38 citations · 59 across the 15 of their papers we have counts for
17 papers
JewelTry: Mask-Free Scale Aware Jewelry Virtual Try-On
Xinlei Niu, Peixia Li, Jun Wang +5
Virtual try-on (VTON) enables customers to visualize how fashion products appear when worn and has become an important technology for online shopping. While recent advances have su…
Towards Realistic and Consistent Orbital Video Generation via 3D Foundation Priors
Rong Wang, Ruyi Zha, Ziang Cheng +3
We present a novel method for generating geometrically realistic and consistent orbital videos from a single image of an object. Existing video generation works mostly rely on pixe…
Joint Shadow Generation and Relighting via Light-Geometry Interaction Maps
Shan Wang, Peixia Li, Chenchen Xu +4
We propose Light-Geometry Interaction (LGI) maps, a novel representation that encodes light-aware occlusion from monocular depth. Unlike ray tracing, which requires full 3D reconst…
SRSR: Enhancing Semantic Accuracy in Real-World Image Super-Resolution with Spatially Re-Focused Text-Conditioning
Chen Chen, Majid Abdolshah, Violetta Shevchenko +3
Existing diffusion-based super-resolution approaches often exhibit semantic ambiguities due to inaccuracies and incompleteness in their text conditioning, coupled with the inherent…
Knowledge Combination to Learn Rotated Detection Without Rotated Annotation
Tianyu Zhu, Bryce Ferenczi, Pulak Purkait +3
Rotated bounding boxes drastically reduce output ambiguity of elongated objects, making it superior to axis-aligned bounding boxes. Despite the effectiveness, rotated detectors are…
Retrieval Augmented Classification for Long-Tail Visual Recognition
Alexander Long, Wei Yin, Thalaiyasingam Ajanthan +6
We introduce Retrieval Augmented Classification (RAC), a generic approach to augmenting standard image classification pipelines with an explicit retrieval module. RAC consists of a…
SG-VAE: Scene Grammar Variational Autoencoder to generate new indoor scenes
Pulak Purkait, Christopher Zach, Ian Reid
Deep generative models have been used in recent years to learn coherent latent representations in order to synthesize high-quality images. In this work, we propose a neural network…
NeuRoRA: Neural Robust Rotation Averaging
Pulak Purkait, Tat-Jun Chin, Ian Reid
Multiple rotation averaging is an essential task for structure from motion, mapping, and robot navigation. The task is to estimate the absolute orientations of several cameras give…
Resolving Marker Pose Ambiguity by Robust Rotation Averaging with Clique Constraints
Shin-Fang Ch'ng, Naoya Sogi, Pulak Purkait +2
Planar markers are useful in robotics and computer vision for mapping and localisation. Given a detected marker in an image, a frequent task is to estimate the 6DOF pose of the mar…
Seeing Behind Things: Extending Semantic Segmentation to Occluded Regions
Pulak Purkait, Christopher Zach, Ian Reid
Semantic segmentation and instance level segmentation made substantial progress in recent years due to the emergence of deep neural networks (DNNs). A number of deep architectures…
Morphological Networks for Image De-raining
Ranjan Mondal, Pulak Purkait, Sanchayan Santra +1
Mathematical morphological methods have successfully been applied to filter out (emphasize or remove) different structures of an image. However, it is argued that these methods cou…
Weakly supervised learning of indoor geometry by dual warping
Pulak Purkait, Ujwal Bonde, Christopher Zach
A major element of depth perception and 3D understanding is the ability to predict the 3D layout of a scene and its contained objects for a novel pose. Indoor environments are part…
Maximum Consensus Parameter Estimation by Reweighted Methods
Pulak Purkait, Christopher Zach, Anders Eriksson
Robust parameter estimation in computer vision is frequently accomplished by solving the maximum consensus (MaxCon) problem. Widely used randomized methods for MaxCon, however, can…
Learning monocular visual odometry with dense 3D mapping from dense 3D flow
Cheng Zhao, Li Sun, Pulak Purkait +2
This paper introduces a fully deep learning approach to monocular SLAM, which can perform simultaneous localization using a neural network for learning visual odometry (L-VO) and d…
SPP-Net: Deep Absolute Pose Regression with Synthetic Views
Pulak Purkait, Cheng Zhao, Christopher Zach
Image based localization is one of the important problems in computer vision due to its wide applicability in robotics, augmented reality, and autonomous systems. There is a rich s…
Minimal Solvers for Monocular Rolling Shutter Compensation under Ackermann Motion
Pulak Purkait, Christopher Zach
Modern automotive vehicles are often equipped with a budget commercial rolling shutter camera. These devices often produce distorted images due to the inter-row delay of the camera…
Dense RGB-D semantic mapping with Pixel-Voxel neural network
Cheng Zhao, Li Sun, Pulak Purkait +1
For intelligent robotics applications, extending 3D mapping to 3D semantic mapping enables robots to, not only localize themselves with respect to the scene's geometrical features…