N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models Paper • 2512.16561 • Published 13 days ago • 19
RePlan: Reasoning-guided Region Planning for Complex Instruction-based Image Editing Paper • 2512.16864 • Published 13 days ago • 10
MotionEdit: Benchmarking and Learning Motion-Centric Image Editing Paper • 2512.10284 • Published 20 days ago • 25
TAPIP3D: Tracking Any Point in Persistent 3D Geometry Paper • 2504.14717 • Published Apr 20 • 8
Gaussian Grouping: Segment and Edit Anything in 3D Scenes Paper • 2312.00732 • Published Dec 1, 2023 • 3