Pith. sign in

REVIEW 6 cited by

DynRsl-VLM: Enhancing Autonomous Driving Perception with Dynamic Resolution Vision-Language Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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

arxiv 2503.11265 v1 pith:RNXIXDIM submitted 2025-03-14 cs.CV

Xirui Zhou , Lianlei Shan , Xiaolin Gui This is my paper
classification cs.CV
keywords imageautonomousdrivingdynamicresolutioncomputationaldynrsl-vlmmodels
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Visual Question Answering (VQA) models, which fall under the category of vision-language models, conventionally execute multiple downsampling processes on image inputs to strike a balance between computational efficiency and model performance. Although this approach aids in concentrating on salient features and diminishing computational burden, it incurs the loss of vital detailed information, a drawback that is particularly damaging in end-to-end autonomous driving scenarios. Downsampling can lead to an inadequate capture of distant or small objects such as pedestrians, road signs, or obstacles, all of which are crucial for safe navigation. This loss of features negatively impacts an autonomous driving system's capacity to accurately perceive the environment, potentially escalating the risk of accidents. To tackle this problem, we put forward the Dynamic Resolution Vision Language Model (DynRsl-VLM). DynRsl-VLM incorporates a dynamic resolution image input processing approach that captures all entity feature information within an image while ensuring that the image input remains computationally tractable for the Vision Transformer (ViT). Moreover, we devise a novel image-text alignment module to replace the Q-Former, enabling simple and efficient alignment with text when dealing with dynamic resolution image inputs. Our method enhances the environmental perception capabilities of autonomous driving systems without overstepping computational constraints.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. TALSC: Timeliness-Aware Large-Small VLM Collaboration for Infrastructure-Assisted Autonomous Driving

    cs.DC 2026-08 reject novelty 5.0 of 10

    TALSC is a Lyapunov drift-plus-estimated-penalty scheduler that maximizes a fitted timeliness metric coupling Age of Information and visual token length for large-small VLM collaboration in autonomous driving.

  2. MAViE: A Multi-scale Adaptive Vision Encoder for Fine-grained Visual Perception and Efficient Multimodal Reasoning

    cs.CV 2026-07 reject novelty 4.0 of 10

    A multi-scale gated fusion plus question-conditioned token router is specified to cut VLM visual tokens ~80% while improving accuracy, but all reported gains are simulated placeholders.

  3. GDGS: 3D Gaussian Splatting Via Geometry-Guided Initialization And Dynamic Density Control

    cs.CV 2025-07 conditional novelty 4.0 of 10

    A 3DGS variant that adds MLP initialization, normal alignment, and region-aware density control reports consistent but modest quality gains over vanilla 3DGS on three standard benchmarks.

  4. A Survey on Vision-Language-Action Models for Autonomous Driving

    cs.CV 2025-06 conditional novelty 4.0 of 10

    A survey organizes vision-language-action models for autonomous driving into four stages, compares over 20 systems, and catalogs datasets, benchmarks, and open challenges.

  5. Building Lightweight Semantic Segmentation Models for Aerial Images Using Dual Relation Distillation

    eess.IV 2025-06 conditional novelty 4.0 of 10

    A student segmentation network trained with spatial and channel relation distillation from a PSPNet ResNet101 teacher gains about 3 to 5 mIoU points on Vaihingen, Potsdam, and Cityscapes.

  6. A Global-Local Cross-Attention Network for Ultra-high Resolution Remote Sensing Image Semantic Segmentation

    cs.CV 2025-06 reject novelty 3.0 of 10

    GLCANet is a dual-branch global-local attention network that reports top mIoU on DeepGlobe, Vaihingen, and Potsdam, but the method and experiments are internally inconsistent and lack code.

Pith tools