The Flow has not summarised this story yet — read it at arXiv Computer Vision.
The same Gaussian of a 3D Gaussian Splatting model is seen from many views, and these views do not always agree on the class it belongs to. The Gaussian may be occluded in some of them, and the confid...
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.
The paper introduces an open‑vocabulary 3D object detection pipeline that uses a promptable segmentation model (SAM3) to generate instance masks from six surround‑view cameras. These masks are converted into metric 3D boxes, achieving up to 0.413 mAP/0.555 NDS without any training when supervised box geometry is borrowed at inference. The approach also improves a supervised LiDAR‑only detector by 0.034 mAP through a camera‑witness rule, demonstrating that measurement precision, not 2D detection, limits performance.
The paper investigates how much semantic information is lost when frozen foundation models are combined for few‑shot 3D segmentation. By varying the number of retained semantic alternatives before fusion, the authors show that keeping the full distribution of class scores yields higher harmonic‑mean IoU than collapsing to a single class. Experiments on ScanNet200 and ScanNet++ confirm that full‑distribution fusion consistently outperforms top‑1 and other operators, and that most useful information is recovered by retaining a compact set of plausible alternatives.
arXiv:2606.18623v2 Announce Type: replace Abstract: Gaussian segmentation is usually posed as transferring object knowledge from 2D foundation models into a 3D representation. This leaves a fundament...
arXiv:2606. 04364v1 Announce Type: cross Abstract: Concept bottleneck models (CBMs) predict a layer of human-named attributes before predicting a class, which makes their decisions auditable.