3DZip: Spatial-Aware Feature Diversity-Guided Token Compression for 3D Question Answering
Summary
3DZip is a three-stage token compression framework for 3D vision-language models that uses voxelization, diversity-guided anchor selection, and spatial constraint merging to reduce tokens while preserving spatial reasoning. It retains 94.7% of original performance with only 128 tokens and achieves 1.92x faster inference on 3DQA benchmarks.
View Cached Full Text
Cached at: 08/04/26, 09:38 AM
Paper page - 3DZip: Spatial-Aware Feature Diversity-Guided Token Compression for 3D Question Answering
Source: https://huggingface.co/papers/2608.01185
Abstract
Recent3Dvision-languagemodels(3DVLMs)constructgeometryawaretokensbyprojecting2Dvisualfeaturesintoworldcoordinates,enablingspatialreasoningfortaskssuchas3Dquestionanswering.However,thisdesigngeneratesthousandsoftokensperscene,resultinginsubstantialcomputationalandmemoryoverhead.Whiletokencompressionhasbeenextensivelystudiedin2DVLMs,existingapproachesrelyonsemanticrelevanceorattention-basedselectionthatoverlookthestructuredspatialnatureof3Dtokens.Moreover,redundancyin3Drepresentationscannotberesolvedbyspatialproximityalone,asobject-leveltokenimbalancepersistsevenafterspatialaggregation.Toaddressthis,wepropose3DZip,athree-stagetokencompressionframeworkthatfirstappliescoarsevoxelizationtoremovepoint-levelredundancy,thenselectsanchortokensbasedonfeature-spacediversityviaaDeterminantalPointProcess,andfinallymergesremainingtokensunderspatialconstraintstopreservegeometriccoherence.Experimentsonthree3Dquestionansweringbenchmarksdemonstratethat3DZipconsistentlyoutperformsexistingcompressionmethods,retaining94.7%oftheoriginalperformancewithonly128tokens,achievinga1.92timesfasterinferencespeed.
View arXiv pageView PDFProject pageGitHub13Add to collection
Get this paper in your agent:
hf papers read 2608\.01185
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2608.01185 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2608.01185 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2608.01185 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
ZipTok3D: High-Fidelity 3D Tokenization with Compact Token Prefixes
ZipTok3D is a 3D tokenizer that achieves high-fidelity reconstruction from extremely short token sequences by organizing geometry into compact global-token prefixes and using iterative decoding, outperforming baselines with significantly reduced token lengths.
Beyond 3D VQAs: Injecting 3D Spatial Priors into Vision-Language Models for Enhanced Geometric Reasoning
This paper proposes GASP, a framework that injects geometric priors into vision-language models via deep supervision with contrastive and depth consistency losses, achieving significant improvements on 3D spatial reasoning benchmarks without using 3D VQA data.
One Token per Multimodal Evidence: Latent Memory for Resource-Constrained QA
Latent Memory introduces a compressed representation approach for external memory in question answering, reducing token consumption and storage requirements while maintaining competitive performance across text-only and multimodal benchmarks.
Attention Consistent Longitudinal Medical Visual Question Answering Guided by Vision Foundation Models
Proposes an attention-guided encoder-decoder for longitudinal medical visual question answering, using a frozen DINO-based mask generator and auxiliary losses to improve consistency and interpretability, achieving strong results on the Medical-Diff-VQA benchmark.
@rsasaki0109: ZipDepth [ECCV 2026] Official implementation of "ZipDepth: Bringing Lightweight Zero-Shot Monocular Depth Anywhere, on …
ZipDepth is a lightweight zero-shot monocular depth estimation model that achieves the best accuracy-efficiency trade-off, running in real time on any device from mobile phones to server GPUs, and has been accepted at ECCV 2026.