← Back to all news
arXiv AI

Scalable Adaptation of 3D Geometric Foundation Models via Weak Supervision from Internet Video

The paper introduces SAGE, a framework that adapts 3D geometric foundation models using weak supervision from raw Internet videos. SAGE employs a hierarchical mining pipeline to generate informative training trajectories, sparse geometric anchoring via SfM point clouds, and dense differentiable consistency through 3D Gaussian rendering, while also replaying a small amount of supervised data to avoid catastrophic forgetting. Experiments on two different backbones show that SAGE reduces Chamfer Distance on unseen benchmarks by 20–42% and consistently improves performance, demonstrating that Internet video can serve as a scalable source for geometric learning.

Related stories

arXiv Computer Vision
Sep 7

Learning 3D Editing without Paired Supervision via Generative Prior Distillation

The paper introduces a framework for instruction‑guided 3D editing that does not require paired 3D supervision. It distills visual, semantic, and geometric knowledge from foundation models into a 3D editing model using a differentiable rendering pipeline, guided by a 2D visual prior from an image editing model and a semantic prior from a Vision‑Language Model. A 3D‑aware Distribution Matching regularization is added to prevent geometric collapse and ensure realistic 3D outputs, leading to superior instruction fidelity and cross‑view consistency compared to state‑of‑the‑art baselines.

By Hao Wen, Weibin Yun, Hongxing Fan, Haotian Lu, Rui Chen, Zehuan Huang, Lu Sheng
llmsdiffusionefficiencymultimodalbenchmarks
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 AI
Jun 9

VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generation

arXiv:2601. 23286v4 Announce Type: replace-cross Abstract: While recent video diffusion models (VDMs) produce visually impressive results, they fundamentally struggle to maintain 3D structural consistency, often resulting in object deformation or spatial drift.

By Hongyang Du, Junjie Ye, Xiaoyan Cong, Runhao Li, Jingcheng Ni, Aman Agarwal, Zeqi Zhou, Zekun Li, Randall Balestriero, Yue Wang
diffusionreinforcement-learningbenchmarkssafety
More like this →
arXiv Computer Vision
Sep 4

Rethinking 3D Noise: Learning 3D-Aware Video Priors via Optimization-Free Morphological Perturbations

The paper introduces 3D Morphological Perturbations, an optimization‑free regularizer for 3D representations such as NeRF and 3D Gaussian Splatting. By treating each Gaussian as a pixel‑like element, the method applies scale, rotation, and pruning perturbations to preserve spatial consistency across views, eliminating the need for per‑scene optimization during dataset curation. Experiments on a lightweight video diffusion sandbox and a 14B‑parameter video model show that the approach improves geometric priors, reduces mean depth error by 12.5% over state‑of‑the‑art 3D artifact refiners, and boosts downstream robotics policy success rates by up to 8.0% on three manipulation tasks.

By Onat \c{S}ahin, Mohammad Altillawi, George Eskandar, Carlos Carbone, Ziyuan Liu
diffusionroboticsefficiencybenchmarks
More like this →
Hugging Face Trending Papers
Jul 2

NeoMap: Training-free Novel-View Synthesis from Single Images and Videos

We study the challenging problem of novel view video synthesis from single images or monocular videos. Existing methods, which operate under the assumption that pre-trained video models lack native novel view synthesis capability and enforce view alignment via camera conditioning, task-specific fine-tuning, or stepwise hard denoising guidance, often suffer from artifacts and compromised global scene consistency.

fine-tuningbenchmarkssafety
More like this →
arXiv Computer Vision
22h ago

ReLift: Dense 3D Tracking as Lifted Trajectory Repair

ReLift presents a feed‑forward framework that treats dense 3D tracking as a problem of repairing and completing lifted trajectories. By alternating attention along and across trajectories, it corrects depth and correspondence errors, and fills in missing motion, all while training solely on simulated 3D trajectory data. The method improves lifted trajectories from any 2D tracker or geometry model, achieving state‑of‑the‑art accuracy on WorldTrack and running faster than leading 4D trackers.

By Assaf Singer, Maroun Khriesh, Noam Rotstein, Yoni Kasten, Or Litany
benchmarks
More like this →
Hugging Face Trending Papers
Jun 16

Domain Generalizable Adaptation of 3D Vision-Language Models via Regularized Fine-Tuning

Domain adaptation remains a central challenge in 3D vision, especially for multimodal foundation models that align 3D point clouds with visual and textual data. While these models demonstrate strong general capabilities, adapting them to downstream domains with limited data often leads to overfitting and catastrophic forgetting.

llmsfine-tuningmultimodalbenchmarks
More like this →