2022-09-11 更新
KinePose: A temporally optimized inverse kinematics technique for 6DOF human pose estimation with biomechanical constraints
Authors:Kevin Gildea, Clara Mercadal-Baudart, Richard Blythman, Aljosa Smolic, Ciaran Simms
Computer vision/deep learning-based 3D human pose estimation methods aim to localize human joints from images and videos. Pose representation is normally limited to 3D joint positional/translational degrees of freedom (3DOFs), however, a further three rotational DOFs (6DOFs) are required for many potential biomechanical applications. Positional DOFs are insufficient to analytically solve for joint rotational DOFs in a 3D human skeletal model. Therefore, we propose a temporal inverse kinematics (IK) optimization technique to infer joint orientations throughout a biomechanically informed, and subject-specific kinematic chain. For this, we prescribe link directions from a position-based 3D pose estimate. Sequential least squares quadratic programming is used to solve a minimization problem that involves both frame-based pose terms, and a temporal term. The solution space is constrained using joint DOFs, and ranges of motion (ROMs). We generate 3D pose motion sequences to assess the IK approach both for general accuracy, and accuracy in boundary cases. Our temporal algorithm achieves 6DOF pose estimates with low Mean Per Joint Angular Separation (MPJAS) errors (3.7{\deg}/joint overall, & 1.6{\deg}/joint for lower limbs). With frame-by-frame IK we obtain low errors in the case of bent elbows and knees, however, motion sequences with phases of extended/straight limbs results in ambiguity in twist angle. With temporal IK, we reduce ambiguity for these poses, resulting in lower average errors.
PDF Project page: https://kevgildea.github.io/KinePose/
点此查看论文截图
Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
Authors:Xingchao Liu, Chengyue Gong, Qiang Liu
We present rectified flow, a surprisingly simple approach to learning (neural) ordinary differential equation (ODE) models to transport between two empirically observed distributions \pi_0 and \pi_1, hence providing a unified solution to generative modeling and domain transfer, among various other tasks involving distribution transport. The idea of rectified flow is to learn the ODE to follow the straight paths connecting the points drawn from \pi_0 and \pi_1 as much as possible. This is achieved by solving a straightforward nonlinear least squares optimization problem, which can be easily scaled to large models without introducing extra parameters beyond standard supervised learning. The straight paths are special and preferred because they are the shortest paths between two points, and can be simulated exactly without time discretization and hence yield computationally efficient models. We show that the procedure of learning a rectified flow from data, called rectification, turns an arbitrary coupling of \pi_0 and \pi_1 to a new deterministic coupling with provably non-increasing convex transport costs. In addition, recursively applying rectification allows us to obtain a sequence of flows with increasingly straight paths, which can be simulated accurately with coarse time discretization in the inference phase. In empirical studies, we show that rectified flow performs superbly on image generation, image-to-image translation, and domain adaptation. In particular, on image generation and translation, our method yields nearly straight flows that give high quality results even with a single Euler discretization step.
PDF
点此查看论文截图
Application of image-to-image translation in improving pedestrian detection
Authors:Devarsh Patel, Sarthak Patel, Megh Patel
The lack of effective target regions makes it difficult to perform several visual functions in low intensity light, including pedestrian recognition, and image-to-image translation. In this situation, with the accumulation of high-quality information by the combined use of infrared and visible images it is possible to detect pedestrians even in low light. In this study we are going to use advanced deep learning models like pix2pixGAN and YOLOv7 on LLVIP dataset, containing visible-infrared image pairs for low light vision. This dataset contains 33672 images and most of the images were captured in dark scenes, tightly synchronized with time and location.
PDF
点此查看论文截图
Many Heads but One Brain: Fusion Brain — a Competition and a Single Multimodal Multitask Architecture
Authors:Daria Bakshandaeva, Denis Dimitrov, Vladimir Arkhipkin, Alex Shonenkov, Mark Potanin, Denis Karachev, Andrey Kuznetsov, Anton Voronov, Aleksandr Petiushko
Supporting the current trend in the AI community, we present the AI Journey 2021 Challenge called Fusion Brain, the first competition which is targeted to make the universal architecture which could process different modalities (in this case, images, texts, and code) and solve multiple tasks for vision and language. The Fusion Brain Challenge combines the following specific tasks: Code2code Translation, Handwritten Text recognition, Zero-shot Object Detection, and Visual Question Answering. We have created datasets for each task to test the participants’ submissions on it. Moreover, we have collected and made publicly available a new handwritten dataset in both English and Russian, which consists of 94,128 pairs of images and texts. We also propose a multimodal and multitask architecture - a baseline solution, in the center of which is a frozen foundation model and which has been trained in Fusion mode along with Single-task mode. The proposed Fusion approach proves to be competitive and more energy-efficient compared to the task-specific one.
PDF
点此查看论文截图