arXiv Computer Vision September 18, 2026 By Euiseok Han, Tri Ton, Hwanhee Kim, Seungyeon Ryu, Chang D. Yoo

SenseFuse: Label-Free Fusion of Image and Shape Encoders for Open-Vocabulary 3D Instance Segmentation

Read the original on arXiv Computer Vision →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv AI

Jul 21

CDIS: Cross-Dimensional Class-Agnostic 3D Instance Segmentation via 2D Mask Tracking and 3D-2D Projection Merging

arXiv:2607. 17778v1 Announce Type: cross Abstract: Class-agnostic 3D instance segmentation is critical for robotic systems operating in unknown environments, enabling perception of previously unseen objects for reliable manipulation and navigation.

By Juno Kim, Hye-Jung Yoon, Yesol Park, Byoung-Tak Zhang

computer-vision robotics benchmarks

arXiv Computer Vision

Aug 24

Stream3Dv2: Geometric-Semantic Fusion Enhanced Streaming Zero-Shot 3D Scene Understanding

arXiv:2608.21136v1 Announce Type: new Abstract: Recently, open-vocabulary zero-shot 3D scene understanding using vision foundation models has emerged as a promising alternative to data-intensive supe...

By Jie Xu, Na Zhao

llms agents computer-vision robotics

arXiv AI

Jul 8

Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction

arXiv:2607. 05568v1 Announce Type: cross Abstract: Representing 3D shapes as compact sets of geometric primitives is fundamental to robotics, simulation, and scene understanding.

By Gregor Kobsik, Tim Elsner, Leif Kobbelt

llms computer-vision robotics fine-tuning multimodal

Hugging Face Trending Papers

Jul 20

CDIS: Cross-Dimensional Class-Agnostic 3D Instance Segmentation via 2D Mask Tracking and 3D-2D Projection Merging

Class-agnostic 3D instance segmentation is critical for robotic systems operating in unknown environments, enabling perception of previously unseen objects for reliable manipulation and navigation. Existing approaches typically project per-frame 2D instance masks into 3D and merge them, which often breaks object identities across time and yields fragmented 3D instances.

computer-vision robotics benchmarks

arXiv AI

Jul 21

OV-MAP: Open-Vocabulary Zero-Shot 3D Instance Segmentation Map for Robots

arXiv:2506. 11585v2 Announce Type: replace-cross Abstract: We introduce OV-MAP, a novel approach to open-world 3D mapping for mobile robots by integrating open-features into 3D maps to enhance object recognition capabilities.

By Juno Kim, Yesol Park, Hye-Jung Yoon, Byoung-Tak Zhang

computer-vision robotics

arXiv Machine Learning

Jun 24

Open-Vocabulary BEV Segmentation with 3D-Aware Geometric Constraints

arXiv:2606. 24353v1 Announce Type: cross Abstract: Bird's-eye view (BEV) perception fuses multi-camera images into a unified top-down representation for autonomous driving.

By Hojun Choi, Seulbin Hwang, Dae Jung Kim, Kisung Kim, Hyunjung Shim, Jinhan Lee

llms agents computer-vision robotics efficiency multimodal benchmarks

One email a morning, machine-written

Related stories

CDIS: Cross-Dimensional Class-Agnostic 3D Instance Segmentation via 2D Mask Tracking and 3D-2D Projection Merging

Stream3Dv2: Geometric-Semantic Fusion Enhanced Streaming Zero-Shot 3D Scene Understanding

Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction

CDIS: Cross-Dimensional Class-Agnostic 3D Instance Segmentation via 2D Mask Tracking and 3D-2D Projection Merging

OV-MAP: Open-Vocabulary Zero-Shot 3D Instance Segmentation Map for Robots

Open-Vocabulary BEV Segmentation with 3D-Aware Geometric Constraints