REVIEW 8 cited by
Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation
read the original abstract
Self-supervised and language-supervised image models contain rich knowledge of the world that is important for generalization. Many robotic tasks, however, require a detailed understanding of 3D geometry, which is often lacking in 2D image features. This work bridges this 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. Using features distilled from a vision-language model, CLIP, we present a way to designate novel objects for manipulation via free-text natural language, and demonstrate its ability to generalize to unseen expressions and novel categories of objects.
Forward citations
Cited by 8 Pith papers
-
Beyond World-Frame Action Heads: Motion-Centric Action Frames for Vision-Language-Action Models
MCF-Proto adds a motion-centric local action frame and prototype parameterization to VLA models, inducing emergent geometric structure and improved robustness from standard demonstrations alone.
-
Action Images: End-to-End Policy Learning via Multiview Video Generation
Action Images turn robot arm motions into interpretable multiview pixel videos, letting video backbones serve as zero-shot policies for end-to-end robot learning.
-
Reconstruction by Generation: 3D Multi-Object Scene Reconstruction from Sparse Observations
RecGen achieves state-of-the-art 3D multi-object scene reconstruction from sparse RGB-D views by combining compositional synthetic scene generation with strong 3D shape priors, outperforming SAM3D by 30%+ in shape qua...
-
C3G: Learning Compact 3D Representations with 2K Gaussians
C3G creates compact 3D Gaussian representations with 2K points by guiding placement via learnable tokens that aggregate multi-view features through attention, yielding better efficiency and performance than dense methods.
-
3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations
DP3 uses compact 3D representations from sparse point clouds inside diffusion policies to learn generalizable visuomotor skills from few demonstrations, reporting 24% gains in simulation and 85% success on real robots.
-
Beyond Point-Attached Semantics: Object-Centric Semantic Fields for Generalizable Manipulation
An object-conditioned continuous semantic field queried at explicit 3D locations yields more stable part cues and higher manipulation success than point-attached 2D/3D features.
-
PhysGraph: A Physics-aware 3D Scene Graph for Perception and Reasoning
PhysGraph reconstructs object-centric 3D geometry from RGB-D, decomposes objects into parts, infers materials and articulations via visual reasoning, and reports SOTA results on semantic segmentation, multi-object mas...
-
Robotic Grasping and Placement Controlled by EEG-Based Hybrid Visual and Motor Imagery
A hybrid visual-motor imagery EEG decoder controls a robot for grasping and placement at 40% and 63% accuracy respectively, yielding 21% end-to-end task success in cue-free online use.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.