LAMP: Lift Image-Editing as General 3D Priors for Open-world Manipulation

• URL: http://arxiv.org/abs/2604.08475v1
• Date: Thu, 09 Apr 2026 17:14:00 GMT
• Title: LAMP: Lift Image-Editing as General 3D Priors for Open-world Manipulation
• Abstract summary: We propose LAMP, which lifts image-editing as 3D priors to extract inter-object 3D transformations as continuous, geometry-aware representations.<n>Our key insight is that image-editing inherently encodes rich 2D spatial cues, and lifting these implicit cues into 3D transformations provides fine-grained and accurate guidance for open-world manipulation.
• Score: 33.021510263749455
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Human-like generalization in open-world remains a fundamental challenge for robotic manipulation. Existing learning-based methods, including reinforcement learning, imitation learning, and vision-language-action-models (VLAs), often struggle with novel tasks and unseen environments. Another promising direction is to explore generalizable representations that capture fine-grained spatial and geometric relations for open-world manipulation. While large-language-model (LLMs) and vision-language-model (VLMs) provide strong semantic reasoning based on language or annotated 2D representations, their limited 3D awareness restricts their applicability to fine-grained manipulation. To address this, we propose LAMP, which lifts image-editing as 3D priors to extract inter-object 3D transformations as continuous, geometry-aware representations. Our key insight is that image-editing inherently encodes rich 2D spatial cues, and lifting these implicit cues into 3D transformations provides fine-grained and accurate guidance for open-world manipulation. Extensive experiments demonstrate that \codename delivers precise 3D transformations and achieves strong zero-shot generalization in open-world manipulation. Project page: https://zju3dv.github.io/LAMP/.

Related papers

• Occ-VLM: Occupancy Grounded Vision Language Model for Indoor Scene Understanding [31.76161781831759]
  We propose Occ-VLM, a novel framework for 3D scene understanding that operates purely on posed RGB images and employs a single 2D vision encoder.<n>Occ-VLM achieves both accurate geometric perception and robust vision-language reasoning.
  arXiv  Detail & Related papers  (2026-06-18T04:24:28Z)
• R2RDreamer: 3D-aware Data Augmentation for Spatially-generalized 2D Manipulation Policies [86.2249156068836]
  R2RDreamer is a real-to-real demonstration augmentation framework.<n>It preserves the geometric consistency of 3D action-observation editing while moving visual completion to 2D video space.
  arXiv  Detail & Related papers  (2026-06-15T17:56:19Z)
• Dexterity-BEV: Aligning 3D World and Actions for Generalizable Robot Policies Learning [51.799524981291235]
  End-to-end manipulation policies show promise for generalizable and dexterous robotic manipulation.<n>They inherit two key limitations from 2D foundation models.<n>We present a series of contributions to address these issues.
  arXiv  Detail & Related papers  (2026-06-01T14:01:11Z)
• Robotic Manipulation is Vision-to-Geometry Mapping ($f(v) \ ightarrow G$): Vision-Geometry Backbones over Language and Video Models [65.05130114320734]
  We argue that the foundation for generalizable robotic control should be a vision-geometry backbone, rather than the widely adopted vision-language or video models.<n>We propose the Vision-Geometry-Action model, which directly conditions action generation on pretrained native 3D representations.<n> Specifically, VGA replaces conventional language or video backbones with a pretrained 3D world model, establishing a seamless vision-to-geometry mapping.
  arXiv  Detail & Related papers  (2026-04-14T15:57:16Z)
• Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding [50.098085774845195]
  We propose a paradigm shift by leveraging the implicit spatial prior within large-scale generation models.<n>We introduce GeneEGA-3D (Video Extracted Generative Awareness), a plug-and-play framework that repurposes a pre-trained video diffusion model as a Latent World Simulator.
  arXiv  Detail & Related papers  (2026-03-19T17:59:58Z)
• GALA: Guided Attention with Language Alignment for Open Vocabulary Gaussian Splatting [74.56128224977279]
  We present GALA, a novel framework for open-vocabulary 3D scene understanding with 3D Gaussian Splatting (3DGS)<n>GALA distills a scene-specific 3D instance feature field via self-supervised contrastive learning.<n>It supports seamless 2D and 3D open-vocabulary queries and reduces memory consumption by avoiding per-Gaussian high-dimensional feature learning.
  arXiv  Detail & Related papers  (2025-08-19T21:26:49Z)
• UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encoding [65.60549881706959]
  We introduce UniUGG, the first unified understanding and generation framework for 3D modalities.<n>Our framework employs an LLM to comprehend and decode sentences and 3D representations.<n>We propose a spatial decoder leveraging a latent diffusion model to generate high-quality 3D representations.
  arXiv  Detail & Related papers  (2025-08-16T07:27:31Z)
• AGO: Adaptive Grounding for Open World 3D Occupancy Prediction [16.994671814016616]
  AGO is a novel 3D occupancy prediction framework with adaptive grounding to handle diverse open-world scenarios.<n>A modality adapter maps 3D embeddings into a space aligned with VLM-derived image embeddings, reducing modality gaps.<n> Experiments on Occ3D-nuScenes show that AGO improves unknown object prediction in zero-shot and few-shot transfer.
  arXiv  Detail & Related papers  (2025-04-14T11:26:20Z)
• Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation [44.58709274218105]
  This work bridges the 2D-to-3D gap for robotic manipulation by leveraging distilled feature fields to combine accurate 3D geometry with rich semantics from 2D foundation models. We present a few-shot learning method for 6-DOF grasping and placing that harnesses these strong spatial and semantic priors to achieve in-the-wild generalization to unseen objects.
  arXiv  Detail & Related papers  (2023-07-27T17:59:14Z)
• CLIP$^2$: Contrastive Language-Image-Point Pretraining from Real-World Point Cloud Data [80.42480679542697]
  We propose Contrastive Language-Image-Point Cloud Pretraining (CLIP$2$) to learn the transferable 3D point cloud representation in realistic scenarios. Specifically, we exploit naturally-existed correspondences in 2D and 3D scenarios, and build well-aligned and instance-based text-image-point proxies from those complex scenarios.
  arXiv  Detail & Related papers  (2023-03-22T09:32:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.