Search Results for author:
Found 21 papers, 5 papers with code
NASA Neural Articulated Shape Approximation
Efficient representation of articulated objects such as human bodies is an important problem in computer vision and graphics.
Robust Symmetry Detection via Riemannian Langevin Dynamics
In contrast, learning-based methods may be more robust to noise, but often overlook partial symmetries due to the scarcity of annotated data.
Streetscapes: Large-scale Consistent Street View Generation Using Autoregressive Video Diffusion
To achieve this goal, we build on recent work on video diffusion, used within an autoregressive framework that can easily scale to long sequences.
Stable Diffusion for Data Augmentation in COCO and Weed Datasets
Generative models have increasingly impacted relative tasks, from computer vision to interior design and other fields.
An Improved CNN-based Neural Network Model for Fruit Sugar Level Detection
Finally, we introduced a novel evaluation metric based on the dataset's standard deviation (STD) to assess detection performance, demonstrating the feasibility of using an artificial neural network model for nondestructive fruit sugar level detection.
LumiGAN: Unconditional Generation of Relightable 3D Human Faces
Unsupervised learning of 3D human faces from unstructured 2D image data is an active research area.
GINA-3D: Learning to Generate Implicit Neural Assets in the Wild
Modeling the 3D world from sensor data for simulation is a scalable way of developing testing and validation environments for robotic learning problems such as autonomous driving.
Object Occlusion of Adding New Categories in Objection Detection
However, we find that the simple mechanism of object occlusion is good enough and can provide acceptable accuracy in real scenarios adding new category.
Revisiting 3D Object Detection From an Egocentric Perspective
Given the insight that SDE would benefit from more accurate geometry descriptions, we propose to represent objects as amodal contours, specifically amodal star-shaped polygons, and devise a simple model, StarPoly, to predict such contours.
NeRFactor: Neural Factorization of Shape and Reflectance Under an Unknown Illumination
This enables the rendering of novel views of the object under arbitrary environment lighting and editing of the object's material properties.
Ranked #4 on
Image Relighting
on Stanford-ORB
Offboard 3D Object Detection from Point Cloud Sequences
While current 3D object recognition research mostly focuses on the real-time, onboard scenario, there are many offboard use cases of perception that are largely under-explored, such as using machines to automatically generate high-quality 3D labels.
Canonical Capsules: Self-Supervised Capsules in Canonical Pose
We propose a self-supervised capsule architecture for 3D point clouds.
NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesis
We present a method that takes as input a set of images of a scene illuminated by unconstrained known lighting, and produces as output a 3D representation that can be rendered from novel viewpoints under arbitrary lighting conditions.
NASA: Neural Articulated Shape Approximation
Efficient representation of articulated objects such as human bodies is an important problem in computer vision and graphics.
CvxNet: Learnable Convex Decomposition
We introduce a network architecture to represent a low dimensional family of convexes.
Cerberus: A Multi-headed Derenderer
To generalize to novel visual scenes with new viewpoints and new object poses, a visual system needs representations of the shapes of the parts of an object that are invariant to changes in viewpoint or pose.
BlockQNN: Efficient Block-wise Neural Network Architecture Generation
The block-wise generation brings unique advantages: (1) it yields state-of-the-art results in comparison to the hand-crafted networks on image classification, particularly, the best network generated by BlockQNN achieves 2. 35% top-1 error rate on CIFAR-10.
Unleashing the Potential of CNNs for Interpretable Few-Shot Learning
Our models are based on the idea of encoding objects in terms of visual concepts, which are interpretable visual cues represented by the feature vectors within CNNs.
Peephole: Predicting Network Performance Before Training
The quest for performant networks has been a significant force that drives the advancements of deep learning in recent years.
Few-shot Learning by Exploiting Visual Concepts within CNNs
In this work, we address these limitations of CNNs by developing novel, flexible, and interpretable models for few-shot learning.
Hierarchical Deep Recurrent Architecture for Video Understanding
The proposed framework contains hierarchical deep architecture, including the frame-level sequence modeling part and the video-level classification part.
