How Much 3D Do Video Foundation Models Encode?

• URL: http://arxiv.org/abs/2512.19949v1
• Date: Tue, 23 Dec 2025 00:38:52 GMT
• Title: How Much 3D Do Video Foundation Models Encode?
• Authors: Zixuan Huang, Xiang Li, Zhaoyang Lv, James M. Rehg,
• Abstract summary: We study the 3D understanding of existing Video Foundation Models (VidFMs) pretrained on vast video data.<n>We propose the first model-agnostic framework that measures the 3D awareness of various VidFMs.<n>We show that state-of-the-art video generation models exhibit a strong understanding of 3D objects and scenes, despite not being trained on any 3D data.
• Score: 29.490293159021807
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Videos are continuous 2D projections of 3D worlds. After training on large video data, will global 3D understanding naturally emerge? We study this by quantifying the 3D understanding of existing Video Foundation Models (VidFMs) pretrained on vast video data. We propose the first model-agnostic framework that measures the 3D awareness of various VidFMs by estimating multiple 3D properties from their features via shallow read-outs. Our study presents meaningful findings regarding the 3D awareness of VidFMs on multiple axes. In particular, we show that state-of-the-art video generation models exhibit a strong understanding of 3D objects and scenes, despite not being trained on any 3D data. Such understanding can even surpass that of large expert models specifically trained for 3D tasks. Our findings, together with the 3D benchmarking of major VidFMs, provide valuable observations for building scalable 3D models.

Related papers

• LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sight [105.9472902251177]
  We present a VLM-native recipe that casts 3D detection as a next-token prediction problem.<n>Our model achieves state-of-the-art results, with 49.89 AP_3D, surpassing the previous best by +15.51 absolute improvement.
  arXiv  Detail & Related papers  (2025-11-25T18:59:45Z)
• Does Your 3D Encoder Really Work? When Pretrain-SFT from 2D VLMs Meets 3D VLMs [72.11701578308804]
  This paper categorizes recent 3D Vision-Language Models into 3D object-centric, 2D image-based, and 3D scene-centric approaches.<n>Despite the architectural similarity of 3D scene-centric VLMs to their 2D counterparts, they have exhibited comparatively lower performance compared with the latest 3D object-centric and 2D image-based approaches.<n>Our investigation suggests that while these models possess cross-modal alignment capabilities, they tend to over-rely on linguistic cues and overfit to frequent answer distributions.
  arXiv  Detail & Related papers  (2025-06-05T17:56:12Z)
• Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors [24.261272070476934]
  Previous research has investigated the application of Multimodal Large Language Models (MLLMs) in understanding 3D scenes by interpreting them as videos.<n>We propose a novel and efficient method called the Video-3D Geometry Large Language Model (VG LLM)<n>Our approach utilizes a 3D visual geometry encoder to extract 3D prior information from video sequences.
  arXiv  Detail & Related papers  (2025-05-30T14:16:41Z)
• Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness [73.72335146374543]
  We introduce reconstructive visual instruction tuning with 3D-awareness (Ross3D), which integrates 3D-aware visual supervision into the training procedure.<n>Ross3D achieves state-of-the-art performance across various 3D scene understanding benchmarks.
  arXiv  Detail & Related papers  (2025-04-02T16:59:55Z)
• You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale [42.67300636733286]
  We present See3D, a visual-conditional multi-view diffusion model trained on large-scale Internet videos for open-world 3D creation.<n>The model aims to Get 3D knowledge by solely Seeing the visual contents from the vast and rapidly growing video data.<n>Our numerical and visual comparisons on single and sparse reconstruction benchmarks show that See3D, trained on cost-effective and scalable video data, achieves notable zero-shot and open-world generation capabilities.
  arXiv  Detail & Related papers  (2024-12-09T17:44:56Z)
• VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models [20.084928490309313]
  This paper presents a novel method for building scalable 3D generative models utilizing pre-trained video diffusion models. By unlocking its multi-view generative capabilities through fine-tuning, we generate a large-scale synthetic multi-view dataset to train a feed-forward 3D generative model. The proposed model, VFusion3D, trained on nearly 3M synthetic multi-view data, can generate a 3D asset from a single image in seconds.
  arXiv  Detail & Related papers  (2024-03-18T17:59:12Z)
• Uni3D: Exploring Unified 3D Representation at Scale [66.26710717073372]
  We present Uni3D, a 3D foundation model to explore the unified 3D representation at scale. Uni3D uses a 2D ViT end-to-end pretrained to align the 3D point cloud features with the image-text aligned features. We show that the strong Uni3D representation also enables applications such as 3D painting and retrieval in the wild.
  arXiv  Detail & Related papers  (2023-10-10T16:49:21Z)
• 3D-LLM: Injecting the 3D World into Large Language Models [60.43823088804661]
  Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning. We propose to inject the 3D world into large language models and introduce a new family of 3D-LLMs. Specifically, 3D-LLMs can take 3D point clouds and their features as input and perform a diverse set of 3D-related tasks.
  arXiv  Detail & Related papers  (2023-07-24T17:59:02Z)
• Gait Recognition in the Wild with Dense 3D Representations and A Benchmark [86.68648536257588]
  Existing studies for gait recognition are dominated by 2D representations like the silhouette or skeleton of the human body in constrained scenes. This paper aims to explore dense 3D representations for gait recognition in the wild. We build the first large-scale 3D representation-based gait recognition dataset, named Gait3D.
  arXiv  Detail & Related papers  (2022-04-06T03:54:06Z)

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.