We present Wid3R, a feed-forward neural network for visual geometry reconstruction that supports wide field-of-view camera models.

We present a novel multi-video 4D Gaussian Splatting (4DGS) approach designed to handle real-world, unsynchronized video sets.

We present Splatblox, a real-time system for autonomous navigation in outdoor environments with dense vegetation, irregular obstacles, and complex terrain.

We present a method for creating digital twins from real-world environments and facilitating data augmentation for training downstream models embedded in unmanned aerial vehicles (UAVs).

We propose MoRe, a training-free Monocular Geometry Refinement method designed to improve cross-view consistency and achieve scale alignment.

We introduce UAV4D, a framework for enabling photorealistic rendering for dynamic real-world scenes captured by UAVs.

We propose a training-free method for 360-degree depth estimation by combining perspective foundation models with graph-based scale alignment.

We propose a complete pipeline for indoor mapping using omnidirectional images, consisting of three key stages: (1) Spherical SfM, (2) Neural Surface Reconstruction, and (3) Texture Optimization.

We propose an extension of K-Planes Neural Radiance Field (NeRF), wherein our algorithm stores a set of tiered feature vectors.

We propose the first learning-based dense matching algorithm for omnidirectional images.

We propose a novel 3D Gaussian splatting algorithm that integrates monocular depth network with anchored Gaussian splatting, enabling robust rendering performance on sparse-view datasets.

We propose a novel approach that integrates mesh representation with 3D Gaussian splats to perform high-quality rendering of reconstructed real-world scenes.

We present a practical method for reconstructing and optimizing textured meshes of large, unbounded real-world scenes that offer high visual and geometric fidelity.

We present a synthetic data generation pipeline based on NeRF for UAV-based perception

We present a new pipeline for acquiring a textured mesh in the wild with a single smartphone.

We have developed a fine-tuning method for metrically accurate depth estimation in a self-supervised way.

We present a novel approach for estimating depth from a monocular camera as it moves through complex and crowded indoor environments.

We first introduce a novel semi-supervised multi-view stereo framework.

We present a novel algorithm for self-supervised monocular depth completion in challenging indoor environments.

We propose SAFENet that is designed to leverage semantic information to overcome the limitations of the photometric loss.

We present a novel learnable normalization technique for style transfer using graph convolutional networks

We propose a novel framework consisting of two components: Target-Guided and Cycle-Free Data Augmentation and Self-Ensembling algorithm

We introduce a weak self-training (WST) method and adversarial background score regularization (BSR) for domain adaptive one-stage object detection.

We propose a pseudo-labeling curriculum based on a density-based clustering algorithm.

Chosen as one of 66 outstanding reviewers of ACCV 2020

Teaching Assistant, CMSC733: Computer Processing of Pictorial Information Fall 2022

Teaching Assistant, CMSC250: Discrete Structure Fall 2021

Teaching Assistant, CMSC426: Computer Vision Spring 2021

Student Tutor for Foreign Students: Introduction to Programming, CS101 2019