6 papers
SHIFT: Surface-aware High-speed Integration For TSDFs
Ayaan Choudhury, Lokender Tiwari
Real-time 3D mapping is fundamental for autonomous robotic navigation, with Euclidean Signed Distance Fields (ESDFs) serving as the standard representation for online motion planni…
Fast and Robust Mesh Simplification for Generated and Real-World 3D Assets
Kunal Bhosikar, Preet Savalia, Lokender Tiwari +1
The rapid growth of 3D content from modern reconstruction and generative pipelines, such as neural rendering and large-scale 3D asset generation, has led to an abundance of dense,…
Enhanced Spatio-Temporal Context for Temporally Consistent Robust 3D Human Motion Recovery from Monocular Videos
Sushovan Chanda, Amogh Tiwari, Lokender Tiwari +3
Recovering temporally consistent 3D human body pose, shape and motion from a monocular video is a challenging task due to (self-)occlusions, poor lighting conditions, complex artic…
DGSAC: Density Guided Sampling and Consensus
Lokender Tiwari, Saket Anand
Robust multiple model fitting plays a crucial role in many computer vision applications. Unlike single model fitting problems, the multi-model fitting has additional challenges. Th…
REGroup: Rank-aggregating Ensemble of Generative Classifiers for Robust Predictions
Lokender Tiwari, Anish Madan, Saket Anand +1
Deep Neural Networks (DNNs) are often criticized for being susceptible to adversarial attacks. Most successful defense strategies adopt adversarial training or random input transfo…
Pseudo RGB-D for Self-Improving Monocular SLAM and Depth Prediction
Lokender Tiwari, Pan Ji, Quoc-Huy Tran +3
Classical monocular Simultaneous Localization And Mapping (SLAM) and the recently emerging convolutional neural networks (CNNs) for monocular depth prediction represent two largely…