Skip to search formSkip to main contentSkip to account menu

Occupancy Networks: Learning 3D Reconstruction in Function Space

This paper proposes Occupancy Networks, a new representation for learning-based 3D reconstruction methods that encodes a description of the 3D output at infinite resolution without excessive memory footprint, and validate that the representation can efficiently encode 3D structure and can be inferred from various kinds of input.
View on IEEE (opens in a new tab)

Differentiable Volumetric Rendering: Learning Implicit 3D Representations Without 3D Supervision

This work proposes a differentiable rendering formulation for implicit shape and texture representations, showing that depth gradients can be derived analytically using the concept of implicit differentiation, and finds that this method can be used for multi-view 3D reconstruction, directly resulting in watertight meshes.
View on IEEE (opens in a new tab)

UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction

This work shows that implicit surface models and radiance fields can be formulated in a unified way, enabling both surface and volume rendering using the same model, and outperforms NeRF in terms of reconstruction quality while performing on par with IDR without requiring masks.
View on IEEE (opens in a new tab)

Occupancy Flow: 4D Reconstruction by Learning Particle Dynamics

This work presents Occupancy Flow, a novel spatio-temporal representation of time-varying 3D geometry with implicit correspondences which can be used for interpolation and reconstruction tasks, and believes that Occupancy flow is a promising new 4D representation which will be useful for a variety of spatio/temporal reconstruction tasks.
View on IEEE (opens in a new tab)

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.
View on IEEE (opens in a new tab)

Learning Implicit Surface Light Fields

This work proposes a novel implicit representation for capturing the visual appearance of an object in terms of its surface light field and shows that the proposed representation can be embedded into a variational auto-encoder for generating novel appearances that conform to the specified illumination conditions.
View on IEEE (opens in a new tab)

Supplementary Material for Occupancy Networks : Learning 3 D Reconstruction in Function Space

In this supplementary document, a detailed overview of the architectures and training procedure is given and the implementation of the baselines are discussed, as well as comparing them to the implementation in the original publications.

Supplementary Material for Learning Implicit Surface Light Fields

The generative model is implemented as a variational autoencoder and the rendering setup is explained in greater detail and how the method can be used in combination with environment maps is discussed.
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)