The paper introduces DeformView, a wide‑baseline multi‑view dataset with pixel‑level annotations of geometric inconsistencies, and evaluates existing multi‑view consistency‑scoring methods, finding they transfer poorly to forensic localization tasks. To address this, the authors propose DEFECt3R, a lightweight learning‑based classifier that leverages cross‑view feature relationships and hard negative supervision to localize inconsistencies at the pixel level, achieving better performance and fewer false positives. Ablation studies confirm the importance of feature representations and correspondence quality for localization.
By Xander Staelens, Alb\'eric Loos, Bert Ramlot, Hannes Mareen, Peter Lambert, Glenn Van Wallendael
arXiv:2607. 21595v1 Announce Type: cross Abstract: Despite rapid progress, most existing vision-language models (VLMs) built from 2D visual inputs often struggle when handling various 3D tasks that require fine-grained spatial understanding and reasoning.
By Wenhao Li, Xueying Jiang, Quanhao Qian, Deli Zhao, Ran Xu, Shijian Lu, Gongjie Zhang
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
PXDepth is a monocular depth estimation model that separates global context modeling from pixel-level depth prediction. It uses a large-patch Vision Transformer to capture scene context and a pixel-space predictor with Context‑Modulated Pixel Transformer blocks to preserve high‑resolution spatial details. The approach maintains fine structures and sharp boundaries while achieving competitive global depth accuracy in zero‑shot benchmarks.
By Zhiyuan Yuan, Guanying Chen, Lingteng Qiu, Ruimao Zhang, Shuguang Cui, Xiaochun Cao
Robots operating safely in cluttered everyday environments often need to infer scene geometry from partial observations. Methods that detect objects in 2D and reconstruct them independently struggle i...
arXiv:2609.36882v1 Announce Type: new
Abstract: Localizing AI-edited regions is essential for interpretable forensic analysis, but remains challenging due to subtle and spatially distributed artifact...
By Junhee Lee, Donghyeon Jeon, Taeoh Kim, Beomyoung Kim, MyeongAh Cho
arXiv:2604.13183v4 Announce Type: replace
Abstract: Generalizable cross-view geo-localization aims to match the same location across views in unseen regions and conditions without GPS supervision. It...
By Hongyang Zhang, Yinhao Liu, Haitao Zhang, Zhongyi Wen, Zhenyu Kuang, Shuxian Liang, Xian-Sheng Hua
arXiv:2607. 04714v1 Announce Type: cross Abstract: Learning motion latents for robotic manipulation heavily relies on extracting motion patterns from visual sequences, yet effective action abstractions require understanding three-dimensional geometric transformations.
By Yunchao Zhang, Yijia Weng, Ruizhe Liu, Ming Hu, Leonidas Guibas, Yanchao Yang
FreeInpaint is a feed‑forward 3D inpainting framework that reconstructs complete, geometrically consistent scenes directly from unposed multi‑view images with masked regions. It extends a 3D foundation model by propagating masked areas across views, using a Learnable Mask Attention mechanism to maintain reliable cross‑view correspondences and a Support Token Refinement strategy that injects diffusion‑generated auxiliary tokens for high‑fidelity completion. Experiments on diverse datasets show that FreeInpaint delivers superior inpainting quality without requiring pre‑computed camera poses, while maintaining fast inference speed.
By Jingyi Pan, Dan Xu, Qiong Luo
The paper introduces Epipolar Distillation (EpiDistill), a method that transfers scale‑aware geometric priors from multi‑view models to monocular depth foundation models using Rectified Stereo Tokens. By preserving epipolar attention patterns, the single‑view model maintains geometric consistency without needing multi‑view inputs during inference. Experiments show significant improvements in zero‑shot metric depth estimation on challenging datasets such as ETH3D and DIODE, and the approach consistently boosts performance of state‑of‑the‑art ViT‑based models like UniDepthV2 and DepthPro.
By Jung-Hee Kim, Xiaoming Liu
The paper introduces 3DWay, a method that predicts 3D consistent waypoints for robot manipulation using multi‑view images. By first generating 2D waypoints that are consistent across views and then triangulating them, the approach provides explicit 3D motion specifications while leveraging pretrained vision‑language models. Experiments demonstrate that 3DWay improves 3D spatial grounding and vision‑language reasoning, enhancing the generalization of robot manipulation policies.
arXiv:2603. 16085v2 Announce Type: replace-cross Abstract: Recent breakthroughs in 3D generation have enabled the synthesis of high-fidelity individual assets.
By Hui Shan, Keyang Luo, Ming Li, Sizhe Zheng, Yanwei Fu, Zhen Chen, Xiangru Huang