Evaluating Foundation Models' 3D Understanding Through Multi-View Correspondence Analysis

• URL: http://arxiv.org/abs/2512.11574v1
• Date: Fri, 12 Dec 2025 14:03:16 GMT
• Title: Evaluating Foundation Models' 3D Understanding Through Multi-View Correspondence Analysis
• Authors: Valentina Lilova, Toyesh Chakravorty, Julian I. Bibo, Emma Boccaletti, Brandon Li, Lívia Baxová, Cees G. M. Snoek, Mohammadreza Salehi,
• Abstract summary: We introduce a novel benchmark for in-context 3D scene understanding that requires no finetuning and directly probes the quality of dense visual features.<n>We benchmark 8 state-of-the-art foundation models and show DINO-based encoders remain competitive across large viewpoint shifts.
• Score: 38.10984626023432
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Benchmarking 3D spatial understanding of foundation models is essential for real-world applications such as robotics and autonomous driving. Existing evaluations often rely on downstream finetuning with linear heads or task-specific decoders, making it difficult to isolate the intrinsic 3D reasoning ability of pretrained encoders. In this work, we introduce a novel benchmark for in-context 3D scene understanding that requires no finetuning and directly probes the quality of dense visual features. Building on the Hummingbird framework, which evaluates in-context 2D scene understanding, we extend the setup to the 3D Multi-View ImageNet (MVImgNet) dataset. Given a set of images from objects in specific angles (keys), we benchmark the performance of segmenting novel views (queries) and report the scores in 4 categories of easy, medium, hard, and extreme based on the key-query view contrast. We benchmark 8 state-of-the-art foundation models and show DINO-based encoders remain competitive across large viewpoint shifts, while 3D-aware models like VGGT require dedicated multi-view adjustments. Our code is publicly available at https://github.com/ToyeshC/open-hummingbird-3d-eval .

Related papers

• PatchAlign3D: Local Feature Alignment for Dense 3D Shape understanding [67.15800065888887]
  Current foundation models for 3D shapes excel at global tasks (retrieval, classification) but transfer poorly to local part-level reasoning.<n>We introduce an encoder-only 3D model that produces language-aligned patch-level features directly from point clouds.<n>Our 3D encoder achieves zero-shot 3D part segmentation with fast single-pass inference without any test-time multi-view rendering.
  arXiv  Detail & Related papers  (2026-01-05T18:55:45Z)
• Sparse Multiview Open-Vocabulary 3D Detection [27.57172918603858]
  3D object detection has traditionally been solved by training to detect a fixed set of categories.<n>In this work, we investigate open-vocabulary 3D object detection in the challenging yet practical sparse-view setting.<n>Our approach is training-free, relying on pre-trained, off-the-shelf 2D foundation models instead of employing computationally expensive 3D feature fusion.
  arXiv  Detail & Related papers  (2025-09-19T12:22:24Z)
• Pts3D-LLM: Studying the Impact of Token Structure for 3D Scene Understanding With Large Language Models [9.658828841170472]
  This work presents a rigorous study of 3D token structures, systematically comparing video-based and point-based representations.<n>We propose a novel approach that enriches visual tokens by incorporating 3D point cloud features from a Sonata pretrained Point Transformer V3 encoder.
  arXiv  Detail & Related papers  (2025-06-06T02:35:26Z)
• E3D-Bench: A Benchmark for End-to-End 3D Geometric Foundation Models [78.1674905950243]
  We present the first comprehensive benchmark for 3D geometric foundation models (GFMs)<n>GFMs directly predict dense 3D representations in a single feed-forward pass, eliminating the need for slow or unavailable precomputed camera parameters.<n>We evaluate 16 state-of-the-art GFMs, revealing their strengths and limitations across tasks and domains.<n>All code, evaluation scripts, and processed data will be publicly released to accelerate research in 3D spatial intelligence.
  arXiv  Detail & Related papers  (2025-06-02T17:53:09Z)
• VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction [86.82819259860186]
  We introduce VLM-3R, a unified framework for Vision-Language Models (VLMs) that incorporates 3D Reconstructive instruction tuning.<n>VLM-3R processes monocular video frames by employing a geometry encoder to derive implicit 3D tokens that represent spatial understanding.
  arXiv  Detail & Related papers  (2025-05-26T17:56:30Z)
• DistillNeRF: Perceiving 3D Scenes from Single-Glance Images by Distilling Neural Fields and Foundation Model Features [65.8738034806085]
  DistillNeRF is a self-supervised learning framework for understanding 3D environments in autonomous driving scenes. Our method is a generalizable feedforward model that predicts a rich neural scene representation from sparse, single-frame multi-view camera inputs.
  arXiv  Detail & Related papers  (2024-06-17T21:15:13Z)
• DatasetNeRF: Efficient 3D-aware Data Factory with Generative Radiance Fields [68.94868475824575]
  This paper introduces a novel approach capable of generating infinite, high-quality 3D-consistent 2D annotations alongside 3D point cloud segmentations. We leverage the strong semantic prior within a 3D generative model to train a semantic decoder. Once trained, the decoder efficiently generalizes across the latent space, enabling the generation of infinite data.
  arXiv  Detail & Related papers  (2023-11-18T21:58:28Z)
• PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm [111.16358607889609]
  We introduce a novel universal 3D pre-training framework designed to facilitate the acquisition of efficient 3D representation.<n>For the first time, PonderV2 achieves state-of-the-art performance on 11 indoor and outdoor benchmarks, implying its effectiveness.
  arXiv  Detail & Related papers  (2023-10-12T17:59:57Z)
• AutoDecoding Latent 3D Diffusion Models [95.7279510847827]
  We present a novel approach to the generation of static and articulated 3D assets that has a 3D autodecoder at its core. The 3D autodecoder framework embeds properties learned from the target dataset in the latent space. We then identify the appropriate intermediate volumetric latent space, and introduce robust normalization and de-normalization operations.
  arXiv  Detail & Related papers  (2023-07-07T17:59:14Z)

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.