We develop an effective point cloud rendering pipeline for novel view synthesis, which enables high fidelity local detail reconstruction, real-time rendering and user-friendly editing. In the heart of our pipeline is an adaptive frequency modulation module called Adaptive Frequency Net (AFNet), which utilizes a hypernetwork to learn the local texture frequency encoding that is consecutively injected into adaptive frequency activation layers to modulate the implicit radiance signal. This mechanism improves the frequency expressive ability of the network with richer frequency basis support, only at a small computational budget. To further boost performance, a preprocessing module is also proposed for point cloud geometry optimization via point opacity estimation. In contrast to implicit rendering, our pipeline supports high-fidelity interactive editing based on point cloud manipulation. Extensive experimental results on NeRF-Synthetic, ScanNet, DTU and Tanks and Temples datasets demonstrate the superior performances achieved by our method in terms of PSNR, SSIM and LPIPS, in comparison to the state-of-the-art.
We consider the problem of intelligently navigating through complex traffic. Urban situations are defined by the underlying map structure and special regulatory objects of e.g. a stop line or crosswalk. Thereon dynamic vehicles (cars, bicycles, etc.) move forward, while trying to keep accident risks low. Especially at intersections, the combination and interaction of traffic elements is diverse and human drivers need to focus on specific elements which are critical for their behavior. To support the analysis, we present in this paper the so-called Risk Navigation System (RNS). RNS leverages a graph-based local dynamic map with Time-To-X indicators for extracting upcoming sharp curves, intersection zones and possible vehicle-to-object collision points. In real car recordings, recommended velocity profiles to avoid risks are visualized within a 2D environment. By focusing on communicating not only the positional but also the temporal relation, RNS potentially helps to enhance awareness and prediction capabilities of the user.
We provide an integrated and systematic automation approach to spatial object recognition and positional detection using AI machine learning and computer vision algorithms for Orange County, California. We describe a comprehensive methodology for multi-sensor, high-resolution field data acquisition, along with post-field processing and pre-analysis processing tasks. We developed a series of algorithmic formulations and workflows that integrate convolutional deep neural network learning with detected object positioning estimation in 360{\deg} equirectancular photosphere imagery. We provide examples of application processing more than 800 thousand cardinal directions in photosphere images across two areas in Orange County, and present detection results for stop-sign and fire hydrant object recognition. We discuss the efficiency and effectiveness of our approach, along with broader inferences related to the performance and implications of this approach for future technological innovations, including automation of spatial data and public asset inventories, and near real-time AI field data systems.
Pruning is a promising approach to compress deep learning models in order to deploy them on resource-constrained edge devices. However, many existing pruning solutions are based on unstructured pruning, which yields models that cannot efficiently run on commodity hardware; and they often require users to manually explore and tune the pruning process, which is time-consuming and often leads to sub-optimal results. To address these limitations, this paper presents Automatic Attention Pruning (AAP), an adaptive, attention-based, structured pruning approach to automatically generate small, accurate, and hardware-efficient models that meet user objectives. First, it proposes iterative structured pruning using activation-based attention maps to effectively identify and prune unimportant filters. Then, it proposes adaptive pruning policies for automatically meeting the pruning objectives of accuracy-critical, memory-constrained, and latency-sensitive tasks. A comprehensive evaluation shows that AAP substantially outperforms the state-of-the-art structured pruning works for a variety of model architectures. Our code is at: https://github.com/kaiqi123/Automatic-Attention-Pruning.git.
Reconstructing a 3D surface from colonoscopy video is challenging due to illumination and reflectivity variation in the video frame that can cause defective shape predictions. Aiming to overcome this challenge, we utilize the characteristics of surface normal vectors and develop a two-step neural framework that significantly improves the colonoscopy reconstruction quality. The normal-based depth initialization network trained with self-supervised normal consistency loss provides depth map initialization to the normal-depth refinement module, which utilizes the relationship between illumination and surface normals to refine the frame-wise normal and depth predictions recursively. Our framework's depth accuracy performance on phantom colonoscopy data demonstrates the value of exploiting the surface normals in colonoscopy reconstruction, especially on en face views. Due to its low depth error, the prediction result from our framework will require limited post-processing to be clinically applicable for real-time colonoscopy reconstruction.
Haptic perception is incredibly important for immersive teleoperation of robots, especially for accomplishing manipulation tasks. We propose a low-cost haptic sensing and rendering system, which is capable of detecting and displaying surface roughness. As the robot fingertip moves across a surface of interest, two microphones capture sound coupled directly through the fingertip and through the air, respectively. A learning-based detector system analyzes the data in real-time and gives roughness estimates with both high temporal resolution and low latency. Finally, an audio-based haptic actuator displays the result to the human operator. We demonstrate the effectiveness of our system through experiments and our winning entry in the ANA Avatar XPRIZE competition finals, where impartial judges solved a roughness-based selection task even without additional vision feedback. We publish our dataset used for training and evaluation together with our trained models to enable reproducibility.
Reduced-order models based on physics are a popular choice in cardiovascular modeling due to their efficiency, but they may experience reduced accuracy when working with anatomies that contain numerous junctions or pathological conditions. We develop one-dimensional reduced-order models that simulate blood flow dynamics using a graph neural network trained on three-dimensional hemodynamic simulation data. Given the initial condition of the system, the network iteratively predicts the pressure and flow rate at the vessel centerline nodes. Our numerical results demonstrate the accuracy and generalizability of our method in physiological geometries comprising a variety of anatomies and boundary conditions. Our findings demonstrate that our approach can achieve errors below 2% and 3% for pressure and flow rate, respectively, provided there is adequate training data. As a result, our method exhibits superior performance compared to physics-based one-dimensional models, while maintaining high efficiency at inference time.
The use of cables for aerial manipulation has shown to be a lightweight and versatile way to interact with objects. However, fastening objects using cables is still a challenge and human is required. In this work, we propose a novel way to secure objects using hitches. The hitch can be formed and morphed in midair using a team of aerial robots with cables. The hitch's shape is modeled as a convex polygon, making it versatile and adaptable to a wide variety of objects. We propose an algorithm to form the hitch systematically. The steps can run in parallel, allowing hitches with a large number of robots to be formed in constant time. We develop a set of actions that include different actions to change the shape of the hitch. We demonstrate our methods using a team of aerial robots via simulation and actual experiments.
This work introduces efficient symbolic algorithms for quantitative reactive synthesis. We consider resource-constrained robotic manipulators that need to interact with a human to achieve a complex task expressed in linear temporal logic. Our framework generates reactive strategies that not only guarantee task completion but also seek cooperation with the human when possible. We model the interaction as a two-player game and consider regret-minimizing strategies to encourage cooperation. We use symbolic representation of the game to enable scalability. For synthesis, we first introduce value iteration algorithms for such games with min-max objectives. Then, we extend our method to the regret-minimizing objectives. Our benchmarks reveal that our symbolic framework not only significantly improves computation time (up to an order of magnitude) but also can scale up to much larger instances of manipulation problems with up to 2x number of objects and locations than the state of the art.
Deep neural networks have been successful in many reinforcement learning settings. However, compared to human learners they are overly data hungry. To build a sample-efficient world model, we apply a transformer to real-world episodes in an autoregressive manner: not only the compact latent states and the taken actions but also the experienced or predicted rewards are fed into the transformer, so that it can attend flexibly to all three modalities at different time steps. The transformer allows our world model to access previous states directly, instead of viewing them through a compressed recurrent state. By utilizing the Transformer-XL architecture, it is able to learn long-term dependencies while staying computationally efficient. Our transformer-based world model (TWM) generates meaningful, new experience, which is used to train a policy that outperforms previous model-free and model-based reinforcement learning algorithms on the Atari 100k benchmark.