Distill3R: A Pipeline for Democratizing 3D Foundation Models on Commodity Hardware

• URL: http://arxiv.org/abs/2602.00865v1
• Date: Sat, 31 Jan 2026 18:56:45 GMT
• Title: Distill3R: A Pipeline for Democratizing 3D Foundation Models on Commodity Hardware
• Abstract summary: Distill3R is a framework designed to distill the geometric reasoning of 3D foundation models into compact students fully trainable on a single workstation.<n>Our methodology centers on two primary innovations: (1) an offline caching pipeline that decouples heavy teacher inference from the training loop through compressed supervision signals, and (2) a confidence-aware distillation loss that leverages teacher uncertainty to enable training on commodity hardware.
• Score: 2.676349883103404
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While multi-view 3D reconstruction has shifted toward large-scale foundation models capable of inferring globally consistent geometry, their reliance on massive computational clusters for training has created a significant barrier to entry for most academic laboratories. To bridge this compute divide, we introduce Distill3R, a framework designed to distill the geometric reasoning of 3D foundation models into compact students fully trainable on a single workstation. Our methodology centers on two primary innovations: (1) an offline caching pipeline that decouples heavy teacher inference from the training loop through compressed supervision signals, and (2) a confidence-aware distillation loss that leverages teacher uncertainty to enable training on commodity hardware. We propose a 72M-parameter student model which achieves a 9x reduction in parameters and a 5x inference speedup compared to its 650M-parameter teacher. The student is fully trainable in under 3 days on a single workstation, whereas its teacher requires massive GPU clusters for up to a week. We demonstrate that the student preserves the structural consistency and qualitative geometric understanding required for functional 3D awareness. By providing a reproducible, single-workstation training recipe, Distill3R serves as an exploratory entry point for democratized 3D vision research and efficient edge deployment. This work is not intended to compete with state-of-the-art foundation models, but to provide an accessible research baseline for laboratories without access to large-scale compute to train and specialize models on their own domain-specific data at minimal cost.

Related papers

• Enhancing deep learning models for time series classification via knowledge distillation [0.49387059996366106]
  Knowledge Distillation (KD) addresses this by transferring knowledge from a large teacher model to a smaller, more efficient student model.<n>We evaluate our approach on UCR Archive, the largest benchmark repository of time series datasets.
  arXiv  Detail & Related papers  (2026-07-07T20:51:22Z)
• Geometric Foundation Model Distillation for Efficient Lunar 3D Reconstruction [0.13999481573773068]
  Large 3D foundation models such as MASt3R achieve state-of-the-art stereo reconstruction but are computationally demanding for deployment under strict hardware constraints.<n>We study how far such models can be compressed through knowledge distillation, using lunar stereo reconstruction as a challenging and practically relevant case study.
  arXiv  Detail & Related papers  (2026-07-02T08:11:32Z)
• TAP-CT: 3D Task-Agnostic Pretraining of Computed Tomography Foundation Models [39.00742360251856]
  Existing foundation models (FMs) in the medical domain often require extensive fine-tuning or rely on training resource-intensive decoders.<n>We introduce a suite of task-agnostic pretraining of CT foundation models (TAP-CT)<n>Our approach incorporates targeted modifications to patch embeddings, positional encodings, and volumetric augmentations, making the architecture depth-aware.
  arXiv  Detail & Related papers  (2025-11-30T12:43:15Z)
• Multimodal Robust Prompt Distillation for 3D Point Cloud Models [16.319048523015773]
  Adrial attacks pose a significant threat to learning-based 3D point cloud models.<n>We propose Multimodal Robust Prompt Distillation (MRPD) for distilling robust 3D point cloud model.<n>It learns lightweight prompts by aligning student point cloud model's features with robust embeddings from three distinct teachers.
  arXiv  Detail & Related papers  (2025-11-26T16:49:38Z)
• Foundry: Distilling 3D Foundation Models for the Edge [15.177160184417575]
  Foundation Model Distillation (FMD) is a new paradigm for compressing large SSL models into compact proxies.<n>We present Foundry, the first implementation of FMD for 3D point clouds.
  arXiv  Detail & Related papers  (2025-11-25T07:53:56Z)
• TriCLIP-3D: A Unified Parameter-Efficient Framework for Tri-Modal 3D Visual Grounding based on CLIP [52.79100775328595]
  3D visual grounding allows an embodied agent to understand visual information in real-world 3D environments based on human instructions.<n>Existing 3D visual grounding methods rely on separate encoders for different modalities.<n>We propose a unified 2D pre-trained multi-modal network to process all three modalities.
  arXiv  Detail & Related papers  (2025-07-20T10:28:06Z)
• UniPre3D: Unified Pre-training of 3D Point Cloud Models with Cross-Modal Gaussian Splatting [64.31900521467362]
  No existing pre-training method is equally effective for both object- and scene-level point clouds.<n>We introduce UniPre3D, the first unified pre-training method that can be seamlessly applied to point clouds of any scale and 3D models of any architecture.
  arXiv  Detail & Related papers  (2025-06-11T17:23:21Z)
• cadrille: Multi-modal CAD Reconstruction with Online Reinforcement Learning [55.16668009268005]
  We propose a multi-modal CAD reconstruction model that simultaneously processes all three input modalities.<n>Inspired by large language model (LLM) training paradigms, we adopt a two-stage pipeline: supervised fine-tuning (SFT) on large-scale procedurally generated data, followed by reinforcement learning (RL) fine-tuning using online feedback, obtained programatically.<n>In the DeepCAD benchmark, our SFT model outperforms existing single-modal approaches in all three input modalities simultaneously.
  arXiv  Detail & Related papers  (2025-05-28T22:32:31Z)
• One RL to See Them All: Visual Triple Unified Reinforcement Learning [92.90120580989839]
  We propose V-Triune, a Visual Triple Unified Reinforcement Learning system that enables visual reasoning and perception tasks within a single training pipeline.<n>V-Triune comprises triple complementary components: Sample-Level Datashelf (to unify diverse task inputs), Verifier-Level Reward (to deliver custom rewards via specialized verifiers).<n>We introduce a novel Dynamic IoU reward, which provides adaptive, progressive, and definite feedback for perception tasks handled by V-Triune.
  arXiv  Detail & Related papers  (2025-05-23T17:41:14Z)
• Learning from Stochastic Teacher Representations Using Student-Guided Knowledge Distillation [64.15918654558816]
  Self-distillation (SSD) training strategy is introduced for filtering and weighting teacher representation to distill from task-relevant representations only.<n> Experimental results on real-world affective computing, wearable/biosignal datasets from the UCR Archive, the HAR dataset, and image classification datasets show that the proposed SSD method can outperform state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-04-19T14:08:56Z)
• PointSeg: A Training-Free Paradigm for 3D Scene Segmentation via Foundation Models [20.379104447051155]
  We present PointSeg, a training-free paradigm that leverages off-the-shelf vision foundation models to address 3D scene perception tasks.<n>PointSeg can segment anything in 3D scene by acquiring accurate 3D prompts to align their corresponding pixels across frames.<n>Our approach significantly surpasses the state-of-the-art specialist training-free model by 14.1$%$, 12.3$%$, and 12.6$%$ mAP on ScanNet, ScanNet++, and KITTI-360 datasets.
  arXiv  Detail & Related papers  (2024-03-11T03:28:20Z)
• SimDistill: Simulated Multi-modal Distillation for BEV 3D Object Detection [56.24700754048067]
  Multi-view camera-based 3D object detection has become popular due to its low cost, but accurately inferring 3D geometry solely from camera data remains challenging. We propose a Simulated multi-modal Distillation (SimDistill) method by carefully crafting the model architecture and distillation strategy. Our SimDistill can learn better feature representations for 3D object detection while maintaining a cost-effective camera-only deployment.
  arXiv  Detail & Related papers  (2023-03-29T16:08:59Z)
• Towards Efficient 3D Object Detection with Knowledge Distillation [38.89710768280703]
  We explore the potential of knowledge distillation for developing efficient 3D object detectors. Our best performing model achieves $65.75%$ 2 mAPH, surpassing its teacher model and requiring only $44%$ of teacher flops. Our most efficient model runs 51 FPS on an NVIDIA A100, which is $2.2times$ faster than PointPillar with even higher accuracy.
  arXiv  Detail & Related papers  (2022-05-30T15:02:16Z)

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.