← Back to all news
arXiv Computer Vision By Alfonso L\'opez-Ruiz, Diego Royo

Memory-efficient GPU pipelines for real-time non-line-of-sight reconstruction

Read the original on arXiv Computer Vision →

The paper presents memory‑efficient GPU pipelines that accelerate real‑time non‑line‑of‑sight (NLOS) reconstruction. By redesigning two wave‑based algorithms—f‑k migration and phasor‑fields—with fused kernels, warp‑level photon binning, batched transforms, CUDA graph replay, and selective FP16 storage, the authors achieve up to 42× speed‑ups over a reference streaming pipeline and 14× over the fastest published GPU baseline while reducing memory usage to as little as 2.5%. The work also includes an ablation study of implementation choices and introduces three denoising strategies that leverage the increased frame budget for future NLOS video processing.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

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.

By Zhican Wang, Guanghui He, Lingjun Gao, Dantong Liu, Shell Xu Hu, Chen Zhang, Zhuoran Song, Nicholas Lane, Hongxiang Fan
agentsroboticsbenchmarks
More like this →
arXiv Computer Vision
Sep 4

ReCoSplat: Online Feed-Forward Gaussian Splatting via Render-and-Compare

ReCoSplat is an online feed‑forward Gaussian splatting model that can synthesize novel views from a stream of observations, handling both posed and unposed inputs and optionally using camera intrinsics. It introduces a Render‑and‑Compare module that renders the current scene from the viewpoint of the incoming observation and compares it to the observation, providing a stable conditioning signal to mitigate the mismatch caused by predicted camera poses. A hybrid KV‑cache compression strategy further reduces memory usage, enabling the model to process long sequences efficiently while achieving state‑of‑the‑art performance on online view synthesis tasks.

By Freeman Cheng, Botao Ye, Xueting Li, Junqi You, Fangneng Zhan, Ming-Hsuan Yang
efficiencybenchmarks
More like this →
arXiv Computer Vision
Aug 31

ABCD: Alpha-Composited Block Coordinate Descent: Constant-VRAM Training for Large Radiance Fields

ABCD (Alpha‑Composited Block Coordinate Descent) is an out‑of‑core training framework for alpha‑composited radiance fields, demonstrated on 3D Gaussian Splatting. It reformulates training as block coordinate descent over spatial partitions, keeping only one block of parameters active while pre‑rendering and collapsing inactive regions into foreground and background RGBA images. This approach reduces peak VRAM usage to a constant with respect to scene size, enabling training on GPUs with limited memory while maintaining reconstruction quality within 5% PSNR of 3DGS.

By Ka Heng Shiu, Kartic Subr
More like this →