Reinforcing 3D Understanding in Point-VLMs via Geometric Reward Credit Assignment

• URL: http://arxiv.org/abs/2604.21160v1
• Date: Thu, 23 Apr 2026 00:01:40 GMT
• Title: Reinforcing 3D Understanding in Point-VLMs via Geometric Reward Credit Assignment
• Abstract summary: We propose a framework that disentangles holistic supervision into field-specific signals and routes them exclusively to their responsible token spans.<n>Our approach bridges the reliability gap by boosting 3D KPA from 0.64 to 0.93, increasing 3D bounding box intersection over union to 0.686, and raising reprojection consistency scores to 0.852.
• Score: 45.205992501478256
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Point-Vision-Language Models promise to empower embodied agents with executable spatial reasoning, yet they frequently succumb to geometric hallucination where predicted 3D structures contradict the observed 2D reality. We identify a key cause of this failure not as a representation bottleneck but as a structural misalignment in reinforcement learning, where sparse geometric tokens are drowned out by noisy and broadcasted sequence-level rewards. To resolve this causal dilution, we propose Geometric Reward Credit Assignment, a framework that disentangles holistic supervision into field-specific signals and routes them exclusively to their responsible token spans. This mechanism transforms vague feedback into precise gradient updates and effectively turns generic policy optimization into targeted structural alignment. Furthermore, we internalize physical constraints via a Reprojection-Consistency term which serves as a cross-modal verifier to penalize physically impossible geometries. Validated on a calibrated benchmark derived from ShapeNetCore, our approach bridges the reliability gap by boosting 3D KPA from 0.64 to 0.93, increasing 3D bounding box intersection over union to 0.686, and raising reprojection consistency scores to 0.852. Crucially, these gains are achieved while maintaining robust 2D localization performance, marking a meaningful step from plausible textual outputs toward physically verifiable spatial predictions.

Related papers

• Stable and Scalable Bundle Adjustment of Holistic 3D Structures [99.03818732955783]
  We present a new version of Bundle Adjustment (BA) for 3D computer vision.<n>BA is developed to jointly optimize cameras, poses and 3D points.<n>By group-induced measurements and cross-feature reprojection, we preserve the sparsity of classical point-only 3D regularization.
  arXiv  Detail & Related papers  (2026-09-03T16:08:03Z)
• Reliability-Aware 3D Geometric Injection for Universal Person Re-identification [47.874819213762926]
  We propose a Universal Monocular 3D-Enhanced ReID framework driven by a Consistency-Aware Reliability Gate and Dual-Stream Residual Fusion.<n>Our method improves challenging, structure-sensitive scenarios while preserving competitive performance on clean domains.
  arXiv  Detail & Related papers  (2026-07-21T08:54:25Z)
• FDR-Occ: Factorized Dense Routing for Full-Spectrum 3D Occupancy Prediction [63.738631229597274]
  Vision-based 3D occupancy prediction fundamentally relies on the 2D-to-3D view transformation.<n>Current paradigms predominantly utilize explicit physical projection, which artificially restricts the routing matrix to strict, sparse camera rays.<n>We propose Factorized Dense Routing (FDR) to break this bottleneck.<n>Our framework achieves state-the-art performance on the Occ3D-nuScenes and Occ3D-Waymo benchmarks.
  arXiv  Detail & Related papers  (2026-07-04T11:12:42Z)
• Robust 3D Alignment of Generative Reconstructions via Partial Monocular Observations [46.983222121901235]
  Generative-to-Partial Monocular Observational Alignment is a critical but under-explored challenge in computer vision.<n>We propose a training-free and interpretable geometric alignment framework that grounds generative 3D priors via a 3D similarity transformation.<n>Experiments demonstrate that our method achieves stable and accurate registration, substantially outperforming both classical geometric pipelines and state-of-the-art learning-based baselines.
  arXiv  Detail & Related papers  (2026-07-01T06:30:47Z)
• LG-HCC: Local Geometry-Aware Hierarchical Context Compression for 3D Gaussian Splatting [77.81227097905865]
  Anchor-based 3DGS compression schemes reduce gaussian redundancy through some advanced context models.<n>We propose a Local Geometry-aware Hierarchical Context Compression framework for 3DGS that incorporates inter-anchor geometric correlations into anchor pruning and entropy coding for compact representation.<n>Experiments show that LG-HCC effectively alleviates structural preservation issues,achieving superior geometric integrity and rendering fidelity while reducing storage by up to 30.85x compared to the Scaffold-GS baseline on the Mip-NeRF360 dataset.
  arXiv  Detail & Related papers  (2026-03-30T13:39:35Z)
• 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)
• SpatialFly: Geometry-Guided Representation Alignment for UAV Vision-and-Language Navigation in Urban Environments [49.966170814478915]
  We propose a geometry-guided spatial representation framework for UAV VLN.<n>Running on RGB observations without explicit 3D reconstruction, SpatialFly introduces a geometry-guided 2D representation alignment mechanism.<n> Experimental results show that SpatialFly consistently outperforms state-of-the-art UAV VLN baselines across both seen and unseen environments.
  arXiv  Detail & Related papers  (2026-03-22T03:56:58Z)
• Shape-of-You: Fused Gromov-Wasserstein Optimal Transport for Semantic Correspondence in-the-Wild [7.4746628878102195]
  Shape-of-You is an unsupervised learning framework for semantic correspondence.<n>It achieves state-of-the-art performance on SPair-71k and AP-10k datasets.
  arXiv  Detail & Related papers  (2026-03-12T07:22:03Z)
• SPAN: Spatial-Projection Alignment for Monocular 3D Object Detection [49.12928389918159]
  Existing monocular 3D detectors typically tame the pronounced nonlinear regression of 3D bounding box through decoupled prediction paradigm.<n>We propose novel Spatial-Projection Alignment (SPAN) with two pivotal components.<n>SPAN enforces an explicit global spatial constraint between the predicted and ground-truth 3D bounding boxes, thereby rectifying spatial drift caused by decoupled attribute regression.<n>3D-2D Projection Alignment ensures that the projected 3D box is aligned tightly within its corresponding 2D detection bounding box on the image plane, mitigating projection misalignment overlooked in previous works.
  arXiv  Detail & Related papers  (2025-11-10T04:48:48Z)
• CAGE: Continuity-Aware edGE Network Unlocks Robust Floorplan Reconstruction [24.09888364478496]
  We present CAGE, a robust framework for reconstructing vector floorplans directly from point-cloud density maps.<n>CAGE achieves state-of-the-art performance, with F1 scores of 99.1% (rooms), 91.7% (corners), and 89.3% (angles)
  arXiv  Detail & Related papers  (2025-09-18T22:10:37Z)
• Robust Self-Supervised LiDAR Odometry via Representative Structure Discovery and 3D Inherent Error Modeling [67.75095378830694]
  We develop a two-stage odometry estimation network, where we obtain the ego-motion by estimating a set of sub-region transformations. In this paper, we aim to alleviate the influence of unreliable structures in training, inference and mapping phases. Our two-frame odometry outperforms the previous state of the arts by 16%/12% in terms of translational/rotational errors.
  arXiv  Detail & Related papers  (2022-02-27T12:52:27Z)

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.