3DTurboQuant: Training-Free Near-Optimal Quantization for 3D Reconstruction Models

• URL: http://arxiv.org/abs/2604.05366v1
• Date: Tue, 07 Apr 2026 03:06:05 GMT
• Title: 3DTurboQuant: Training-Free Near-Optimal Quantization for 3D Reconstruction Models
• Abstract summary: Existing method for compressing 3D reconstructors requires learning a data-dependent codebook through per-scene fine-tuning.<n>We show this is unnecessary. parameter vectors that dominate storage in these models fall in a dimension range where a single random rotation transforms any input into coordinates with a known Beta distribution.<n>We develop 3D, deriving (1) a dimension-dependent criterion that predicts which parameters can be quantized and at what bit-width before running any experiment, (2) norm-separation bounds connecting quantization MSE to rendering PSNR per scene, and (3) an entry-grouping strategy extending rotation-based quantization
• Score: 2.0789144738685956
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Every existing method for compressing 3D Gaussian Splatting, NeRF, or transformer-based 3D reconstructors requires learning a data-dependent codebook through per-scene fine-tuning. We show this is unnecessary. The parameter vectors that dominate storage in these models, 45-dimensional spherical harmonics in 3DGS and 1024-dimensional key-value vectors in DUSt3R, fall in a dimension range where a single random rotation transforms any input into coordinates with a known Beta distribution. This makes precomputed, data-independent Lloyd-Max quantization near-optimal, within a factor of 2.7 of the information-theoretic lower bound. We develop 3D, deriving (1) a dimension-dependent criterion that predicts which parameters can be quantized and at what bit-width before running any experiment, (2) norm-separation bounds connecting quantization MSE to rendering PSNR per scene, (3) an entry-grouping strategy extending rotation-based quantization to 2-dimensional hash grid features, and (4) a composable pruning-quantization pipeline with a closed-form compression ratio. On NeRF Synthetic, 3DTurboQuant compresses 3DGS by 3.5x with 0.02dB PSNR loss and DUSt3R KV caches by 7.9x with 39.7dB pointmap fidelity. No training, no codebook learning, no calibration data. Compression takes seconds. The code will be released (https://github.com/JaeLee18/3DTurboQuant)

Related papers

• CodecSplat: Ultra-Compact Latent Coding for Feed-Forward 3D Gaussian Splatting [53.50198425973128]
  We introduce CodecSplat, an ultracompact latent coding framework for feed-forward 3D Gaussian splatting.<n>CodecSplat achieves 23.56-26.36 dB and 24.76-27.05 dB with only 20.00-10777 PSNR with 3.37-12 and 3.37-12 respectively.
  arXiv  Detail & Related papers  (2026-05-25T08:17:35Z)
• OCTOPUS: Optimized KV Cache for Transformers via Octahedral Parametrization Under optimal Squared error quantization [13.284869342523095]
  Key-value (KV) dominates memory bandwidth and footprint in autoregressive inference.<n>Recent rotation-preconditioned codecs (TurboQuant, PolarQuant) show that a structured random rotation followed by a per-coordinate quantizer matched to an analytically tractable marginal is a near-optimal recipe for KV compression.<n>OCTOPUS advances this paradigm through joint quantization of rotated coordinate triplets.
  arXiv  Detail & Related papers  (2026-05-20T14:19:51Z)
• MesonGS++: Post-training Compression of 3D Gaussian Splatting with Hyperparameter Searching [27.114461961869782]
  3D Gaussian Splatting (3DGS) achieves high-quality novel view with real-time rendering, but its storage cost remains prohibitive for practical deployment.<n>We propose MesonGS, a size-aware post-training for 3D Gaussian compression. On the side, MesonGS combines joint importance-based pruning, octree geometry, transformations, selective vector quantization for higher-degree spherical harmonics, and group-wise mixed-precision quantization with entropy coding.
  arXiv  Detail & Related papers  (2026-04-29T15:30:06Z)
• Tail-Aware Post-Training Quantization for 3D Geometry Models [58.79500829118265]
  Post-Training Quantization (PTQ) enables efficient inference without retraining.<n>PTQ fails to transfer effectively to 3D models due to intricate feature distributions and prohibitive calibration overhead.<n>We propose TAPTQ, a Tail-Aware Post-Training Quantization pipeline for 3D geometric learning.
  arXiv  Detail & Related papers  (2026-02-02T07:21:15Z)
• Quantized Visual Geometry Grounded Transformer [67.15451442018258]
  This paper proposes the first Quantization framework for VGGTs, namely QuantVGGT.<n>We introduce Dual-Smoothed Fine-Grained Quantization, which integrates pre-global Hadamard rotation and post-local channel smoothing.<n>We also design Noise-Filtered Diverse Sampling, which filters outliers via deep-layer statistics.
  arXiv  Detail & Related papers  (2025-09-25T15:17:11Z)
• Speedy Deformable 3D Gaussian Splatting: Fast Rendering and Compression of Dynamic Scenes [57.69608119350651]
  Recent extensions of 3D Gaussian Splatting (3DGS) to dynamic scenes achieve high-quality novel view synthesis by using neural networks to predict the time-varying deformation of each Gaussian.<n>However, performing per-Gaussian neural inference at every frame poses a significant bottleneck, limiting rendering speed and increasing memory and compute requirements.<n>We present Speedy Deformable 3D Gaussian Splatting (SpeeDe3DGS), a general pipeline for accelerating the rendering speed of dynamic 3DGS and 4DGS representations by reducing neural inference through two complementary techniques.
  arXiv  Detail & Related papers  (2025-06-09T16:30:48Z)
• FlexGS: Train Once, Deploy Everywhere with Many-in-One Flexible 3D Gaussian Splatting [57.97160965244424]
  3D Gaussian splatting (3DGS) has enabled various applications in 3D scene representation and novel view synthesis.<n>Previous approaches have focused on pruning less important Gaussians, effectively compressing 3DGS.<n>We present an elastic inference method for 3DGS, achieving substantial rendering performance without additional fine-tuning.
  arXiv  Detail & Related papers  (2025-06-04T17:17:57Z)
• Compressing 3D Gaussian Splatting by Noise-Substituted Vector Quantization [14.71160140310766]
  3D Gaussian Splatting (3DGS) has demonstrated remarkable effectiveness in 3D reconstruction, achieving high-quality results with real-time radiance field rendering.<n>However, a key challenge is the substantial storage cost: reconstructing a single scene typically requires millions of Gaussian splats, each represented by 59 floating-point parameters, resulting in approximately 1 GB of memory.<n>We propose a compression method by building separate attribute codebooks and storing only discrete code indices. Specifically, we employ noise-substituted vector quantization technique to jointly train the codebooks and model features, ensuring consistency between descent gradient optimization and parameter discretization
  arXiv  Detail & Related papers  (2025-04-03T22:19:34Z)
• TC-GS: Tri-plane based compression for 3D Gaussian Splatting [28.502636841299356]
  3D Gaussian Splatting (3DGS) has emerged as a prominent framework for novel view synthesis, providing high fidelity and rapid rendering speed.<n>We propose a well-structured tri-plane to encode Gaussian attributes, leveraging the distribution of attributes for compression.<n>Our approach has achieved results comparable to or surpass that of SOTA 3D Gaussians Splatting compression work in extensive experiments across multiple datasets.
  arXiv  Detail & Related papers  (2025-03-26T04:26:22Z)
• CAT-3DGS: A Context-Adaptive Triplane Approach to Rate-Distortion-Optimized 3DGS Compression [10.869104603083676]
  3D Gaussian Splatting (3DGS) has recently emerged as a promising 3D representation.<n>The needs to compress and transmit the 3DGS representation to the remote side are overlooked.<n>This new application calls for rate-distortion-optimized 3DGS compression.
  arXiv  Detail & Related papers  (2025-03-01T05:42:52Z)
• PUP 3D-GS: Principled Uncertainty Pruning for 3D Gaussian Splatting [59.277480452459315]
  We propose a principled sensitivity pruning score that preserves visual fidelity and foreground details at significantly higher compression ratios.<n>We also propose a multi-round prune-refine pipeline that can be applied to any pretrained 3D-GS model without changing its training pipeline.
  arXiv  Detail & Related papers  (2024-06-14T17:53:55Z)

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.