AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

3D Open-Vocabulary Panoptic Segmentation with 2D-3D Vision-Language Distillation

Zihao Xiao, Longlong Jing, Shangxuan Wu, Alex Zihao Zhu, Jingwei Ji, Chiyu Max Jiang, Wei-Chih Hung, Thomas Funkhouser, Weicheng Kuo, Anelia Angelova, Yin Zhou, Shiwei Sheng

ECCV 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary semantic segmentation · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add voxel-level distillation loss L_V (ablation)Ours · nuScenes val (B12/N4)PQ: 56.3 -> 62.0Improved
add voxel-level distillation loss L_V (ablation)Ours · nuScenes val (B12/N4)PQ novel stuff: 0.2 -> 35.2Improved
add object-level distillation loss L_O (ablation)PFC + QA + fusion · nuScenes val (B12/N4)PQ novel things: 38.1 -> 43.8Improved
add object-level distillation loss L_O (ablation)PFC + QA + fusion · nuScenes val (B12/N4)PQ: 56.4 -> 56.3No clear effect
add multimodal LiDAR + CLIP feature fusion (ablation)PFC + QA · nuScenes val (B12/N4)PQ: 55.5 -> 56.4Improved
add fixed query set for base stuff classes (query assignment) (ablation)PFC · nuScenes val (B12/N4)PQ: 54.8 -> 55.5Improved
add query assignment (effect on novel classes) (ablation)PFC · nuScenes val (B12/N4)PQ novel things: 37.3 -> 35.7Hurt
replace 2D-style open-vocab model PFC with proposed fusion, single head and distillation lossesPFC baseline · SemanticKITTI val (B14/N5)PQ: 33.7 -> 42.2Improved
use a different base/novel split with 5 novel classesOurs · nuScenes val (B11/N5)PQ: 62.0 -> 52.8Hurt
train P3Former with base classes only vs open-vocab methodP3Former · nuScenes val base stuffPQ base stuff: 64.2 vs 69.2 (Ours)Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy