SAM‑V is a geometry‑aware extension of the Segment Anything Model (SAM) that integrates 3D priors from a feed‑forward geometry model (VGGT) into 2D segmentation. It uses a prompt‑fusion mechanism to combine sparse SAM prompts with view‑specific camera tokens and local VGGT features, enabling a mask decoder that attends to both dense 2D and 3D cues. The resulting end‑to‑end system produces consistent multi‑view instance segmentation in a single forward pass, achieving significant gains on the IGGT 3D tracking benchmark without offline mask matching or explicit 3D reconstruction.
By Jiangshan Gong, Yuqun Wu, Qiqian Fu, Yao Xiao, Chuhang Zou, Shenlong Wang, Derek Hoiem
arXiv:2606.16569v2 Announce Type: replace
Abstract: Registering two captures of the same indoor space taken at different times underpins persistent spatial memory for robots and AR systems, yet the r...
By Zhiang Chen, Nahyuk Lee, Boyang Sun, Taein Kwon, Marc Pollefeys, Zuria Bauer, Sunghwan Hong
The paper introduces Self-Geometry, a plug‑and‑play test‑time adaptation framework that enforces explicit multi‑view geometric constraints on Vision Foundation Models (VFMs) using 2D pixel correspondences as pseudo ground truth. It combines Geometric Disentanglement Optimization—mixing Multi‑View and Epipolar Consistency losses with Gradient Disentanglement—to avoid gradient conflicts, a Frame Angular‑Neighbor sampler based on SO(3) geodesic distances to select informative views, and a Lightweight TTA module that adapts VFMs via LoRA. Experiments on six VFMs and four benchmarks (7Scenes, ETH3D, ScanNet++, HiRoom) show consistent improvements in pose and geometry estimation.
By Seokhyun Youn, Dahyeon Kye, Sung-Ho Bae, Jihyong Oh
arXiv:2610.07958v1 Announce Type: new
Abstract: Feed-forward 3D Gaussian Splatting (3DGS) reconstructs a scene in a single forward pass, replacing per-scene optimization with a network trained across...
By Minhyeok Lee, Jungho Lee, Minseok Kang, Heeseung Choi, Ig-Jae Kim, Sangyoun Lee
arXiv:2512.22819v2 Announce Type: replace
Abstract: Panoramic depth estimation captures the complete 360$^\circ$ scene geometry, being essential for robotics and AR/VR applications. While perspective...
By Hualie Jiang, Ziyang Song, Zhiqiang Lou, Rui Xu, Minglang Tan
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
arXiv:2503. 19947v2 Announce Type: replace-cross Abstract: Generalized metric depth understanding is critical for precise vision-guided robotics, which current state-of-the-art (SOTA) vision-encoders do not support.
By Paul Koch, J\"org Kr\"uger
The paper introduces OVIE, a monocular novel-view synthesis method that eliminates the need for multi‑view training data. By using a frozen depth estimator to generate pseudo‑target views from single images and applying masked and adversarial losses, OVIE is trained on 30 million uncurated images. It achieves state‑of‑the‑art performance on RealEstate10K and DL3DV, produces highly consistent multi‑view trajectories, and runs at 116 FPS—over 600× faster than the fastest baseline.
By Adrien Ramanana Rahary, Nicolas Dufour, Patrick Perez, David Picard
CrossDepth introduces geometry-constrained attention for multi-view surround depth estimation, addressing cross-image inconsistencies caused by varying camera intrinsics and limited receptive fields. The method conditions features on per-pixel camera-aware ray embeddings and extends pixel context via cross-image attention limited to geometrically plausible regions. Trained self-supervised with photometric consistency, it achieves better depth accuracy and consistency on DDAD and nuScenes compared to existing self-supervised approaches.
By Samer Abualhanud, Max Mehltretter
The paper introduces a biologically inspired framework that learns object‑centric visual representations from raw videos without human annotations or camera calibration. By using motion boundaries detected via optical flow and clustering to create pseudo‑instance masks, the method supervises a single‑image encoder with pixel‑level pairwise metric learning. Training on 195 million pseudo‑labeled frames and expanding to 421 million frames through Motion‑Verified Self‑Training, the approach yields Swin‑based encoders that outperform or match supervised and self‑supervised baselines on tasks such as monocular depth estimation, 3D object detection, 3D occupancy prediction, and end‑to‑end planning.
By Boshi Li, Xiaohui Wang, Xiaoyang Wu, Zhichao Li, Ya Yang, Naiyan Wang
arXiv:2604.09045v2 Announce Type: replace
Abstract: Recent works on 3D scene understanding leverage 2D masks from visual foundation models (VFMs) to supervise radiance fields, enabling instance-level...
By Tsuheng Hsu, Guiyu Liu, Juho Kannala, Janne Heikkil\"a
DART is a new RGB‑D pretraining method for surgical vision foundation models that incorporates pseudo‑labeled depth maps as a pixel‑space reconstruction target during training. By adding a depth reconstruction head to DINOv2’s masked iBOT framework, DART improves representation quality without affecting downstream RGB‑only fine‑tuning or inference. Across eight surgical benchmarks—including segmentation, depth estimation, and image‑level recognition—DART outperforms both natural‑image and in‑domain baselines, demonstrating that geometric pseudo‑labels can strengthen foundation model pretraining without extra labels or inference cost.
By John J. Han, Adam Schmidt, Muhammad Abdullah Jamal, Jie Ying Wu, Omid Mohareri