Learning Structural Latent Points for Efficient Visual Representations in Robotic Manipulation

• URL: http://arxiv.org/abs/2605.21258v1
• Date: Wed, 20 May 2026 14:48:01 GMT
• Title: Learning Structural Latent Points for Efficient Visual Representations in Robotic Manipulation
• Abstract summary: Implicit representations lack explicit structural cues, whereas explicit ones preserve geometry but suffer from resolution limits and weak generalization.<n>We propose a novel pretraining framework that learns a hybrid representation-structural latent points.<n>The resulting compact latent preserves coarse structural tendencies, which do not encode precise geometry but capture richer rough shape and semantic information.
• Score: 28.481044299307346
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Current 3D-aware pretraining methods for embodied perception and manipulation are largely built on differentiable rendering frameworks, producing either fully implicit neural fields or fully explicit geometric primitives. Implicit representations, while expressive, lack explicit structural cues, whereas explicit ones preserve geometry but suffer from resolution limits and weak generalization. To address these limitations, we propose a novel pretraining framework that learns a hybrid representation-structural latent points. Specifically, we insert a point-wise latent variational autoencoder into the latent space of a point-cloud autoencoder, jointly regularizing point-wise features and coordinates toward a Gaussian prior. The resulting compact latent preserves coarse structural tendencies, which do not encode precise geometry but capture richer rough shape and semantic information, effectively combining the expressiveness of implicit representations with the structural priors of explicit ones. In addition, informed by shared design choices in prior work, we develop a streamlined, efficient 3DGS-based rendering pipeline that is deliberately kept lightweight, improving efficiency while leaving greater representational capacity to the front-end latent module. Extensive evaluations on RLBench, ManiSkill2, and a real-robot platform demonstrate consistent gains in task success, sample efficiency, and robustness to viewpoint and scene variations over strong baselines. Ablation studies further confirm that each component of our framework is critical to overall performance.

Related papers

• A Persistent Homology Design Space for 3D Point Cloud Deep Learning [5.810033007426438]
  Persistent Homology (PH) offers stable, multi-scale descriptors of intrinsic shape structure.<n>Despite strong theoretical guarantees and increasing empirical adoption, its integration into deep learning for point clouds remains largely ad hoc and architecturally peripheral.<n>In this work, we introduce a unified design space for Persistent-Homology driven learning in 3D point clouds.
  arXiv  Detail & Related papers  (2026-04-05T22:38:37Z)
• Towards Foundation Models for 3D Scene Understanding: Instance-Aware Self-Supervised Learning for Point Clouds [53.82500407523346]
  PointINS is an instance-oriented self-supervised framework that enriches point cloud representations through geometry-aware learning.<n>PointINS achieves on average +3.5% mAP improvement for indoor instance segmentation and +4.1% PQ gain for outdoor panoptic segmentation.
  arXiv  Detail & Related papers  (2026-03-26T08:31:06Z)
• StepVAR: Structure-Texture Guided Pruning for Visual Autoregressive Models [98.72926158261937]
  We propose a training-free token pruning framework for Visual AutoRegressive models.<n>We employ a lightweight high-pass filter to capture local texture details, while leveraging Principal Component Analysis (PCA) to preserve global structural information.<n>To maintain valid next-scale prediction under sparse tokens, we introduce a nearest neighbor feature propagation strategy.
  arXiv  Detail & Related papers  (2026-03-02T11:35:05Z)
• SUG-Occ: An Explicit Semantics and Uncertainty Guided Sparse Learning Framework for Real-Time 3D Occupancy Prediction [5.730573889498275]
  We propose SUG-Occ, an explicit Semantics and Uncertainty Guided Sparse Learning Enabled 3D Occupancy Prediction Framework.<n>We first utilize semantic and uncertainty priors to suppress projections from free space during view transformation.<n>We then employ an explicit unsigned distance encoding to enhance geometric consistency, producing a structurally consistent sparse 3D representation.
  arXiv  Detail & Related papers  (2026-01-16T16:07:38Z)
• LOC: A General Language-Guided Framework for Open-Set 3D Occupancy Prediction [9.311605679381529]
  We propose LOC, a general language-guided framework adaptable to various occupancy networks.<n>For self-supervised tasks, we employ a strategy that fuses multi-frame LiDAR points for dynamic/static scenes, using Poisson reconstruction to fill voids, and assigning semantics to voxels via K-Nearest Neighbor (KNN)<n>Our model predicts dense voxel features embedded in the CLIP feature space, integrating textual and image pixel information, and classifies based on text and semantic similarity.
  arXiv  Detail & Related papers  (2025-10-25T03:27:19Z)
• Understanding and Improving Length Generalization in Hierarchical Sparse Attention Models [33.99822400076112]
  Chunk-based sparse attention has emerged as a promising paradigm for extreme length generalization.<n>We present a systematic dissection of these models to identify the core components driving their performance.<n>We establish a new state-of-the-art for training-free length extrapolation, successfully generalizing models trained on a 4K context to 32 million tokens on RULER and BABILong.
  arXiv  Detail & Related papers  (2025-10-20T06:17:57Z)
• Light-SQ: Structure-aware Shape Abstraction with Superquadrics for Generated Meshes [60.92139345612904]
  We present Light-SQ, a novel superquadric-based optimization framework.<n>We propose a block-regrow-fill strategy guided by structure-aware volumetric decomposition.<n>Experiments demonstrate that Light-SQ enables efficient, high-fidelity, and editable shape abstraction with superquadrics.
  arXiv  Detail & Related papers  (2025-09-29T16:18:32Z)
• "Principal Components" Enable A New Language of Images [79.45806370905775]
  We introduce a novel visual tokenization framework that embeds a provable PCA-like structure into the latent token space.<n>Our approach achieves state-of-the-art reconstruction performance and enables better interpretability to align with the human vision system.
  arXiv  Detail & Related papers  (2025-03-11T17:59:41Z)
• Human as Points: Explicit Point-based 3D Human Reconstruction from Single-view RGB Images [71.91424164693422]
  We introduce an explicit point-based human reconstruction framework called HaP.<n>Our approach is featured by fully-explicit point cloud estimation, manipulation, generation, and refinement in the 3D geometric space.<n>Our results may indicate a paradigm rollback to the fully-explicit and geometry-centric algorithm design.
  arXiv  Detail & Related papers  (2023-11-06T05:52:29Z)
• Convolutional Occupancy Networks [88.48287716452002]
  We propose Convolutional Occupancy Networks, a more flexible implicit representation for detailed reconstruction of objects and 3D scenes. By combining convolutional encoders with implicit occupancy decoders, our model incorporates inductive biases, enabling structured reasoning in 3D space. We empirically find that our method enables the fine-grained implicit 3D reconstruction of single objects, scales to large indoor scenes, and generalizes well from synthetic to real data.
  arXiv  Detail & Related papers  (2020-03-10T10:17:07Z)

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.