Search Results for author:
Found 18 papers, 5 papers with code
GSN: Generalisable Segmentation in Neural Radiance Field
Our GSN representation generates new views of unseen scenes on the fly along with consistent, per-pixel semantic features.
StyleTRF: Stylizing Tensorial Radiance Fields
In this work, we present StyleTRF, a compact, quick-to-optimize strategy for stylized view generation using TensoRF.
Casual Indoor HDR Radiance Capture from Omnidirectional Images
We present PanoHDR-NeRF, a neural representation of the full HDR radiance field of an indoor scene, and a pipeline to capture it casually, without elaborate setups or complex capture protocols.
SHARP: Shape-Aware Reconstruction of People in Loose Clothing
The parametric body prior enforces geometrical consistency on the body shape and pose, while the non-parametric representation models loose clothing and handle self-occlusions as well.
Appearance Editing with Free-viewpoint Neural Rendering
We present a neural rendering framework for simultaneous view synthesis and appearance editing of a scene from multi-view images captured under known environment illumination.
Reconstruction of People in Loose Clothing
3D human body reconstruction from monocular images is an interesting and ill-posed problem in computer vision with wider applications in multiple domains.
Geometric Scene Refocusing
We present a comprehensive algorithm for post-capture refocusing in a geometrically correct manner.
PeeledHuman: Robust Shape Representation for Textured 3D Human Body Reconstruction
We introduce PeeledHuman - a novel shape representation of the human body that is robust to self-occlusions.
A Flexible Neural Renderer for Material Visualization
Photo realism in computer generated imagery is crucially dependent on how well an artist is able to recreate real-world materials in the scene.
Graphics
Semantic Hierarchical Priors for Intrinsic Image Decomposition
Global context priors establish correspondences at the scene level.
Nose, eyes and ears: Head pose estimation by locating facial keypoints
Monocular head pose estimation requires learning a model that computes the intrinsic Euler angles for pose (yaw, pitch, roll) from an input image of human face.
Ranked #2 on
Head Pose Estimation
on AFLW
Part-based Graph Convolutional Network for Action Recognition
We divide the skeleton graph into four subgraphs with joints shared across them and learn a recognition model using a part-based graph convolutional network.
Ranked #21 on
Action Recognition
on NTU RGB+D
RefocusGAN: Scene Refocusing using a Single Image
Post-capture control of the focus position of an image is a useful photographic tool.
View-graph Selection Framework for SfM
Accuracy and efficiency of large-scale SfM is crucially dependent on the input view-graph.
Composite Focus Measure for High Quality Depth Maps
Depth from focus is a highly accessible method to estimate the 3D structure of everyday scenes.
A Unified View-Graph Selection Framework for Structure from Motion
Accuracy and efficiency of large-scale SfM is crucially dependent on the input view-graph.
From Traditional to Modern : Domain Adaptation for Action Classification in Short Social Video Clips
In this paper, we focus on the problem of unsupervised action classification in wild vines using traditional labeled datasets.
Multistage SFM: A Coarse-to-Fine Approach for 3D Reconstruction
We present a multistage approach for SFM reconstruction of a single component that breaks the sequential nature of the incremental SFM methods.
