Initialization and Alignment for Adversarial Texture Optimization

  title={Initialization and Alignment for Adversarial Texture Optimization},
  author={Xiaoming Zhao and Zhizhen Zhao and Alexander G. Schwing},
  booktitle={European Conference on Computer Vision},
. While recovery of geometry from image and video data has received a lot of attention in computer vision, methods to capture the texture for a given geometry are less mature. Specifically, classical methods for texture generation often assume clean geometry and reasonably well-aligned image data. While very recent methods, e.g ., adversarial texture optimization, better handle lower-quality data obtained from hand-held devices, we find them to still struggle frequently. To improve robustness… 

Figures and Tables from this paper



Adversarial Texture Optimization From RGB-D Scans

This work proposes an approach to produce photorealistic textures for approximate surfaces, even from misaligned images, by learning an objective function that is robust to these errors by using a conditional adversarial loss obtained from weakly-supervised views.

Patch-based optimization for image-based texture mapping

This paper uses patch-based synthesis to reconstruct a set of photometrically-consistent aligned images by drawing information from the source images by using patch search and vote, and reconstruction.

Shape and Viewpoint without Keypoints

We present a learning framework that learns to recover the 3D shape, pose and texture from a single image, trained on an image collection without any ground truth 3D shape, multi-view, camera

Texture Fields: Learning Texture Representations in Function Space

Texture Fields, a novel texture representation which is based on regressing a continuous 3D function parameterized with a neural network is proposed, which is able to represent high frequency texture and naturally blend with modern deep learning techniques.

Color adjustment in image-based texture maps

Texture Mapping for 3D Reconstruction with RGB-D Sensor

This paper first adaptively selects an optimal image for each face of the 3D model, which can effectively remove blurring and ghost artifacts produced by multiple image blending, and adopts a non-rigid global-to-local correction step to reduce the seaming effect between textures.

NeuTex: Neural Texture Mapping for Volumetric Neural Rendering

By separating geometry and texture, this work allows users to edit appearance by simply editing 2D texture maps and demonstrates that this representation can be reconstructed using only multi-view image supervision and generates high-quality rendering results.

Deferred neural rendering

This work proposes Neural Textures, which are learned feature maps that are trained as part of the scene capture process that can be utilized to coherently re-render or manipulate existing video content in both static and dynamic environments at real-time rates.

DeepVoxels: Learning Persistent 3D Feature Embeddings

This work proposes DeepVoxels, a learned representation that encodes the view-dependent appearance of a 3D scene without having to explicitly model its geometry, based on a Cartesian 3D grid of persistent embedded features that learn to make use of the underlying3D scene structure.

Photorealistic Facial Texture Inference Using Deep Neural Networks

A data-driven inference method is presented that can synthesize a photorealistic texture map of a complete 3D face model given a partial 2D view of a person in the wild and successful face reconstructions from a wide range of low resolution input images are demonstrated.