← Back to all news
arXiv AI

OC-GS: Gaussian Splatting for Irregular Turntable Capture

OC-GS introduces an object‑centric Gaussian splatting method that refines the angle of each image while keeping a shared camera, rotation axis, and pivot for turntable reconstruction. By jointly optimizing image‑derived geometry and angles, it reconstructs objects from sparse, irregular captures and outperforms four pose‑free Gaussian splatting baselines across various view counts. Ablation studies confirm that both image‑derived angle initialization and the shared motion model are essential for the observed improvements, with real captures showing a 0.70 dB PSNR gain.

Related stories

arXiv Computer Vision
4d ago

Gauss What You Need: Compact Gaussian Splatting Across Scene Scales

Gauss What You Need: Compact Gaussian Splatting Across Scene Scales introduces TangoGS, a method that automatically selects the number of Gaussian primitives for 3D Gaussian Splatting by combining capture-derived model sizing with training-based adaptation. The approach first estimates a learning allowance based on the capture’s total pixels, then adjusts the number of Gaussians during training according to reconstruction quality. On standard benchmarks, TangoGS matches the best baseline’s PSNR while using 48% fewer Gaussians, and on larger captures it scales automatically to achieve the highest mean PSNR with 2.3× more Gaussians.

By Afif Boudaoud, Jiayi Liu, Alexandru Calotoiu, Torsten Hoefler
benchmarks
More like this →
arXiv Computer Vision
2d ago

AESplat: Advancing Pose-Free Feed-Forward 3D Gaussian Splatting via Decoupled Appearance Modeling

AESplat is a new pose‑free feed‑forward 3D Gaussian Splatting framework that improves rendering quality by decoupling view‑independent and view‑dependent appearance modeling. It directly extracts the base view‑independent appearance from input images and predicts higher‑order spherical harmonic coefficients with a shallow MLP that incorporates 3D‑aware inductive biases. Experiments on several datasets show AESplat outperforms state‑of‑the‑art methods, achieving up to 0.8 dB higher PSNR than NAS3R and 1.1 dB over DepthSplat on RealEstate10K.

By Shiwei Ren, Zhiang Liu, Yongchun Fang, Hongwei Chen
benchmarks
More like this →
arXiv AI
4d ago

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 →
arXiv Computer Vision
Sep 21

2D GauSS-MI: Efficient Active Scene Reconstruction with Balanced Visual and Geometric Quality

The paper introduces 2D GauSS-MI, an active scene reconstruction framework that uses 2D Gaussian Splatting (2DGS) to efficiently process incremental RGB‑D data. It presents an online 2DGS mapping pipeline and a probabilistic reliability model to assess view‑dependent reconstruction quality. Leveraging this model, the authors define a Shannon Mutual Information metric that guides active view selection, balancing visual and geometric quality while reducing computational cost and storage compared to state‑of‑the‑art baselines.

By Yuhan Xie, Jia Pan
benchmarks
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 →