arXiv Machine Learning

UGG: Unified Generative Geometry Model

UGG is a unified generative geometry model that jointly learns RGB video and geometric representations such as depth and camera pose. By assigning different noise levels across modalities and time, it treats visual generation and geometric prediction as conditional completions within a single generative framework. This approach allows learning from heterogeneous datasets, supports inference-time search over multiple scene hypotheses, and outperforms non-unified baselines in tasks like camera-controlled video generation, depth estimation, and camera pose prediction, even with sparse observations.

arXiv Computer Vision
Aug 31

Video Generative Models as Geometry Learner

The paper introduces GeoNeXt, a framework that repurposes pretrained video generative models for geometry estimation by framing it as a next‑frame prediction task. Unlike prior methods that either train separate depth/normal models or fine‑tune image diffusion backbones, GeoNeXt jointly models images and geometric targets, leveraging the structured knowledge of video models for more data‑efficient learning. Experiments show zero‑shot monocular depth and surface normal estimation that outperforms existing generative approaches and rivals discriminative state‑of‑the‑art methods while using far less training data.

By Haosen Yang, Jifei Song, Zhensong Zhang, Xiatian Zhu, Jiankang Deng
arXiv Computer Vision
Oct 21

CARI4D: Category Agnostic 4D Reconstruction of Human-Object Interaction

CARI4D is a category‑agnostic method that reconstructs spatially and temporally consistent 4D human‑object interactions from monocular RGB videos at metric scale. It introduces a pose hypothesis selection algorithm that integrates predictions from foundation models, refines them via a learned render‑and‑compare paradigm, and reasons about contacts to satisfy physical constraints. Experiments demonstrate a 38% improvement on in‑distribution data and 36% on unseen data compared to prior work, and the model generalizes to unseen categories, enabling zero‑shot application to internet videos.

By Xianghui Xie, Bowen Wen, Yan Chang, Hesam Rabeti, Jiefeng Li, Ye Yuan, Gerard Pons-Moll, Stan Birchfield
arXiv Computer Vision
Sep 3

RoGe: Novel View Synthesis via End-to-End Implicit Reconstruction and Generation

RoGe is a new end‑to‑end framework for novel view synthesis that jointly learns an implicit 3D scene representation and a video diffusion model. It eliminates the need for explicit 3D intermediates by querying the implicit scene with camera rays to produce geometric features that condition the diffusion model. Experiments on DL3DV show that RoGe surpasses reconstruction‑based, generation‑based, and hybrid baselines in image quality and temporal consistency, and ablations confirm the benefits of ray‑queried features and joint training.

By Xiaolei Lang, Ze Kang, Zehao Huang, Naiyan Wang
arXiv Computer Vision
Aug 26

SceneReGen: Generative Reconstruction of 3D Scenes from a Single Image

SceneReGen is a new framework for reconstructing 3D scenes from a single image by generating and assembling complete object meshes within a shared observation‑aligned scene frame. It uses selective pose factorization to encode each object’s observed orientation directly into the generated mesh, while estimating translation and scale from instance‑level and global scene cues. Evaluated on the 3D‑FUTURE dataset, SceneReGen outperforms existing methods on scene‑level metrics and shows strong performance on object‑level metrics, demonstrating its effectiveness in autonomous‑driving and embodied‑AI scenarios.

By Zefan Tian, Yuteng Ye, Yiheng Zhang, Yuhang Yang, Xueqiang Lv, Shizhou Zhang, Le Liu, Di Xu
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
arXiv AI
Sep 28

DepthEvidence: Unifying Metric Depth Prediction and Geometric Reasoning in Multimodal Language Models

DepthEvidence is a 4B multimodal language model that integrates dense metric depth predictions into language generation. It employs a camera‑conditioned decoder to produce full‑resolution depth maps and a dense‑to‑language interface that converts these predictions into object‑aligned geometry tokens. The model is trained with geometric supervision and instruction tuning, and it sets new state‑of‑the‑art results on a Depth‑VQA benchmark and on instance‑level metric depth estimation across nine datasets.

By Jiangning Wei, Yuan Yao, Miaomiao Cui, Mingsheng Li, Humen Zhong, Shuai Bai, Zhibo Yang