View synthesis

About: View synthesis is a research topic. Over the lifetime, 1701 publications have been published within this topic receiving 42333 citations.

Predicting Novel Views Using Generative Adversarial Query Network

Abstract: The problem of predicting a novel view of the scene using an arbitrary number of observations is a challenging problem for computers as well as for humans. This paper introduces the Generative Adversarial Query Network (GAQN), a general learning framework for novel view synthesis that combines Generative Query Network (GQN) and Generative Adversarial Networks (GANs). The conventional GQN encodes input views into a latent representation that is used to generate a new view through a recurrent variational decoder. The proposed GAQN builds on this work by adding two novel aspects: First, we extend the current GQN architecture with an adversarial loss function for improving the visual quality and convergence speed. Second, we introduce a feature-matching loss function for stabilizing the training procedure. The experiments demonstrate that GAQN is able to produce high-quality results and faster convergence compared to the conventional approach

VUNet: Dynamic Scene View Synthesis for Traversability Estimation using an RGB Camera

Abstract: We present VUNet, a novel view(VU) synthesis method for mobile robots in dynamic environments, and its application to the estimation of future traversability. Our method predicts future images for given virtual robot velocity commands using only RGB images at previous and current time steps. The future images result from applying two types of image changes to the previous and current images: 1) changes caused by different camera pose, and 2) changes due to the motion of the dynamic obstacles. We learn to predict these two types of changes disjointly using two novel network architectures, SNet and DNet. We combine SNet and DNet to synthesize future images that we pass to our previously presented method GONet to estimate the traversable areas around the robot. Our quantitative and qualitative evaluation indicate that our approach for view synthesis predicts accurate future images in both static and dynamic environments. We also show that these virtual images can be used to estimate future traversability correctly. We apply our view synthesis-based traversability estimation method to two applications for assisted teleoperation.

Moving Object Verification in Airborne Video Sequences

Abstract: This paper presents an end-to-end system for moving object verification in airborne video sequences. Using a sample selection module, the system first selects frames from a short sequence and stores them in an exemplar database. To handle appearance change due to potentially large aspect angle variations, a homography-based view synthesis method is then used to generate a novel view of each image in the exemplar database at the same pose as the testing object in each frame of a testing video segment. A rotationally invariant color matcher and a spatial-feature matcher based on distance transforms are combined using a weighted average rule to compare the novel view and the testing object. After looping over all testing frames, the set of match scores is passed to a temporal analysis module to examine the behavior of the testing object, and calculate a final likelihood. Very good verification performance is achieved over thousands of trials for both color and infrared video sequences using the proposed system.

Virtual View Synthesis of People from Multiple View Video

Abstract: This paper addresses the synthesis of virtual views of people from multiple view image sequences. We consider the target area of the multiple camera “3D Virtual Studio” with the ultimate goal of capturing video-realistic dynamic human appearance. A mesh based reconstruction framework is introduced to initialise and optimise the shape of a dynamic scene for view-dependent rendering, making use of silhouette and stereo data as complementary shape cues. The technique addresses two key problems: (1) robust shape reconstruction; and (2) accurate image correspondence for view dependent rendering in the presence of camera calibration error. We present results against ground truth data in synthetic test cases and for captured sequences of people in a studio. The framework demonstrates a higher resolution in rendering compared to shape from silhouette and multiple view stereo.

Immersive Video Coding: Should Geometry Information Be Transmitted as Depth Maps?

Abstract: Immersive video often refers to multiple views with texture and scene geometry information, from which different viewports can be synthesized on the client side. To design efficient immersive video coding solutions, it is desirable to minimize bitrate, pixel rate and complexity. We investigate whether the classical approach of sending the geometry of a scene as depth maps is appropriate to serve this purpose. Previous work shows that bypassing depth transmission entirely and estimating depth at the client side improves the synthesis performance while saving bitrate and pixel rate. In order to understand if the encoder side depth maps contain information that is beneficial to be transmitted, we first explore a hybrid approach which enables partial depth map transmission using a block-based RD-based decision in the depth coding process. This approach reveals that partial depth map transmission may improve the rendering performance but does not present a good compromise in terms of compression efficiency. This led us to address the remaining drawbacks of decoder side depth estimation: complexity and depth map inaccuracy. We propose a novel system that takes advantage of high quality depth maps at the server side by encoding them into lightweight features that support the depth estimator at the client side. These features allow reducing the amount of data that has to be handled during decoder side depth estimation by 88%, which significantly speeds up the cost computation and the energy minimization of the depth estimator. Furthermore, −46.0% and −37.9% average synthesis BD-Rate gains are achieved compared to the classical approach with depth maps estimated at the encoder.