DISORF: A Distributed Online NeRF Training and Rendering Framework for Mobile Robots

no code implementations • 1 Mar 2024 • Chunlin Li, Ruofan Liang, Hanrui Fan, Zhengen Zhang, Sankeerth Durvasula, Nandita Vijaykumar

We present a framework, DISORF, to enable online 3D reconstruction and visualization of scenes captured by resource-constrained mobile robots and edge devices.

3D Reconstruction

DISTWAR: Fast Differentiable Rendering on Raster-based Rendering Pipelines

no code implementations • 1 Dec 2023 • Sankeerth Durvasula, Adrian Zhao, Fan Chen, Ruofan Liang, Pawan Kumar Sanjaya, Nandita Vijaykumar

In this work, we observe that the gradient computation phase during training is a significant bottleneck on GPUs due to the large number of atomic operations that need to be processed.

EvConv: Fast CNN Inference on Event Camera Inputs For High-Speed Robot Perception

no code implementations • 8 Mar 2023 • Sankeerth Durvasula, Yushi Guan, Nandita Vijaykumar

We also demonstrate a speedup of up to 1. 6X for inference using CNNs for tasks such as depth estimation, object recognition, and optical flow estimation, with almost no loss in accuracy.

Depth Estimation Object Recognition +2