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.

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.

llms diffusion

arXiv Computer Vision

Sep 1

ReconSplat: Generalizable 3D Scene Reconstruction Beyond Observed Views

arXiv:2608.28895v1 Announce Type: new Abstract: We introduce ReconSplat, a feed-forward model for 3D scene reconstruction that aims to address the longstanding trade-off between plausible view genera...

By Giuseppe Stracquadanio, Kevin Raj, Julia Grabinski, Stefan Roth

diffusion benchmarks

arXiv Computer Vision

Sep 2

Monocular Depth Estimation from a Single Image: Progress and Opportunities

arXiv:2609.01172v1 Announce Type: new Abstract: Monocular depth estimation has long stood as a fundamental challenge in computer vision, enabling a wide range of applications including 3D reconstruct...

By Muxin Liu, Xiaoyang Lyu, Yang-Tian Sun, Yi-Hua Huang, Ziyi Yang, Peng Dai, Xiaojuan Qi

agents computer-vision robotics benchmarks

arXiv AI

Jul 21

Depth Estimators Are Implicit Neural Fields for 3D Scene Geometry Inpainting and Reconstruction

arXiv:2607. 16286v1 Announce Type: cross Abstract: The 3D geometry of real-world scene data is often incomplete.

By Yingzhao Jian, Zihao Lin, Hehe Fan

benchmarks

arXiv Machine Learning

Jun 25

SparseGS: Sparse View Synthesis using 3D Gaussian Splatting

arXiv:2312. 00206v4 Announce Type: replace-cross Abstract: 3D Gaussian Splatting (3DGS) has recently enabled real-time rendering of unbounded 3D scenes for novel view synthesis.

By Haolin Xiong, Sairisheek Muttukuru, Hanyuan Xiao, Rishi Upadhyay, Pradyumna Chari, Yajie Zhao, Achuta Kadambi

efficiency

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

benchmarks safety

arXiv Computer Vision

Aug 24

M2Depth: Unifying Monocular Depth Foundation Priors with Multi-View Stereo

arXiv:2608.20788v1 Announce Type: new Abstract: Deep learning-based Multi-View Stereo (MVS) has advanced significantly but often generalizes poorly to unseen scenes, particularly in occluded areas or...

By Byeonggwon Lee, Sanggi Lee, Siwoo Lee, Khang Truong Giang, Soohwan Song

benchmarks

arXiv Computer Vision

Sep 30

GeoVerse: World-Consistent Novel View Synthesis in Geometric Latent Space

arXiv:2609.35734v2 Announce Type: replace Abstract: Novel view synthesis from sparse images must reconcile faithful reconstruction of observed regions with plausible completion of unseen content, whi...

By Kerui Ren, Tao Lu, Linning Xu, Changjian Jiang, Mu Huang, Chunhua Shen, Mulin Yu, Bo Dai

diffusion

arXiv AI

Jun 30

One Scene, Two Depths: Probing Geometric Ambiguity in Monocular Foundation Models

arXiv:2606. 29600v1 Announce Type: cross Abstract: A faithful 3D world representation should account for layered geometry, where a single camera ray may contain multiple visible and geometrically valid surfaces.

By Xiaohao Xu, Feng Xue, Xiang Li, Haowei Li, Shusheng Yang, Tianyi Zhang, Matthew Johnson-Roberson, Xiaonan Huang

llms computer-vision benchmarks

arXiv Machine Learning

Jul 3

RGB-Pointmap Pretraining for Unified 3D Scene Understanding

arXiv:2604. 02546v3 Announce Type: replace-cross Abstract: Pretraining 3D encoders through alignment with Contrastive Language-Image Pre-training (CLIP) has emerged as a promising direction for learning generalizable representations for 3D scene understanding.

By Ye Mao, Weixun Luo, Ranran Huang, Junpeng Jing, Krystian Mikolajczyk

llms nlp fine-tuning benchmarks safety

arXiv AI

Oct 26

Easy-3Dfy: Object-Level Geometric Composition for Single-Image 3D Scene Construction

Easy-3Dfy introduces a compositional workflow for single-image 3D scene construction that separates object generation from scene layout estimation. By using a specialized 3D object generator for detailed geometry and a 3D foundation model for spatial understanding, the method aligns object-local meshes with partial scene pointmaps via an RPF-based aligner. This approach consistently outperforms SAM-3Dfy on geometric metrics in Scene-Maker and 3D-FUTURE200 without requiring full scene-level supervision.

By Ziang Zhang, Wenyou Yi, Zehan Wang, Jiachen Xu, Xintong Han, Chunchao Guo, Zhou Zhao

arXiv AI

Oct 15

Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective

arXiv:2604.14025v2 Announce Type: replace-cross Abstract: Reconstructing 3D representations from 2D inputs is a fundamental task in computer vision and graphics, serving as a cornerstone for understa...

By Weijie Wang, Qihang Cao, Sensen Gao, Donny Y. Chen, Haofei Xu, Wenjing Bian, Songyou Peng, Tat-Jen Cham, Chuanxia Zheng, Andreas Geiger, Jianfei Cai, Jia-Wang Bian, Bohan Zhuang

computer-vision benchmarks

Related stories