More Like this

1. PanoSynthVR: Toward Light-weight 360-Degree View Synthesis from a Single Panoramic Input

   Waidhofer, John ; Gadgil, Richa ; Dickson, Anthony ; Zollman, Stefanie ; Ventura, Jonathan ( January 2022 , International Symposium on Mixed and Augmented Reality)

   We investigate how real-time, 360 degree view synthesis can be achieved on current virtual reality hardware from a single panoramic image input. We introduce a light-weight method to automatically convert a single panoramic input into a multi-cylinder image representation that supports real-time, free-viewpoint view synthesis rendering for virtual reality. We apply an existing convolutional neural network trained on pinhole images to a cylindrical panorama with wrap padding to ensure agreement between the left and right edges. The network outputs a stack of semi-transparent panoramas at varying depths which can be easily rendered and composited with over blending. Quantitative experiments and a user study show that the method produces convincing parallax and fewer artifacts than a textured mesh representation.
2. Learning neural representation of camera pose with matrix representation of pose shift via view synthesis

   Zhu, Y. ; Gao, R. ; Huang, S. ; Zhu, S. C. ; Wu, Y. N. ( January 2021 , IEEE Conference on Computer Vision and Pattern Recognition)

   How to effectively represent camera pose is an essential problem in 3D computer vision, especially in tasks such as camera pose regression and novel view synthesis. Traditionally, 3D position of the camera is represented by Cartesian coordinate and the orientation is represented by Euler angle or quaternions. These representations are manually designed, which may not be the most effective representation for downstream tasks. In this work, we propose an approach to learn neural representations of camera poses and 3D scenes, coupled with neural representations of local camera movements. Specifically, the camera pose and 3D scene are represented as vectors and the local camera movement is represented as a matrix operating on the vector of the camera pose. We demonstrate that the camera movement can further be parametrized by a matrix Lie algebra that underlies a rotation system in the neural space. The vector representations are then concatenated and generate the posed 2D image through a decoder network. The model is learned from only posed 2D images and corresponding camera poses, without access to depths or shapes. We conduct extensive experiments on synthetic and real datasets. The results show that compared with other camera pose representations, our learned representation is moremore »robust to noise in novel view synthesis and more effective in camera pose regression.« less
3. Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Rendering

   Youngjoong Kwon ; Dahun Kim ; Duygu Ceylan ; Henry Fuchs ( December 2021 , 35th Conference on Neural Information Processing Systems (NeurIPS 2021))

   In this paper, we aim at synthesizing a free-viewpoint video of an arbitrary human performance using sparse multi-view cameras. Recently, several works have addressed this problem by learning person-specific neural radiance fields (NeRF) to capture the appearance of a particular human. In parallel, some work proposed to use pixel-aligned features to generalize radiance fields to arbitrary new scenes and objects. Adopting such generalization approaches to humans, however, is highly challenging due to the heavy occlusions and dynamic articulations of body parts. To tackle this, we propose Neural Human Performer, a novel approach that learns generalizable neural radiance fields based on a parametric human body model for robust performance capture. Specifically, we first introduce a temporal transformer that aggregates tracked visual features based on the skeletal body motion over time. Moreover, a multi-view transformer is proposed to perform cross-attention between the temporally-fused features and the pixel-aligned features at each time step to integrate observations on the fly from multiple views. Experiments on the ZJU-MoCap and AIST datasets show that our method significantly outperforms recent generalizable NeRF methods on unseen identities and poses. The video results and code are available at https://youngjoongunc.github.io/nhp.
4. FIXMYPOSE: Pose Correctional Captioning and Retrieval

   Kim, Hyounghun ; Zala, Abhay ; Burri, Graham ; Bansal, Mohit ( February 2021 , Proceedings of the AAAI Conference on Artificial Intelligence)

   Interest in physical therapy and individual exercises such as yoga/dance has increased alongside the well-being trend, and people globally enjoy such exercises at home/office via video streaming platforms. However, such exercises are hard to follow without expert guidance. Even if experts can help, it is almost impossible to give personalized feedback to every trainee remotely. Thus, automated pose correction systems are required more than ever, and we introduce a new captioning dataset named FixMyPose to address this need. We collect natural language descriptions of correcting a “current” pose to look like a “target” pose. To support a multilingual setup, we collect descriptions in both English and Hindi. The collected descriptions have interesting linguistic properties such as egocentric relations to the environment objects, analogous references, etc., requiring an understanding of spatial relations and commonsense knowledge about postures. Further, to avoid ML biases, we maintain a balance across characters with diverse demographics, who perform a variety of movements in several interior environments (e.g., homes, offices). From our FixMyPose dataset, we introduce two tasks: the pose-correctional-captioning task and its reverse, the target-pose-retrieval task. During the correctional-captioning task, models must generate the descriptions of how to move from the current to the target posemore »image, whereas in the retrieval task, models should select the correct target pose given the initial pose and the correctional description. We present strong cross-attention baseline models (uni/multimodal, RL, multilingual) and also show that our baselines are competitive with other models when evaluated on other image-difference datasets. We also propose new task-specific metrics (object-match, body-part-match, direction-match) and conduct human evaluation for more reliable evaluation, and we demonstrate a large human-model performance gap suggesting room for promising future work. Finally, to verify the sim-to-real transfer of our FixMyPose dataset, we collect a set of real images and show promising performance on these images. Data and code are available: https://fixmypose-unc.github.io.« less
5. Rotationally-Consistent Novel View Synthesis for Humans

   https://doi.org/10.1145/3394171.3413754  

   Kwon, Youngjoong ; Petrangeli, Stefano ; Kim, Dahun ; Wang, Haoliang ; Fuchs, Henry ; Swaminathan, Viswanathan ( October 2020 , MM '20: Proceedings of the 28th ACM International Conference on Multimedia)

   Human novel view synthesis aims to synthesize target views of a human subject given input images taken from one or more reference viewpoints. Despite significant advances in model-free novel view synthesis, existing methods present two major limitations when applied to complex shapes like humans. First, these methods mainly focus on simple and symmetric objects, e.g., cars and chairs, limiting their performances to fine-grained and asymmetric shapes. Second, existing methods cannot guarantee visual consistency across different adjacent views of the same object. To solve these problems, we present in this paper a learning framework for the novel view synthesis of human subjects, which explicitly enforces consistency across different generated views of the subject. Specifically, we introduce a novel multi-view supervision and an explicit rotational loss during the learning process, enabling the model to preserve detailed body parts and to achieve consistency between adjacent synthesized views. To show the superior performance of our approach, we present qualitative and quantitative results on the Multi-View Human Action (MVHA) dataset we collected (consisting of 3D human models animated with different Mocap sequences and captured from 54 different viewpoints), the Pose-Varying Human Model (PVHM) dataset, and ShapeNet. The qualitative and quantitative results demonstrate that our approachmore »outperforms the state-of-the-art baselines in both per-view synthesis quality, and in preserving rotational consistency and complex shapes (e.g. fine-grained details, challenging poses) across multiple adjacent views in a variety of scenarios, for both humans and rigid objects.« less