← Back to all news
arXiv Computer Vision

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

The paper introduces Z3D, a method that leverages internal representations from 3D Foundation Models (3DFMs) to perform zero‑shot novel depth synthesis. By decoding hidden surfaces and applying latent diffusion on 3DFM representations, Z3D can estimate realistic depth maps for unseen views across multiple datasets. This demonstrates that 3DFMs capture extensive general knowledge about 3D scenes, enabling accurate reconstruction without additional training.

Related stories

Hugging Face Trending Papers
Sep 3

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

The paper explores how 3D Foundation Models (3DFMs) like VGGT can be leveraged for zero‑shot depth synthesis. By decoding hidden surfaces from the models’ internal representations, the authors introduce Z3D, a method that uses latent diffusion on 3DFM representations to estimate pointmaps in unseen views. Experiments demonstrate that Z3D can generate realistic depth maps across multiple datasets.

llmsdiffusion
More like this →
Hugging Face Trending Papers
Sep 3

Sparse auto-regressive modeling for scene generation from multi-view images

The paper introduces SPAR3S, a sparse voxel‑aligned 3D latent generative model that completes 3D scenes from sparse, unconstrained multi‑view images. By representing only occupied voxels in a compact latent space and training a masked autoregressive transformer with photometric supervision via differentiable 3D Gaussian Splatting, the method predicts missing latent tokens and spatial support, enabling efficient and spatially consistent generation of unseen regions. Experiments on synthetic indoor scenes and RealEstate10k demonstrate higher novel‑view quality and real‑world applicability compared to prior work.

llmsdiffusion
More like this →
arXiv AI
Jul 7

MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sources

arXiv:2601. 22054v2 Announce Type: replace-cross Abstract: Scaling has powered recent advances in vision foundation models, yet extending this paradigm to metric depth estimation remains challenging due to heterogeneous sensor noise, camera-dependent biases, and metric ambiguity in noisy cross-source 3D data.

By Baorui Ma, Jiahui Yang, Donglin Di, Xuancheng Zhang, Jianxun Cui, Hao Li, Yan Xie, Wei Chen
llmscomputer-visionmultimodalbenchmarks
More like this →
arXiv Machine Learning
Sep 4

Sparse auto-regressive modeling for scene generation from multi-view images

The paper introduces SPAR3S, a sparse voxel‑aligned 3D latent generative model that completes 3D scenes from sparse, unconstrained multi‑view images. It learns a compact voxel‑aligned latent space using photometric supervision via differentiable 3D Gaussian Splatting, and employs a masked autoregressive transformer to predict missing voxel occupancy and latent tokens. Experiments on synthetic indoor scenes and RealEstate10k show that SPAR3S achieves higher novel‑view quality than prior methods and generalizes to real‑world data.

By Thomas Lucas, Maxime Pietrantoni, Philippe Weinzaepfel, Wonjune Cho, Bardienus Pieter Duisterhof, Vincent Leroy, Jerome Revaud
llmsdiffusion
More like this →