Search Results for author:
Found 9 papers, 2 papers with code
Practical Face Reconstruction via Differentiable Ray Tracing
The proposed method models scene illumination via a novel, parameterized virtual light stage, which in-conjunction with differentiable ray-tracing, introduces a coarse-to-fine optimization formulation for face reconstruction.
Towards High Fidelity Monocular Face Reconstruction with Rich Reflectance using Self-supervised Learning and Ray Tracing
In this paper, we build our work on the aforementioned approaches and propose a new method that greatly improves reconstruction quality and robustness in general scenes.
Ranked #12 on
3D Face Reconstruction
on NoW Benchmark
Data Dependent Kernel Approximation using Pseudo Random Fourier Features
Thus, reducing the number of feature dimensions is necessary to effectively scale to large datasets.
A comparison of dense region detectors for image search and fine-grained classification
Our results show that the regular dense detector is outperformed by other methods in most situations, leading us to improve the state of the art in comparable setups on standard retrieval and fined-grain benchmarks.
Covariance Descriptors for 3D Shape Matching and Retrieval
We evaluate the performance of the proposed Bag of Covariance Matrices framework on 3D shape matching and retrieval applications and demonstrate its superiority compared to descriptor-based techniques.
Face Reflectance and Geometry Modeling via Differentiable Ray Tracing
We present a novel strategy to automatically reconstruct 3D faces from monocular images with explicitly disentangled facial geometry (pose, identity and expression), reflectance (diffuse and specular albedo), and self-shadows.
S2F2: Self-Supervised High Fidelity Face Reconstruction from Monocular Image
We present a novel face reconstruction method capable of reconstructing detailed face geometry, spatially varying face reflectance from a single monocular image.
SCAF: Skip-Connections in Auto-encoder for Face alignment with few annotated data
Supervised face alignment methods need large amounts of training data to achieve good performance in terms of accuracy and generalization.
Ranked #30 on
Face Alignment
on WFLW
Exploring StyleGAN Latent Space for Face Alignment with Limited Training Data
In this paper, we propose to use StyleGAN to perform face alignment with limited training data instead of image generation.
Ranked #3 on
Face Alignment
on AFLW-19
