← Back to all news
Hugging Face Trending Papers

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.

Related stories

arXiv Computer Vision
Sep 4

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.

By Denis M. Akola, David F. Fouhey
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 Computer Vision
Sep 24

GaussianDS: Depth-supervised Semantic Gaussian Splatting for Scene Understanding

GaussianDS introduces a depth‑supervised framework for 3D Gaussian Splatting that jointly optimizes RGB appearance, depth, and compact semantics from scratch. By arranging multi‑view images into a pose‑aware pseudo‑video and propagating view‑consistent masks via SAM2, the method aligns semantic lifting with geometric cues, using depth supervision and edge‑aware refinement to curb semantic drift and boundary leakage. The approach achieves state‑of‑the‑art performance on LERF and 3D‑OVS benchmarks while preserving high‑fidelity reconstruction and enabling downstream tasks such as 3D object removal.

By Yufei Zhang, Chenlu Zhan, Hongwei Wang
benchmarkssafety
More like this →
arXiv Computer Vision
6d ago

VolFill: Single-View Amodal 3D Scene Reconstruction with Volumetric Flow Matching

VolFill is a generative framework that reconstructs the complete 3D geometry of a scene from a single RGB image, addressing the challenge of inferring hidden structures. It uses a hybrid 3D VAE to encode sparse truncated unsigned distance function grids into a latent space, and a latent Diffusion Transformer to denoise and recover the full scene. By conditioning on a geometry foundation model, VolFill leverages spatial priors and provides a structured representation that enables direct surface extraction and scalable occupancy queries, outperforming existing amodal baselines on SCRREAM and NRGB-D datasets.

By Tuan Duc Ngo, Chuang Gan, Evangelos Kalogerakis
llmsdiffusion
More like this →