Pranay Meshram

I’m a Ph.D. student at the University at Buffalo working with Dr. Karthik Dantu at DRONES Lab.

My research focuses on building robust perception and planning systems for autonomous robots operating in unstructured environments. I work on visual SLAM, 3D reconstruction quality metrics, semantic-geometric terrain abstraction, and self-supervised depth estimation from polarization. My work spans from developing efficient edge-based perception models to large-scale planning frameworks that enable reliable autonomy in challenging real-world conditions.

I’ve led teams to top results in hardware-efficient autonomy—1st in latency at the 2022 ACM/IEEE TinyML Contest (overall 5th) and 4th place at DAC SDC 2022. Previously, I was a Research Scientist Intern at Meta Reality Labs working on self-supervised stereo depth estimation.

Resume

news

Dec 09, 2025	Our paper “QAL: A Loss for Recall–Precision Balance in 3D Reconstruction” has been accepted to WACV 2026! 🎉
Nov 02, 2025	UBPercept placed 5th overall at the 2022 ACM/IEEE TinyML Design Contest at ICCAD (Nov. 2), and earned 1st in latency and 3rd in flash (memory). Full results: TinyML Contest Winners.
Jul 08, 2022	Built a monocular visual odometry (VO) pipeline in Rust on the KITTI benchmark. Implemented feature tracking, pose estimation, and trajectory reconstruction, with plotting utilities to compare estimated trajectories against ground truth. Benchmarked VO accuracy across sequences and experimented with tuning feature detection thresholds and RANSAC parameters to handle motion blur and texture-poor regions. Added demos and visualizations to highlight drift over long trajectories and loop-closure opportunities. Git Repository
Jun 21, 2022	DAC System Design Contest 2022 – 4th place (UBPercept). Built an FPGA-friendly CNN pipeline on Ultra96V2 with quantization-aware training and deployment automation, targeting tight latency/memory budgets. Led a 7-member team through data curation, profiling, and inference optimization; automated builds and on-board evaluation to iterate rapidly on accuracy–efficiency trade-offs. Documented lessons on model pruning and kernel fusion for edge devices. Results
Dec 20, 2020	Cleaner Bot: a simple coverage-planning demo exploring unknown 2D space (project link, video linked).

latest posts

Jul 08, 2022	Monocular Visual Odometry in Rust (KITTI)
Jun 21, 2022	DAC SDC 2022 – FPGA-Friendly CNN (UBPercept)
Jun 21, 2022	DAC SDC 2022 - 4th Place (UBPercept)

selected publications

arXiv
QAL: A Loss for Recall–Precision Balance in 3D Reconstruction

Pranay Meshram, Yash Turkar, Kartikeya Singh, and 3 more authors

arXiv preprint arXiv:2511.17824, 2025

Abs Bib HTML

Volumetric learning underpins many 3D vision tasks such as completion, reconstruction, and mesh generation, yet training objectives still rely on Chamfer Distance (CD) or Earth Mover’s Distance (EMD), which fail to balance recall and precision. We propose Quality-Aware Loss (QAL), a drop-in replacement for CD/EMD that combines a coverage-weighted nearest-neighbor term with an uncovered–ground-truth attraction term, explicitly decoupling recall and precision into tunable components.
@article{meshram2025qal, title = {QAL: A Loss for Recall--Precision Balance in 3D Reconstruction}, author = {Meshram, Pranay and Turkar, Yash and Singh, Kartikeya and Masilamani, Praveen Raj and Adhivarahan, Charuvahan and Dantu, Karthik}, journal = {arXiv preprint arXiv:2511.17824}, year = {2025}, }
arXiv
Empir3D: A Framework for Multi-Dimensional Point Cloud Assessment

Yash Turkar, Pranay Meshram, Christo Aluckal, and 2 more authors

arXiv preprint arXiv:2306.03660, 2024

Abs Bib HTML

Empir3D proposes a multi-dimensional point cloud evaluation framework with metrics for resolution, accuracy, coverage, and artifacts, providing richer assessment of SLAM and point cloud completion results beyond traditional Chamfer or EMD.
@article{turkar2024empir3d, title = {Empir3D: A Framework for Multi-Dimensional Point Cloud Assessment}, author = {Turkar, Yash and Meshram, Pranay and Aluckal, Christo and Adhivarahan, Charuvahan and Dantu, Karthik}, journal = {arXiv preprint arXiv:2306.03660}, year = {2024}, }