SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimization

Jiang, Yue; Ji, Dantong; Han, Zhizhong; Zwicker, Matthias

doi:10.1109/cvpr42600.2020.00133

Cited by 196 publications

(111 citation statements)

References 31 publications

Supporting

Mentioning

103

Contrasting

Order By: Relevance

“…We will address this limitation in future work by investigating multiresolution methods for training [JJHZ20], adapting our network to take spatial locality into account. A major benefit of our approach to compression is that we do not need to store the entire volume in memory at once, since during training we need only access random samples of the field.…”

Section: Discussionmentioning

confidence: 99%

Compressive Neural Representations of Volumetric Scalar Fields

Jiang

Levine

et al. 2021

Computer Graphics Forum

View full text Add to dashboard Cite

We present an approach for compressing volumetric scalar fields using implicit neural representations. Our approach represents a scalar field as a learned function, wherein a neural network maps a point in the domain to an output scalar value. By setting the number of weights of the neural network to be smaller than the input size, we achieve compressed representations of scalar fields, thus framing compression as a type of function approximation. Combined with carefully quantizing network weights, we show that this approach yields highly compact representations that outperform state‐of‐the‐art volume compression approaches. The conceptual simplicity of our approach enables a number of benefits, such as support for time‐varying scalar fields, optimizing to preserve spatial gradients, and random‐access field evaluation. We study the impact of network design choices on compression performance, highlighting how simple network architectures are effective for a broad range of volumes.

show abstract

Section: Discussionmentioning

confidence: 99%

Compressive Neural Representations of Volumetric Scalar Fields

Jiang

Levine

et al. 2021

Computer Graphics Forum

View full text Add to dashboard Cite

show abstract

“…For rigid scenes, the sphere tracing algorithm [19,27,53] is widely used to find the intersection point of a ray and the SDF. However, it is not feasible here due to the deformation fields.…”

Section: Differentiable Non-rigid Ray-castingmentioning

confidence: 99%

SelfRecon: Self Reconstruction Your Digital Avatar from Monocular Video

Jiang¹,

Ye²,

Bao³

et al. 2022

Preprint

View full text Add to dashboard Cite

We propose SelfRecon, a clothed human body reconstruction method that combines implicit and explicit representations to recover space-time coherent geometries from a monocular self-rotating human video. Explicit methods require a predefined template mesh for a given sequence, while the template is hard to acquire for a specific subject. Meanwhile, the fixed topology limits the reconstruction accuracy and clothing types. Implicit methods support arbitrary topology and have high quality due to continuous geometric representation. However, it is difficult to integrate multi-frame information to produce a consistent registration sequence for downstream applications. We propose to combine the advantages of both representations. We utilize differential mask loss of the explicit mesh to obtain the coherent overall shape, while the details on the implicit surface are refined with the differentiable neural rendering. Meanwhile, the explicit mesh is updated periodically to adjust its topology changes, and a consistency loss is designed to match both representations closely. Compared with existing methods, SelfRecon can produce high-fidelity surfaces for arbitrary clothed humans with self-supervised optimization. Extensive experimental results demonstrate its effectiveness on real captured monocular videos.

show abstract

“…Since classic shape reconstruction works by Park et al and Mescheder et al [37], [38], NIRs have been used for novel view synthesis [13], [39]- [41] and multi-view reconstruction [42]- [44]. Recently, NIRs have been used to improve CT [45]- [49] and MR [50] imaging.…”

Section: Neural Implicit Representations and Reconstructionmentioning

confidence: 99%

Neural Computed Tomography

Gupta¹,

Colvert²,

Contijoch³

2022

Preprint

View full text Add to dashboard Cite

Motion during acquisition of a set of projections can lead to significant motion artifacts in computed tomography reconstructions despite fast acquisition of individual views. In cases such as cardiac imaging, motion may be unavoidable and evaluating motion may be of clinical interest. Reconstructing images with reduced motion artifacts has typically been achieved by developing systems with faster gantry rotation or using algorithms which measure and/or estimate the displacements. However, these approaches have had limited success due to both physical constraints as well as the challenge of estimating/measuring non-rigid, temporally varying, and patient-specific motions. We propose a novel reconstruction framework, NeuralCT, to generate time-resolved images free from motion artifacts. Our approaches utilizes a neural implicit approach and does not require estimation or modeling of the underlying motion. Instead, boundaries are represented using a signed distance metric and neural implicit framework. We utilize 'analysis-by-synthesis' to identify a solution consistent with the acquired sinogram as well as spatial and temporal consistency constraints. We illustrate the utility of NeuralCT in three progressively more complex scenarios: translation of a small circle, heartbeat-like change in an ellipse's diameter, and complex topological deformation. Without hyperparameter tuning or change to the architecture, NeuralCT provides high quality image reconstruction for all three motions, as compared to filtered backprojection using mean-square-error and Dice metrics. Code and supplemental movies are available at https://kunalmgupta.github.io/projects/NeuralCT.html.

show abstract

SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimization

Cited by 196 publications

References 31 publications

Compressive Neural Representations of Volumetric Scalar Fields

Compressive Neural Representations of Volumetric Scalar Fields

SelfRecon: Self Reconstruction Your Digital Avatar from Monocular Video

Neural Computed Tomography

Contact Info

Product

Resources

About