Zero-Shot Novel Depth Synthesis Using 3D Foundation Models Scene Representations

• URL: http://arxiv.org/abs/2609.04174v1
• Date: Thu, 03 Sep 2026 17:54:52 GMT
• Title: Zero-Shot Novel Depth Synthesis Using 3D Foundation Models Scene Representations
• Abstract summary: 3D Foundation Models (3DFMs) have recently pushed the boundaries of 3D vision by predicting rich unified representations with feed-foward transformers.<n>In this paper, we investigate using their internal representations to infer 3D in the scene from new views.
• Score: 15.647814813324267
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 3D Foundation Models (3DFMs) such as VGGT have recently pushed the boundaries of 3D vision by predicting rich unified representations with feed-foward transformers. The scene representations learned by these models enable strong performance on multiple 3D vision tasks. In this paper, we investigate using their internal representations to infer 3D in the scene from new views. Our hypothesis is that in order to solve the task of 3D reconstruction, these models need to learn a representation that includes a large amount of general knowledge about 3D scenes. After showing that it is possible to decode hidden surfaces from internal 3DFM representations, we propose a method, Z3D, that estimates pointmaps in unseen views by doing latent diffusion on 3DFM representation. We show that Z3D can predict realistic depth maps for new views across multiple datasets.

Related papers

• Emergent Extreme-View Geometry in 3D Foundation Models [26.53730031068199]
  3D foundation models (3DFMs) have recently transformed 3D vision, enabling joint prediction of depths, poses, and point maps directly from images.<n>We study their internal representations and find that 3DFMs exhibit an emergent understanding of extreme-view geometry, despite never being trained for such conditions.<n>We introduce a lightweight alignment scheme that refines their internal 3D representation by tuning only a small subset of backbone bias terms, leaving all decoder heads frozen.<n>We contribute MegaUnScene, a new benchmark of Internet scenes unseen by existing 3DFMs, with dedicated test splits for both relative pose estimation and dense 3D reconstruction
  arXiv  Detail & Related papers  (2025-11-27T18:40:03Z)
• 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)
• Probing the 3D Awareness of Visual Foundation Models [56.68380136809413]
  We analyze the 3D awareness of visual foundation models. We conduct experiments using task-specific probes and zero-shot inference procedures on frozen features.
  arXiv  Detail & Related papers  (2024-04-12T17:58:04Z)
• Denoising Diffusion via Image-Based Rendering [54.20828696348574]
  We introduce the first diffusion model able to perform fast, detailed reconstruction and generation of real-world 3D scenes. First, we introduce a new neural scene representation, IB-planes, that can efficiently and accurately represent large 3D scenes. Second, we propose a denoising-diffusion framework to learn a prior over this novel 3D scene representation, using only 2D images.
  arXiv  Detail & Related papers  (2024-02-05T19:00:45Z)
• 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)
• 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)
• MonoNeRD: NeRF-like Representations for Monocular 3D Object Detection [31.58403386994297]
  We propose MonoNeRD, a novel detection framework that can infer dense 3D geometry and occupancy. Specifically, we model scenes with Signed Distance Functions (SDF), facilitating the production of dense 3D representations. To the best of our knowledge, this work is the first to introduce volume rendering for M3D, and demonstrates the potential of implicit reconstruction for image-based 3D perception.
  arXiv  Detail & Related papers  (2023-08-18T09:39:52Z)
• CLIP-Guided Vision-Language Pre-training for Question Answering in 3D Scenes [68.61199623705096]
  We design a novel 3D pre-training Vision-Language method that helps a model learn semantically meaningful and transferable 3D scene point cloud representations. We inject the representational power of the popular CLIP model into our 3D encoder by aligning the encoded 3D scene features with the corresponding 2D image and text embeddings. We evaluate our model's 3D world reasoning capability on the downstream task of 3D Visual Question Answering.
  arXiv  Detail & Related papers  (2023-04-12T16:52:29Z)
• RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation [68.06991943974195]
  We present RenderDiffusion, the first diffusion model for 3D generation and inference, trained using only monocular 2D supervision. We evaluate RenderDiffusion on FFHQ, AFHQ, ShapeNet and CLEVR datasets, showing competitive performance for generation of 3D scenes and inference of 3D scenes from 2D images.
  arXiv  Detail & Related papers  (2022-11-17T20:17:04Z)
• CoCoNets: Continuous Contrastive 3D Scene Representations [21.906643302668716]
  This paper explores self-supervised learning of amodal 3D feature representations from RGB and RGB-D posed images and videos. We show the resulting 3D visual feature representations effectively scale across objects and scenes, imagine information occluded or missing from the input viewpoints, track objects over time, align semantically related objects in 3D, and improve 3D object detection.
  arXiv  Detail & Related papers  (2021-04-08T15:50:47Z)

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.