image restoration algorithms seek to restore the color, contrast, and appearance of a scene that is imaged underwater. They are a critical tool in applications ranging from marine ecology and aquaculture to underwater construction and archaeology. While existing pixel-domain diffusion-based image restoration approaches are effective at restoring simple scenes with limited depth variation, they are computationally intensive and often generate unrealistic artifacts when applied to scenes with complex geometry and significant depth variation. In this work we overcome these limitations by combining a novel network architecture (SLURPP) with an accurate synthetic data generation pipeline. SLURPP combines pretrained latent diffusion models -- which encode strong priors on the geometry and depth of scenes -- with an explicit scene decomposition -- which allows one to model and account for the effects of light attenuation and backscattering. To train SLURPP we design a physics-based underwater image synthesis pipeline that applies varied and realistic underwater degradation effects to existing terrestrial image datasets. This approach enables the generation of diverse training data with dense medium/degradation annotations. We evaluate our method extensively on both synthetic and real-world benchmarks and demonstrate state-of-the-art performance. Notably, SLURPP is over 200X faster than existing diffusion-based methods while offering ~ 3 dB improvement in PSNR on synthetic benchmarks. It also offers compelling qualitative improvements on real-world data. Project website https://tianfwang.github.io/slurpp/.

Seong Jong Yoo, Snehesh Shrestha, Irina Muresanu et al.

Musicians delicately control their bodies to generate music. Sometimes, their motions are too subtle to be captured by the human eye. To analyze how they move to produce the music, we need to estimate precise 4D human pose (3D pose over time). However, current state-of-the-art (SoTA) visual pose estimation algorithms struggle to produce accurate monocular 4D poses because of occlusions, partial views, and human-object interactions. They are limited by the viewing angle, pixel density, and sampling rate of the cameras and fail to estimate fast and subtle movements, such as in the musical effect of vibrato. We leverage the direct causal relationship between the music produced and the human motions creating them to address these challenges. We propose VioPose: a novel multimodal network that hierarchically estimates dynamics. High-level features are cascaded to low-level features and integrated into Bayesian updates. Our architecture is shown to produce accurate pose sequences, facilitating precise motion analysis, and outperforms SoTA. As part of this work, we collected the largest and the most diverse calibrated violin-playing dataset, including video, sound, and 3D motion capture poses. Code and dataset can be found in our project page \url{https://sj-yoo.info/viopose/}.

Chinmaya Devaraj, Cornelia Fermuller, Yiannis Aloimonos

Videos are more informative than images because they capture the dynamics of the scene. By representing motion in videos, we can capture dynamic activities. In this work, we introduce GPT-4 generated motion descriptions that capture fine-grained motion descriptions of activities and apply them to three action datasets. We evaluated several video-text models on the task of retrieval of motion descriptions. We found that they fall far behind human expert performance on two action datasets, raising the question of whether video-text models understand motion in videos. To address it, we introduce a method of improving motion understanding in video-text models by utilizing motion descriptions. This method proves to be effective on two action datasets for the motion description retrieval task. The results draw attention to the need for quality captions involving fine-grained motion information in existing datasets and demonstrate the effectiveness of the proposed pipeline in understanding fine-grained motion during video-text retrieval.

Tianyi Xiong, Jiayi Wu, Botao He et al.

By combining differentiable rendering with explicit point-based scene representations, 3D Gaussian Splatting (3DGS) has demonstrated breakthrough 3D reconstruction capabilities. However, to date 3DGS has had limited impact on robotics, where high-speed egomotion is pervasive: Egomotion introduces motion blur and leads to artifacts in existing frame-based 3DGS reconstruction methods. To address this challenge, we introduce Event3DGS, an {\em event-based} 3DGS framework. By exploiting the exceptional temporal resolution of event cameras, Event3GDS can reconstruct high-fidelity 3D structure and appearance under high-speed egomotion. Extensive experiments on multiple synthetic and real-world datasets demonstrate the superiority of Event3DGS compared with existing event-based dense 3D scene reconstruction frameworks; Event3DGS substantially improves reconstruction quality (+3dB) while reducing computational costs by 95\%. Our framework also allows one to incorporate a few motion-blurred frame-based measurements into the reconstruction process to further improve appearance fidelity without loss of structural accuracy.

Siyuan Peng, Kate Ladenheim, Snehesh Shrestha et al.

This paper introduces the concept of a design tool for artistic performances based on attribute descriptions. To do so, we used a specific performance of falling actions. The platform integrates a novel machine-learning (ML) model with an interactive interface to generate and visualize artistic movements. Our approach's core is a cyclic Attribute-Conditioned Variational Autoencoder (AC-VAE) model developed to address the challenge of capturing and generating realistic 3D human body motions from motion capture (MoCap) data. We created a unique dataset focused on the dynamics of falling movements, characterized by a new ontology that divides motion into three distinct phases: Impact, Glitch, and Fall. The ML model's innovation lies in its ability to learn these phases separately. It is achieved by applying comprehensive data augmentation techniques and an initial pose loss function to generate natural and plausible motion. Our web-based interface provides an intuitive platform for artists to engage with this technology, offering fine-grained control over motion attributes and interactive visualization tools, including a 360-degree view and a dynamic timeline for playback manipulation. Our research paves the way for a future where technology amplifies the creative potential of human expression, making sophisticated motion generation accessible to a wider artistic community.

Chahat Deep Singh, Nitin J. Sanket, Chethan M. Parameshwara et al.

Recent advances in object segmentation have demonstrated that deep neural networks excel at object segmentation for specific classes in color and depth images. However, their performance is dictated by the number of classes and objects used for training, thereby hindering generalization to never seen objects or zero-shot samples. To exacerbate the problem further, object segmentation using image frames rely on recognition and pattern matching cues. Instead, we utilize the 'active' nature of a robot and their ability to 'interact' with the environment to induce additional geometric constraints for segmenting zero-shot samples. In this paper, we present the first framework to segment unknown objects in a cluttered scene by repeatedly 'nudging' at the objects and moving them to obtain additional motion cues at every step using only a monochrome monocular camera. We call our framework NudgeSeg. These motion cues are used to refine the segmentation masks. We successfully test our approach to segment novel objects in various cluttered scenes and provide an extensive study with image and motion segmentation methods. We show an impressive average detection rate of over 86% on zero-shot objects.

Nitin J. Sanket, Chahat Deep Singh, Chethan M. Parameshwara et al.

The rapid rise of accessibility of unmanned aerial vehicles or drones pose a threat to general security and confidentiality. Most of the commercially available or custom-built drones are multi-rotors and are comprised of multiple propellers. Since these propellers rotate at a high-speed, they are generally the fastest moving parts of an image and cannot be directly "seen" by a classical camera without severe motion blur. We utilize a class of sensors that are particularly suitable for such scenarios called event cameras, which have a high temporal resolution, low-latency, and high dynamic range. In this paper, we model the geometry of a propeller and use it to generate simulated events which are used to train a deep neural network called EVPropNet to detect propellers from the data of an event camera. EVPropNet directly transfers to the real world without any fine-tuning or retraining. We present two applications of our network: (a) tracking and following an unmarked drone and (b) landing on a near-hover drone. We successfully evaluate and demonstrate the proposed approach in many real-world experiments with different propeller shapes and sizes. Our network can detect propellers at a rate of 85.1% even when 60% of the propeller is occluded and can run at upto 35Hz on a 2W power budget. To our knowledge, this is the first deep learning-based solution for detecting propellers (to detect drones). Finally, our applications also show an impressive success rate of 92% and 90% for the tracking and landing tasks respectively.

Chethan M. Parameshwara, Simin Li, Cornelia Fermüller et al.

Spiking Neural Networks (SNN) are the so-called third generation of neural networks which attempt to more closely match the functioning of the biological brain. They inherently encode temporal data, allowing for training with less energy usage and can be extremely energy efficient when coded on neuromorphic hardware. In addition, they are well suited for tasks involving event-based sensors, which match the event-based nature of the SNN. However, SNNs have not been as effectively applied to real-world, large-scale tasks as standard Artificial Neural Networks (ANNs) due to the algorithmic and training complexity. To exacerbate the situation further, the input representation is unconventional and requires careful analysis and deep understanding. In this paper, we propose \textit{SpikeMS}, the first deep encoder-decoder SNN architecture for the real-world large-scale problem of motion segmentation using the event-based DVS camera as input. To accomplish this, we introduce a novel spatio-temporal loss formulation that includes both spike counts and classification labels in conjunction with the use of new techniques for SNN backpropagation. In addition, we show that \textit{SpikeMS} is capable of \textit{incremental predictions}, or predictions from smaller amounts of test data than it is trained on. This is invaluable for providing outputs even with partial input data for low-latency applications and those requiring fast predictions. We evaluated \textit{SpikeMS} on challenging synthetic and real-world sequences from EV-IMO, EED and MOD datasets and achieving results on a par with a comparable ANN method, but using potentially 50 times less power.

Eadom Dessalene, Chinmaya Devaraj, Michael Maynord et al.

Human actions involving hand manipulations are structured according to the making and breaking of hand-object contact, and human visual understanding of action is reliant on anticipation of contact as is demonstrated by pioneering work in cognitive science. Taking inspiration from this, we introduce representations and models centered on contact, which we then use in action prediction and anticipation. We annotate a subset of the EPIC Kitchens dataset to include time-to-contact between hands and objects, as well as segmentations of hands and objects. Using these annotations we train the Anticipation Module, a module producing Contact Anticipation Maps and Next Active Object Segmentations - novel low-level representations providing temporal and spatial characteristics of anticipated near future action. On top of the Anticipation Module we apply Egocentric Object Manipulation Graphs (Ego-OMG), a framework for action anticipation and prediction. Ego-OMG models longer term temporal semantic relations through the use of a graph modeling transitions between contact delineated action states. Use of the Anticipation Module within Ego-OMG produces state-of-the-art results, achieving 1st and 2nd place on the unseen and seen test sets, respectively, of the EPIC Kitchens Action Anticipation Challenge, and achieving state-of-the-art results on the tasks of action anticipation and action prediction over EPIC Kitchens. We perform ablation studies over characteristics of the Anticipation Module to evaluate their utility.

Nitin J. Sanket, Chahat Deep Singh, Varun Asthana et al.

Morphable design and depth-based visual control are two upcoming trends leading to advancements in the field of quadrotor autonomy. Stereo-cameras have struck the perfect balance of weight and accuracy of depth estimation but suffer from the problem of depth range being limited and dictated by the baseline chosen at design time. In this paper, we present a framework for quadrotor navigation based on a stereo camera system whose baseline can be adapted on-the-fly. We present a method to calibrate the system at a small number of discrete baselines and interpolate the parameters for the entire baseline range. We present an extensive theoretical analysis of calibration and synchronization errors. We showcase three different applications of such a system for quadrotor navigation: (a) flying through a forest, (b) flying through an unknown shaped/location static/dynamic gap, and (c) accurate 3D pose detection of an independently moving object. We show that our variable baseline system is more accurate and robust in all three scenarios. To our knowledge, this is the first work that applies the concept of morphable design to achieve a variable baseline stereo vision system on a quadrotor.

Kanishka Ganguly, Behzad Sadrfaridpour, Pavan Mantripragada et al.

Grasping and manipulating a wide variety of objects is a fundamental skill that would determine the success and wide spread adaptation of robots in homes. Several end-effector designs for robust manipulation have been proposed but they mostly work when provided with prior information about the objects or equipped with external sensors for estimating object shape or size. Such approaches are limited to many-shot or unknown objects and are prone to estimation errors from external estimation systems. We propose an approach to grasp and manipulate previously unseen or zero-shot objects: the objects without any prior of their shape, size, material and weight properties, using only feedback from tactile sensors which is contrary to the state-of-the-art. Such an approach provides robust manipulation of objects either when the object model is not known or when it is estimated incorrectly from an external system. Our approach is inspired by the ideology of how animals or humans manipulate objects, i.e., by using feedback from their skin. Our grasping and manipulation revolves around the simple notion that objects slip if not grasped stably. This slippage can be detected and counteracted for a robust grasp that is agnostic to the type, shape, size, material and weight of the object. At the crux of our approach is a novel tactile feedback based controller that detects and compensates for slip during grasp. We successfully evaluate and demonstrate our proposed approach on many real world experiments using the Shadow Dexterous Hand equipped with BioTac SP tactile sensors for different object shapes, sizes, weights and materials. We obtain an overall success rate of 73.5%

Matthew Evanusa, Snehesh Shrestha, Michelle Girvan et al.

In many real-world applications, fully-differentiable RNNs such as LSTMs and GRUs have been widely deployed to solve time series learning tasks. These networks train via Backpropagation Through Time, which can work well in practice but involves a biologically unrealistic unrolling of the network in time for gradient updates, are computationally expensive, and can be hard to tune. A second paradigm, Reservoir Computing, keeps the recurrent weight matrix fixed and random. Here, we propose a novel hybrid network, which we call Hybrid Backpropagation Parallel Echo State Network (HBP-ESN) which combines the effectiveness of learning random temporal features of reservoirs with the readout power of a deep neural network with batch normalization. We demonstrate that our new network outperforms LSTMs and GRUs, including multi-layer "deep" versions of these networks, on two complex real-world multi-dimensional time series datasets: gesture recognition using skeleton keypoints from ChaLearn, and the DEAP dataset for emotion recognition from EEG measurements. We show also that the inclusion of a novel meta-ring structure, which we call HBP-ESN M-Ring, achieves similar performance to one large reservoir while decreasing the memory required by an order of magnitude. We thus offer this new hybrid reservoir deep learning paradigm as a new alternative direction for RNN learning of temporal or sequential data.

Matthew Evanusa, Cornelia Fermüller, Yiannis Aloimonos

Deep Reservoir Computing has emerged as a new paradigm for deep learning, which is based around the reservoir computing principle of maintaining random pools of neurons combined with hierarchical deep learning. The reservoir paradigm reflects and respects the high degree of recurrence in biological brains, and the role that neuronal dynamics play in learning. However, one issue hampering deep reservoir network development is that one cannot backpropagate through the reservoir layers. Recent deep reservoir architectures do not learn hidden or hierarchical representations in the same manner as deep artificial neural networks, but rather concatenate all hidden reservoirs together to perform traditional regression. Here we present a novel Deep Reservoir Network for time series prediction and classification that learns through the non-differentiable hidden reservoir layers using a biologically-inspired backpropagation alternative called Direct Feedback Alignment, which resembles global dopamine signal broadcasting in the brain. We demonstrate its efficacy on two real world multidimensional time series datasets.

Matthew Evanusa, Cornelia Fermuller, Yiannis Aloimonos

The brain is known to be a highly complex, asynchronous dynamical system that is highly tailored to encode temporal information. However, recent deep learning approaches to not take advantage of this temporal coding. Spiking Neural Networks (SNNs) can be trained using biologically-realistic learning mechanisms, and can have neuronal activation rules that are biologically relevant. This type of network is also structured fundamentally around accepting temporal information through a time-decaying voltage update, a kind of input that current rate-encoding networks have difficulty with. Here we show that a large, deep layered SNN with dynamical, chaotic activity mimicking the mammalian cortex with biologically-inspired learning rules, such as STDP, is capable of encoding information from temporal data. We argue that the randomness inherent in the network weights allow the neurons to form groups that encode the temporal data being inputted after self-organizing with STDP. We aim to show that precise timing of input stimulus is critical in forming synchronous neural groups in a layered network. We analyze the network in terms of network entropy as a metric of information transfer. We hope to tackle two problems at once: the creation of artificial temporal neural systems for artificial intelligence, as well as solving coding mechanisms in the brain.

Nitin J. Sanket, Chahat Deep Singh, Cornelia Fermüller et al.

Odometry on aerial robots has to be of low latency and high robustness whilst also respecting the Size, Weight, Area and Power (SWAP) constraints as demanded by the size of the robot. A combination of visual sensors coupled with Inertial Measurement Units (IMUs) has proven to be the best combination to obtain robust and low latency odometry on resource-constrained aerial robots. Recently, deep learning approaches for Visual Inertial fusion have gained momentum due to their high accuracy and robustness. However, the remarkable advantages of these techniques are their inherent scalability (adaptation to different sized aerial robots) and unification (same method works on different sized aerial robots) by utilizing compression methods and hardware acceleration, which have been lacking from previous approaches. To this end, we present a deep learning approach for visual translation estimation and loosely fuse it with an Inertial sensor for full 6DoF odometry estimation. We also present a detailed benchmark comparing different architectures, loss functions and compression methods to enable scalability. We evaluate our network on the MSCOCO dataset and evaluate the VI fusion on multiple real-flight trajectories.

Eadom Dessalene, Michael Maynord, Chinmaya Devaraj et al.

We introduce Egocentric Object Manipulation Graphs (Ego-OMG) - a novel representation for activity modeling and anticipation of near future actions integrating three components: 1) semantic temporal structure of activities, 2) short-term dynamics, and 3) representations for appearance. Semantic temporal structure is modeled through a graph, embedded through a Graph Convolutional Network, whose states model characteristics of and relations between hands and objects. These state representations derive from all three levels of abstraction, and span segments delimited by the making and breaking of hand-object contact. Short-term dynamics are modeled in two ways: A) through 3D convolutions, and B) through anticipating the spatiotemporal end points of hand trajectories, where hands come into contact with objects. Appearance is modeled through deep spatiotemporal features produced through existing methods. We note that in Ego-OMG it is simple to swap these appearance features, and thus Ego-OMG is complementary to most existing action anticipation methods. We evaluate Ego-OMG on the EPIC Kitchens Action Anticipation Challenge. The consistency of the egocentric perspective of EPIC Kitchens allows for the utilization of the hand-centric cues upon which Ego-OMG relies. We demonstrate state-of-the-art performance, outranking all other previous published methods by large margins and ranking first on the unseen test set and second on the seen test set of the EPIC Kitchens Action Anticipation Challenge. We attribute the success of Ego-OMG to the modeling of semantic structure captured over long timespans. We evaluate the design choices made through several ablation studies. Code will be released upon acceptance

John Kanu, Eadom Dessalene, Xiaomin Lin et al.

While traditional methods for instruction-following typically assume prior linguistic and perceptual knowledge, many recent works in reinforcement learning (RL) have proposed learning policies end-to-end, typically by training neural networks to map joint representations of observations and instructions directly to actions. In this work, we present a novel framework for learning to perform temporally extended tasks using spatial reasoning in the RL framework, by sequentially imagining visual goals and choosing appropriate actions to fulfill imagined goals. Our framework operates on raw pixel images, assumes no prior linguistic or perceptual knowledge, and learns via intrinsic motivation and a single extrinsic reward signal measuring task completion. We validate our method in two environments with a robot arm in a simulated interactive 3D environment. Our method outperforms two flat architectures with raw-pixel and ground-truth states, and a hierarchical architecture with ground-truth states on object arrangement tasks.

Nitin J. Sanket, Chethan M. Parameshwara, Chahat Deep Singh et al.

Dynamic obstacle avoidance on quadrotors requires low latency. A class of sensors that are particularly suitable for such scenarios are event cameras. In this paper, we present a deep learning -- based solution for dodging multiple dynamic obstacles on a quadrotor with a single event camera and on-board computation. Our approach uses a series of shallow neural networks for estimating both the ego-motion and the motion of independently moving objects. The networks are trained in simulation and directly transfer to the real world without any fine-tuning or retraining. We successfully evaluate and demonstrate the proposed approach in many real-world experiments with obstacles of different shapes and sizes, achieving an overall success rate of 70% including objects of unknown shape and a low light testing scenario. To our knowledge, this is the first deep learning -- based solution to the problem of dynamic obstacle avoidance using event cameras on a quadrotor. Finally, we also extend our work to the pursuit task by merely reversing the control policy, proving that our navigation stack can cater to different scenarios.

Chengxi Ye, Matthew Evanusa, Hua He et al.

Convolution is a central operation in Convolutional Neural Networks (CNNs), which applies a kernel to overlapping regions shifted across the image. However, because of the strong correlations in real-world image data, convolutional kernels are in effect re-learning redundant data. In this work, we show that this redundancy has made neural network training challenging, and propose network deconvolution, a procedure which optimally removes pixel-wise and channel-wise correlations before the data is fed into each layer. Network deconvolution can be efficiently calculated at a fraction of the computational cost of a convolution layer. We also show that the deconvolution filters in the first layer of the network resemble the center-surround structure found in biological neurons in the visual regions of the brain. Filtering with such kernels results in a sparse representation, a desired property that has been missing in the training of neural networks. Learning from the sparse representation promotes faster convergence and superior results without the use of batch normalization. We apply our network deconvolution operation to 10 modern neural network models by replacing batch normalization within each. Extensive experiments show that the network deconvolution operation is able to deliver performance improvement in all cases on the CIFAR-10, CIFAR-100, MNIST, Fashion-MNIST, Cityscapes, and ImageNet datasets.

Kanishka Ganguly, Behzad Sadrfaridpour, Cornelia Fermüller et al.

Grasping objects requires tight integration between visual and tactile feedback. However, there is an inherent difference in the scale at which both these input modalities operate. It is thus necessary to be able to analyze tactile feedback in isolation in order to gain information about the surface the end-effector is operating on, such that more fine-grained features may be extracted from the surroundings. For tactile perception of the robot, inspired by the concept of the tactile flow in humans, we present the computational tactile flow to improve the analysis of the tactile feedback in robots using a Shadow Dexterous Hand. In the computational tactile flow model, given a sequence of pressure values from the tactile sensors, we define a virtual surface for the pressure values and define the tactile flow as the optical flow of this surface. We provide case studies that demonstrate how the computational tactile flow maps reveal information on the direction of motion and 3D structure of the surface, and feedback regarding the action being performed by the robot.

Anton Mitrokhin, Chengxi Ye, Cornelia Fermuller et al.

We present the first event-based learning approach for motion segmentation in indoor scenes and the first event-based dataset - EV-IMO - which includes accurate pixel-wise motion masks, egomotion and ground truth depth. Our approach is based on an efficient implementation of the SfM learning pipeline using a low parameter neural network architecture on event data. In addition to camera egomotion and a dense depth map, the network estimates pixel-wise independently moving object segmentation and computes per-object 3D translational velocities for moving objects. We also train a shallow network with just 40k parameters, which is able to compute depth and egomotion. Our EV-IMO dataset features 32 minutes of indoor recording with up to 3 fast moving objects simultaneously in the camera field of view. The objects and the camera are tracked by the VICON motion capture system. By 3D scanning the room and the objects, accurate depth map ground truth and pixel-wise object masks are obtained, which are reliable even in poor lighting conditions and during fast motion. We then train and evaluate our learning pipeline on EV-IMO and demonstrate that our approach far surpasses its rivals and is well suited for scene constrained robotics applications.