arXiv Computer Vision
AQ3D: Adaptive Query Transformer for 3D Instance Segmentation
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Oct 22
Not All Tasks Quantize Equally: Fisher-Guided Quantization for Visual Geometry Transformer
arXiv:2605.15828v4 Announce Type: replace Abstract: Feed-forward 3D reconstruction models, represented by Visual Geometry Grounded Transformer (VGGT), jointly predict multiple visual geometry tasks s...
arXiv Computer Vision
Aug 26
Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding
arXiv:2604.19609v2 Announce Type: replace Abstract: Transformers have become a common foundation across deep learning, yet 3D scene understanding still relies on specialized backbones with strong dom...
arXiv Computer Vision
1d ago
Rotation Is Token-Blind: A Structural Criterion for Post-Training Quantization of Feed-Forward Geometry Transformers
The paper introduces QMapAnything, a post‑training quantization framework tailored for feed‑forward geometry transformers that use Transformers to predict camera poses, depth, and structure in a single pass. It addresses the challenge that heterogeneous token types share a single activation quantization grid, which can cause high‑leverage tokens to dominate outputs. By treating rotation and smoothing as token‑blind reparameterizations and defining a statistic γ to gauge when differentiated bias correction is needed, the method achieves W4A8 quantization that closely matches full‑precision performance while W8A8 reduces peak memory by 2.2–3.1× and speeds up inference by up to 3.1× on real hardware.
arXiv Computer Vision
Sep 30
PGL-3D: Towards Progressive Geometric Learning for 3D Visual Query Localization
PGL-3D introduces a progressive geometric learning framework for 3D visual query localization, where intermediate cuboids guide feature aggregation and refinement. The method predicts a complete cuboid for each proposal, selects reference observations via Query‑Tube‑Memory, pools query‑conditioned features, and re‑predicts refined cuboids. A training‑only objective, ST‑D9O, supervises cuboid geometry at every stage, yielding significant performance gains over prior baselines.
arXiv Computer Vision
Oct 7
DensiTok: Making Feed-Forward 3D Gaussian Splatting See More Views Than It Is Given
arXiv:2610.07958v1 Announce Type: new Abstract: Feed-forward 3D Gaussian Splatting (3DGS) reconstructs a scene in a single forward pass, replacing per-scene optimization with a network trained across...
arXiv Computer Vision
Aug 28
KISS-GS: 3D Gaussian Splatting Compression Kept Simple
KISS-GS is a modular compression pipeline for 3D Gaussian Splatting (3DGS) scenes that separates compression from training. It first compacts a vanilla 3DGS scene by 15.7× using state‑of‑the‑art pruning, then encodes the result into the SOG‑XT image‑based format, achieving an additional 6.6× reduction. Optional encoding‑aware fine‑tuning can further cut the size by 2.2×, yielding total reductions of 85× to 319× on standard benchmarks while enabling web‑native decoding.