AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

SAM4D: Segment Anything in Camera and LiDAR Streams

Jianyun Xu, Song Wang, Ziqian Ni, Chunyong Hu, Sheng Yang, Jianke Zhu, Qiang Li

ICCV 2025 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 10 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 ego-motion compensation in memory attention (ablation)SAM4D · Waymo-4DSeg semi-supervised stream segmentationLiDAR NMP: 746 -> 582Improved
add ego-motion compensation in memory attention (ablation)SAM4D · Waymo-4DSeg semi-supervised stream segmentationLiDAR mIoU (%): 52.2 -> 55.7Improved
add ego-motion compensation in memory attention (ablation)SAM4D · Waymo-4DSeg semi-supervised stream segmentationImage mIoU (%): 69.7 -> 69.8No clear effect
add LiDAR input to camera-only model (ablation)SAM4D-C · Waymo-4DSeg semi-supervised stream segmentationImage NMP: 301 -> 280Improved
add LiDAR input to camera-only model (ablation)SAM4D-C · Waymo-4DSeg semi-supervised stream segmentationImage mIoU (%): 68.6 -> 69.8Improved
add camera input to LiDAR-only model (ablation)SAM4D-L · Waymo-4DSeg semi-supervised stream segmentationLiDAR mIoU (%): 47.0 -> 55.7Improved
use SAM4D multimodal model instead of SAM2 plus projectionSAM2+Project · Waymo-4DSeg semi-supervised stream segmentationLiDAR mIoU (%): 32.0 -> 55.7Improved
increase resolution to image 768 and voxel 0.15 m (ablation)SAM4D · Waymo-4DSeg semi-supervised stream segmentationImage mIoU (%): 60.5 -> 69.8Improved
increase resolution to image 768 and voxel 0.15 m (ablation)SAM4D · Waymo-4DSeg semi-supervised stream segmentationLiDAR NMP: 985 -> 582Improved
fine-tune on nuScenes instead of zero-shotSAM4D · nuScenes semi-supervised stream segmentationLiDAR mIoU (%): 25.9 -> 44.8Improved
use 3 clicks instead of 1 click (LiDAR-prompted)SAM4D · Waymo-4DSeg cross-modal frame segmentation (LiDAR-prompted)Image mIoU (%): 49.6 -> 64.2Improved
use bounding box instead of 3 clicks (image-prompted)SAM4D · Waymo-4DSeg cross-modal frame segmentation (image-prompted)LiDAR mIoU (%): 53.1 -> 47.0Hurt

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