skip to main content

This content will become publicly available on October 1, 2024

Title: Autonomous Aesthetic Views Finding in Indoor Scenes with Deep Reinforcement Learning
Placing and orienting a camera to compose aesthetically meaningful shots of a scene is not only a key objective in real-world photography and cinematography but also for virtual content creation. The framing of a camera often significantly contributes to the story telling in movies, games, and mixed reality applications. Generating single camera poses or even contiguous trajectories either requires a significant amount of manual labor or requires solving highdimensional optimization problems, which can be computationally demanding and error-prone. In this paper, we introduce GAIT, a Deep Reinforcement Learning (DRL) agent, that learns to automatically control a camera to generate a sequence of aesthetically meaningful views for synthetic 3D indoor scenes. To generate sequences of frames with high aesthetic value, GAIT relies on a neural aesthetics estimator, which is trained on a crowed-sourced dataset. Additionally, we introduce regularization techniques for diversity and smoothness to generate visually interesting trajectories for a 3D environment, and to constrain agent acceleration in the reward function to generate a smooth sequence of camera frames. We validated our method by comparing it to baseline algorithms, based on a perceptual user study, and through ablation studies. The source code of our method will be released with the final version of our paper.  more » « less
Award ID(s):
Author(s) / Creator(s):
; ; ; ; ; ;
Date Published:
Journal Name:
International Conference on Computer Vision
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Telecystoscopy can lower the barrier to access critical urologic diagnostics for patients around the world. A major challenge for robotic control of flexible cystoscopes and intuitive teleoperation is the pose estimation of the scope tip. We propose a novel real-time camera localization method using video recordings from a prior cystoscopy and 3D bladder reconstruction to estimate cystoscope pose within the bladder during follow-up telecystoscopy. We map prior video frames into a low-dimensional space as a dictionary so that a new image can be likewise mapped to efficiently retrieve its nearest neighbor among the dictionary images. The cystoscope pose is then estimated by the correspondence among the new image, its nearest dictionary image, and the prior model from 3D reconstruction. We demonstrate performance of our methods using bladder phantoms with varying fidelity and a servo-controlled cystoscope to simulate the use case of bladder surveillance through telecystoscopy. The servo-controlled cystoscope with 3 degrees of freedom (angulation, roll, and insertion axes) was developed for collecting cystoscope videos from bladder phantoms. Cystoscope videos were acquired in a 2.5D bladder phantom (bladder-shape cross-section plus height) with a panorama of a urothelium attached to the inner surface. Scans of the 2.5D phantom were performed in separate arc trajectories each of which is generated by actuation on the angulation with a fixed roll and insertion length. We further included variance in moving speed, imaging distance and existence of bladder tumors. Cystoscope videos were also acquired in a water-filled 3D silicone bladder phantom with hand-painted vasculature. Scans of the 3D phantom were performed in separate circle trajectories each of which is generated by actuation on the roll axis under a fixed angulation and insertion length. These videos were used to create 3D reconstructions, dictionary sets, and test data sets for evaluating the computational efficiency and accuracy of our proposed method in comparison with a method based on global Scale-Invariant Feature Transform (SIFT) features, named SIFT-only. Our method can retrieve the nearest dictionary image for 94–100% of test frames in under 55[Formula: see text]ms per image, whereas the SIFT-only method can only find the image match for 56–100% of test frames in 6000–40000[Formula: see text]ms per image depending on size of the dictionary set and richness of SIFT features in the images. Our method, with a speed of around 20 Hz for the retrieval stage, is a promising tool for real-time image-based scope localization in robotic cystoscopy when prior cystoscopy images are available. 
    more » « less
  2. In this paper we derive a new capability for robots to measure relative direction, or Angle-of-Arrival (AOA), to other robots, while operating in non-line-of-sight and unmapped environments, without requiring external infrastructure. We do so by capturing all of the paths that a WiFi signal traverses as it travels from a transmitting to a receiving robot in the team, which we term as an AOA profile. The key intuition behind our approach is to emulate antenna arrays in the air as a robot moves freely in 2D or 3D space. The small differences in the phase and amplitude of WiFi signals are thus processed with knowledge of a robots’ local displacements (often provided via inertial sensors) to obtain the profile, via a method akin to Synthetic Aperture Radar (SAR). The main contribution of this work is the development of i) a framework to accommodate arbitrary 2D and 3D trajectories, as well as continuous mobility of both transmitting and receiving robots, while computing AOA profiles between them and ii) an accompanying analysis that provides a lower bound on variance of AOA estimation as a function of robot trajectory geometry that is based on the Cramer Rao Bound and antenna array theory. This is a critical distinction with previous work on SAR that restricts robot mobility to prescribed motion patterns, does not generalize to the full 3D space, and/or requires transmitting robots to be static during data acquisition periods. In fact, we find that allowing robots to use their full mobility in 3D space while performing SAR, results in more accurate AOA profiles and thus better AOA estimation. We formally characterize this observation as the informativeness of the trajectory; a computable quantity for which we derive a closed form. All theoretical developments are substantiated by extensive simulation and hardware experiments on air/ground robot platforms. Our experimental results bolster our theoretical findings, demonstrating that 3D trajectories provide enhanced and consistent accuracy, with AOA error of less than 10 deg for 95% of trials. We also show that our formulation can be used with an off-the-shelf trajectory estimation sensor (Intel RealSense T265 tracking camera), for estimating the robots’ local displacements, and we provide theoretical as well as empirical results that show the impact of typical trajectory estimation errors on the measured AOA. Finally, we demonstrate the performance of our system on a multi-robot task where a heterogeneous air/ground pair of robots continuously measure AOA profiles over a WiFi link to achieve dynamic rendezvous in an unmapped, 300 square meter environment with occlusions. 
    more » « less
  3. Synthetic data is highly useful for training machine learning systems performing image-based 3D reconstruction, as synthetic data has applications in both extending existing generalizable datasets and being tailored to train neural networks for specific learning tasks of interest. In this paper, we introduce and utilize a synthetic data generation suite capable of generating data given existing 3D scene models as input. Specifically, we use our tool to generate image sequences for use with Multi-View Stereo (MVS), moving a camera through the virtual space according to user-chosen camera parameters. We evaluate how the given camera parameters and type of 3D environment affect how applicable the generated image sequences are to the MVS task using five pre-trained neural networks on image sequences generated from three different 3D scene datasets. We obtain generated predictions for each combination of parameter value and input image sequence, using standard error metrics to analyze the differences in depth predictions on image sequences across 3D datasets, parameters, and networks. Among other results, we find that camera height and vertical camera viewing angle are the parameters that cause the most variation in depth prediction errors on these image sequences. 
    more » « less
  4. In computer vision, tracking humans across camera views remains challenging, especially for complex scenarios with frequent occlusions, significant lighting changes and other difficulties. Under such conditions, most existing appearance and geometric cues are not reliable enough to distinguish humans across camera views. To address these challenges, this paper presents a stochastic attribute grammar model for leveraging complementary and discriminative human attributes for enhancing cross-view tracking. The key idea of our method is to introduce a hierarchical representation, parse graph, to describe a subject and its movement trajectory in both space and time domains. This results in a hierarchical compositional representation, comprising trajectory entities of varying level, including human boxes, 3D human boxes, tracklets and trajectories. We use a set of grammar rules to decompose a graph node (e.g. tracklet) into a set of children nodes (e.g. 3D human boxes), and augment each node with a set of attributes, including geometry (e.g., moving speed, direction), accessories (e.g., bags), and/or activities (e.g., walking, running). These attributes serve as valuable cues, in addition to appearance features (e.g., colors), in determining the associations of human detection boxes across cameras. In particular, the attributes of a parent node are inherited by its children nodes, resulting in consistency constraints over the feasible parse graph. Thus, we cast cross-view human tracking as finding the most discriminative parse graph for each subject in videos. We develop a learning method to train this attribute grammar model from weakly supervised training data. To infer the optimal parse graph and its attributes, we develop an alternative parsing method that employs both top-down and bottom-up computations to search the optimal solution. We also explicitly reason the occlusion status of each entity in order to deal with significant changes of camera viewpoints. We evaluate the proposed method over public video benchmarks and demonstrate with extensive experiments that our method clearly outperforms state-of-theart tracking methods. 
    more » « less
  5. Online lecture videos are increasingly important e-learning materials for students. Automated content extraction from lecture videos facilitates information retrieval applications that improve access to the lecture material. A significant number of lecture videos include the speaker in the image. Speakers perform various semantically meaningful actions during the process of teaching. Among all the movements of the speaker, key actions such as writing or erasing potentially indicate important features directly related to the lecture content. In this paper, we present a methodology for lecture video content extraction using the speaker actions. Each lecture video is divided into small temporal units called action segments. Using a pose estimator, body and hands skeleton data are extracted and used to compute motion-based features describing each action segment. Then, the dominant speaker action of each of these segments is classified using Random forests and the motion-based features. With the temporal and spatial range of these actions, we implement an alternative way to draw key-frames of handwritten content from the video. In addition, for our fixed camera videos, we also use the skeleton data to compute a mask of the speaker writing locations for the subtraction of the background noise from the binarized key-frames. Our method has been tested on a publicly available lecture video dataset, and it shows reasonable recall and precision results, with a very good compression ratio which is better than previous methods based on content analysis. 
    more » « less