GT-PCQA: Geometry-Texture Decoupled Point Cloud Quality Assessment with MLLM

• URL: http://arxiv.org/abs/2603.14951v1
• Date: Mon, 16 Mar 2026 08:04:30 GMT
• Title: GT-PCQA: Geometry-Texture Decoupled Point Cloud Quality Assessment with MLLM
• Abstract summary: We propose a novel MLLM-based no-reference PCQA framework, GT-PCQA, built upon two key strategies.<n>First, to enable stable and effective instruction tuning under scarce PCQA supervision, a 2D-3D joint training strategy is proposed.<n>Second, a geometry-texture decoupling strategy is presented, which integrates a dual-prompt mechanism with an alternating optimization scheme to mitigate the inherent texture-dominant bias of pre-trained MLLMs.
• Score: 93.22843816779255
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With the rapid advancement of Multi-modal Large Language Models (MLLMs), MLLM-based Image Quality Assessment (IQA) methods have shown promising generalization. However, directly extending these MLLM-based IQA methods to PCQA remains challenging. On the one hand, existing PCQA datasets are limited in scale, which hinders stable and effective instruction tuning of MLLMs. On the other hand, due to large-scale image-text pretraining, MLLMs tend to rely on texture-dominant reasoning and are insufficiently sensitive to geometric structural degradations that are critical for PCQA. To address these gaps, we propose a novel MLLM-based no-reference PCQA framework, termed GT-PCQA, which is built upon two key strategies. First, to enable stable and effective instruction tuning under scarce PCQA supervision, a 2D-3D joint training strategy is proposed. This strategy formulates PCQA as a relative quality comparison problem to unify large-scale IQA datasets with limited PCQA datasets. It incorporates a parameter-efficient Low-Rank Adaptation (LoRA) scheme to support instruction tuning. Second, a geometry-texture decoupling strategy is presented, which integrates a dual-prompt mechanism with an alternating optimization scheme to mitigate the inherent texture-dominant bias of pre-trained MLLMs, while enhancing sensitivity to geometric structural degradations. Extensive experiments demonstrate that GT-PCQA achieves competitive performance and exhibits strong generalization.

Related papers

• PCQA-R1: Advancing Generalized 3D Point Cloud Quality Assessment with Reinforcement Learning [51.75061005702151]
  No-reference point cloud quality assessment (PCQA) has been an active topic in recent years and is used to measure and optimize the visual experience of point clouds.<n>We present PCQA-R1, the first reinforcement learning LMM for 3D point cloud quality assessment to simultaneously model quality understanding and scoring.
  arXiv  Detail & Related papers  (2026-08-19T07:21:58Z)
• Evaluation of AutoML Frameworks for IDS under Imbalanced Data Conditions of the NSL-KDD Dataset [0.0]
  This work investigates the impact of severe class imbalance on the performance of automated machine learning (AutoML) frameworks for network intrusion detection.<n>We preserve the original five-class distribution, including highly underrepresented attacks such as R2L and U2R.<n>Nine open-source AutoML frameworks were analyzed under a unified and reproducible experimental protocol.
  arXiv  Detail & Related papers  (2026-06-10T19:08:25Z)
• IQA-Spider: Unifying Multi-Granularity Image Quality Assessment with Reasoning, Grounding and Referring [17.642234624165685]
  We present IQA-Spider, the first image quality assessment (IQA) framework that unifies reasoning, grounding, and referring into a single LMM-based framework for multi-granularity quality understanding.
  arXiv  Detail & Related papers  (2026-05-23T12:39:37Z)
• DPC-VQA: Decoupling Quality Perception and Residual Calibration for Video Quality Assessment [49.02765249211074]
  multimodal large language models (MLLMs) have shown promising performance on video quality assessment (VQA) tasks.<n>Adapting them to new scenarios remains expensive due to large-scale retraining and costly mean opinion score (MOS) annotations.<n>We propose DPC-VQA, a decoupling perception and calibration framework for video quality assessment.
  arXiv  Detail & Related papers  (2026-04-14T14:40:23Z)
• FLRQ: Faster LLM Quantization with Flexible Low-Rank Matrix Sketching [4.01326804806241]
  We introduce Rank1-Sketch-based Flexible Rank Selection (R1-FLR) and Best Low-rank Approximation under Clipping (BLC)<n>R1-FLR applies the R1-Sketch with Gaussian projection for the fast low-rank approximation, enabling outlier-aware rank extraction for each layer.<n>BLC aims at minimizing the low-rank quantization error under the scaling and clipping strategy.
  arXiv  Detail & Related papers  (2026-01-09T10:06:45Z)
• ALARM: Automated MLLM-Based Anomaly Detection in Complex-EnviRonment Monitoring with Uncertainty Quantification [16.05388703860442]
  In this paper, we introduce our UQ-supported MLLM-based visual anomaly detection framework called ALARM.<n>AlARM integrates quality-assurance techniques like reasoning chain, self-reflection, and MLLM ensemble for robust and accurate performance.<n> Extensive empirical evaluations are conducted using the real-world smart-home benchmark data and wound image classification data, which shows ALARM's superior performance and its generic applicability across different domains for reliable decision-making.
  arXiv  Detail & Related papers  (2025-12-01T19:03:14Z)
• Continual Action Quality Assessment via Adaptive Manifold-Aligned Graph Regularization [53.82400605816587]
  Action Quality Assessment (AQA) quantifies human actions in videos, supporting applications in sports scoring, rehabilitation, and skill evaluation.<n>A major challenge lies in the non-stationary nature of quality distributions in real-world scenarios.<n>We introduce Continual AQA (CAQA), which equips with Continual Learning capabilities to handle evolving distributions.
  arXiv  Detail & Related papers  (2025-10-08T10:09:47Z)
• ALOPE: Adaptive Layer Optimization for Translation Quality Estimation using Large Language Models [8.518082319087375]
  Large Language Models (LLMs) have shown remarkable performance across a wide range of natural language processing tasks.<n>QE for Machine Translation (MT) assesses the quality of a source-target pair without relying on reference translations.<n>This paper introduces ALOPE, an adaptive layer-optimization framework designed to enhance LLM-based QE.
  arXiv  Detail & Related papers  (2025-08-10T20:59:44Z)
• Test-Time Alignment for Large Language Models via Textual Model Predictive Control [63.508812485566374]
  Textual Model Predictive Control (TMPC) is a novel predictive planning framework adapted for aligning Large Language Models at inference time.<n>TMPC is evaluated on three tasks with distinct segmentation properties: discourse-level translation, long-form response generation, and program synthesis.<n>Results demonstrate that TMPC consistently improves performance, highlighting the generality.
  arXiv  Detail & Related papers  (2025-02-28T07:24:33Z)
• Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function Optimization [49.362750475706235]
  Reinforcement Learning (RL) plays a crucial role in aligning large language models with human preferences and improving their ability to perform complex tasks.<n>We introduce Direct Q-function Optimization (DQO), which formulates the response generation process as a Markov Decision Process (MDP) and utilizes the soft actor-critic (SAC) framework to optimize a Q-function directly parameterized by the language model.<n> Experimental results on two math problem-solving datasets, GSM8K and MATH, demonstrate that DQO outperforms previous methods, establishing it as a promising offline reinforcement learning approach for aligning language models.
  arXiv  Detail & Related papers  (2024-10-11T23:29:20Z)
• NeuralQP: A General Hypergraph-based Optimization Framework for Large-scale QCQPs [8.503330120957052]
  This paper introduces NeuralQP, a general hypergraph-based framework for large-scale Quadratically Constrained Quadratic Programs (QCQPs) We prove that our framework UniEGNN with our hypergraph representation is equivalent to the Interior-Point Method (IPM) for quadratic programming. Experiments on two benchmark problems and large-scale real-world instances from QPLIB demonstrate that NeuralQP outperforms state-of-the-art solvers.
  arXiv  Detail & Related papers  (2024-09-28T10:42:47Z)
• Few-Shot Image Quality Assessment via Adaptation of Vision-Language Models [93.91086467402323]
  Gradient-Regulated Meta-Prompt IQA Framework (GRMP-IQA) designed to efficiently adapt the visual-language pre-trained model, CLIP, to IQA tasks.<n> GRMP-IQA consists of two core modules: (i) Meta-Prompt Pre-training Module and (ii) Quality-Aware Gradient Regularization.
  arXiv  Detail & Related papers  (2024-09-09T07:26:21Z)

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.