arXiv Computer Vision
LiPS: Lightweight Panoptic Segmentation for Resource-Constrained Robotics
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
Jun 30
GROW$^2$: Grounding Which and Where for Robot Tool Use
arXiv:2606. 30632v1 Announce Type: cross Abstract: Can the robot use a plate to cut a cake if no knife is available?
arXiv Computer Vision
4d ago
S4VY: Segment Anything in Feed-Forward 4D Visual Geometry
arXiv:2609.36875v1 Announce Type: new Abstract: Accurate instance segmentation in dynamic scenes is important for downstream applications such as robotics and autonomous driving. Existing Segment Any...
arXiv Computer Vision
Sep 1
CoRe-GS: Coarse-to-Refined Gaussian Splatting with Semantic Object Focus
arXiv:2509.04859v4 Announce Type: replace Abstract: Fast and efficient photorealistic 3D reconstruction with (semantic) Gaussian Splatting (GS) is crucial for time-critical robotic perception and nav...
arXiv Computer Vision
Sep 22
PanoSeg3R: Feed-Forward 3D Semantic Segmentation for Panoramic Images with an Automatic Data Curation Pipeline
arXiv:2609.22687v1 Announce Type: new Abstract: We present PanoSeg3R, a feed-forward framework for 3D panoramic semantic segmentation. Unlike existing methods designed for perspective inputs, PanoSeg...
arXiv Computer Vision
Sep 18
SenseFuse: Label-Free Fusion of Image and Shape Encoders for Open-Vocabulary 3D Instance Segmentation
SenseFuse introduces a label‑free fusion approach that balances 2D image and 3D shape encoders for open‑vocabulary 3D instance segmentation. By selecting a scene‑level fusion weight through an adaptive, sensitivity‑based mechanism, it improves mask labeling accuracy across multiple datasets, recovering up to 93% of the potential gain from an oracle weight. The method demonstrates that image and shape encoders have complementary failure patterns, leading to higher instance AP in most evaluated settings.
arXiv Computer Vision
Sep 24
VLMs Can Describe, But Not Measure: Object-Centric Scene Understanding for Robotic Manipulation
The paper introduces a modular perception framework that uses vision‑language models (VLMs) to annotate object‑level regions from a single RGB‑D observation, then grounds these annotations with depth data to build an object‑centric representation. Experiments on 151 tabletop scenes demonstrate that this decomposition maintains strong semantic performance while significantly improving localization and depth estimation compared to direct VLM inference. The resulting representation is integrated into a task‑planning system for robotic manipulation.