arXiv Computer Vision
Localization and Neural Splatting on the Edge: An FPGA Scene Memory for Robots
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
Sep 23
LEAP-NBV: Lightweight Edge Active-Perception for Foundation-Model Next-Best-View Planning
arXiv:2609.23974v1 Announce Type: new Abstract: Foundation models are endowing autonomous systems with greater intelligence, enabling a more comprehensive understanding of the environment through vis...
arXiv AI
Aug 18
Efficient Block-Layer Parallel Inference for Vision-Language-Action on Hybrid Architectures
arXiv:2608. 14586v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models are becoming a promising paradigm for autonomous driving, but their deployment on existing vehicle platforms remains difficult because they introduce both high inference latency and strong GPU-side resource pressure.
Hugging Face Trending Papers
Sep 21
LEAP-NBV: Lightweight Edge Active-Perception for Foundation-Model Next-Best-View Planning
Foundation models are endowing autonomous systems with greater intelligence, enabling a more comprehensive understanding of the environment through visual perception. A representative example is Human...
arXiv Machine Learning
Jun 30
Efficient 3D Gaussian Splatting with Axis-Shared Rasterization and Order-independent Transmittance
arXiv:2506. 07069v2 Announce Type: replace-cross Abstract: 3D Gaussian Splatting (3DGS) has emerged as a powerful technique for novel view synthesis, combining high-quality reconstruction with efficient rendering.
arXiv Computer Vision
Oct 16
FALCON: FPGA-Accelerated Latency-Certifiable Occupancy Networks for Camera-Based Autonomous Driving
FALCON is a camera‑based 3D occupancy front‑end built on the AMD Kria KR260 FPGA that provides explicit latency guarantees for autonomous driving perception. The system uses cycle‑bounded programmable‑logic compute, a measured inference envelope over 100k frames, and a watchdog to flag stale outputs, achieving all 300k proxy frames within a 100 ms deadline plus at most 10.2 ms. On the full FlashOcc pipeline the board attains 29.88 mIoU on the Occ3D‑nuScenes set, matching 92.8 % of an FP32 baseline, while maintaining tighter tail latency than competing Jetson Orin and datacenter GPUs.
arXiv AI
Jul 21
CaT-GS: Efficient 3DGS Rendering for Large Scale Scenes via Inter-frame Caching and Tile Scheduling
arXiv:2607. 17842v1 Announce Type: cross Abstract: Recent breakthroughs in 3D Gaussian Splatting (3DGS) have advanced neural rendering with high fidelity and speed.