Search Results for author:
Found 12 papers, 7 papers with code
ViewDiff: 3D-Consistent Image Generation with Text-to-Image Models
In this paper, we present a method that leverages pretrained text-to-image models as a prior, and learn to generate multi-view images in a single denoising process from real-world data.
VR-NeRF: High-Fidelity Virtualized Walkable Spaces
We present an end-to-end system for the high-fidelity capture, model reconstruction, and real-time rendering of walkable spaces in virtual reality using neural radiance fields.
Learning Neural Duplex Radiance Fields for Real-Time View Synthesis
Neural radiance fields (NeRFs) enable novel view synthesis with unprecedented visual quality.
Neural Lens Modeling
Recent methods for 3D reconstruction and rendering increasingly benefit from end-to-end optimization of the entire image formation process.
Neural Assets: Volumetric Object Capture and Rendering for Interactive Environments
Creating realistic virtual assets is a time-consuming process: it usually involves an artist designing the object, then spending a lot of effort on tweaking its appearance.
RC-MVSNet: Unsupervised Multi-View Stereo with Neural Rendering
Finding accurate correspondences among different views is the Achilles' heel of unsupervised Multi-View Stereo (MVS).
TransformerFusion: Monocular RGB Scene Reconstruction using Transformers
We introduce TransformerFusion, a transformer-based 3D scene reconstruction approach.
NPMs: Neural Parametric Models for 3D Deformable Shapes
Crucially, once learned, our neural parametric models of shape and pose enable optimization over the learned spaces to fit to new observations, similar to the fitting of a traditional parametric model, e. g., SMPL.
Neural Deformation Graphs for Globally-consistent Non-rigid Reconstruction
We introduce Neural Deformation Graphs for globally-consistent deformation tracking and 3D reconstruction of non-rigid objects.
Neural Non-Rigid Tracking
We introduce a novel, end-to-end learnable, differentiable non-rigid tracker that enables state-of-the-art non-rigid reconstruction by a learned robust optimization.
Learning to Optimize Non-Rigid Tracking
One of the widespread solutions for non-rigid tracking has a nested-loop structure: with Gauss-Newton to minimize a tracking objective in the outer loop, and Preconditioned Conjugate Gradient (PCG) to solve a sparse linear system in the inner loop.
DeepDeform: Learning Non-rigid RGB-D Reconstruction with Semi-supervised Data
Applying data-driven approaches to non-rigid 3D reconstruction has been difficult, which we believe can be attributed to the lack of a large-scale training corpus.
