arXiv Computer Vision
VaViT: Vanilla ViT for Automotive Point Cloud Semantic 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 26
IGLOSS: Image Generation for Lidar Open-vocabulary Semantic Segmentation
IGLOSS introduces a zero‑shot open‑vocabulary semantic segmentation approach for 3D automotive LiDAR data. The method generates prototype images from text to bridge the image‑text modality gap, then matches 3D point features with 2D image features derived from a Vision Foundation Model. It achieves state‑of‑the‑art results on nuScenes and SemanticKITTI, with code, models, and images publicly available.
arXiv Computer Vision
Oct 16
SpaceCache: Intermediate Feature Reuse for Efficient Semantic Segmentation on Point Cloud Streams
SpaceCache is a training‑free feature cache that reuses intermediate features from point‑cloud transformers across consecutive frames, allowing tokens of previously seen regions to skip transformer blocks and only compute new tokens. The method limits cache entry age and evicts low‑confidence entries to maintain reliability, and it operates once per encoder stage at negligible cost. Experiments on outdoor and indoor datasets (nuScenes, Waymo, ScanNet) with Utonia and LitePT‑B backbones show up to 1.65× speedup with less than 1‑point mIoU loss, outperforming token‑merging approaches.
arXiv Computer Vision
Sep 16
SSC-Priors: Exploring Semantic and Visibility Priors to Boost Lidar Semantic Scene Completion
arXiv:2609.17413v1 Announce Type: new Abstract: This paper investigates easy strategies to boost the performance of existing networks for lidar semantic scene completion (SSC) without requiring compl...
arXiv Machine Learning
Jun 9
SegmentAnyTreeV2: Scaling Transformer-Based Tree Instance Segmentation Across Sensors, Platforms, and Forests
arXiv:2606. 08206v1 Announce Type: cross Abstract: We present SegmentAnyTreeV2, a sensor- and platform-agnostic framework for semantic and instance segmentation of forest point clouds.
arXiv Computer Vision
Sep 17
Decoder-Agnostic Token Merging for Vision Transformers: A Systematic Study of G2TM
The paper studies Graph-Guided Token Merging (G2TM), a module that reduces token count in Vision Transformers. It evaluates G2TM across multiple segmentation frameworks and decoder types, finding that its performance gains are tied to the encoder rather than the decoder. The authors report consistent reductions in GFLOPs (22‑47%) and throughput improvements (up to 74%) on ADE20K, with optimal hyperparameters depending mainly on backbone pre‑training and target dataset.
arXiv Computer Vision
Sep 10
CLFTv2: Efficient Camera-LiDAR Fusion for Semantic Segmentation via Hierarchical Feature Pyramids
arXiv:2609.09881v1 Announce Type: new Abstract: Semantic segmentation for autonomous driving requires reliable detection of vulnerable road users (VRUs) despite heavy class imbalance. We introduce CL...