← Back to all news
arXiv Computer Vision By Ka Heng Shiu, Kartic Subr

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

Read the original on arXiv Computer Vision →

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.

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

Hugging Face Trending Papers
Jun 17

Splaxel: Efficient Distributed Training of 3D Gaussian Splatting for Large-scale Scene Reconstruction via Pixel-level Communication

3D Gaussian Splatting (3DGS) enables high-fidelity and real-time 3D scene reconstruction, but scaling training to large-scale scenes requires optimizing hundreds of millions of Gaussians across multiple GPUs. Existing distributed approaches either partition scenes into isolated regions, causing global inconsistency, or rely on global Gaussian-level exchanges, which lead to substantial growth in inter-GPU communication and quickly dominate iteration time.

benchmarks
More like this →
arXiv AI
Sep 28

Geometric-Photometric Event-based 3D Gaussian Ray Tracing

The paper introduces GPERT, a framework that separates event-based 3D Gaussian Splatting into two rendering branches: event-by-event geometry rendering and snapshot-based radiance rendering. By employing ray-tracing and warped event images, GPERT balances accuracy and temporal resolution, achieving state‑of‑the‑art results on real‑world datasets and competitive performance on synthetic data. The method operates without pretrained models or COLMAP initialization, offers flexible event selection, and produces sharp reconstructions of scene edges with rapid training.

By Kai Kohyama, Yoshimitsu Aoki, Guillermo Gallego, Shintaro Shiba
benchmarks
More like this →