The paper introduces MaSS, a framework that adds a dedicated structural representation pathway to self‑supervised monocular depth estimation. By using a scene‑structure discrimination objective, MaSS learns generalized, layout‑aware structural representations that decouple from contextual features. Experiments on four diverse datasets show MaSS outperforms prior methods and benefits from mixed‑domain training, while zero‑shot tests on eight additional datasets confirm its strong generalizability to out‑of‑distribution scenes.
By Mengtan Zhang, Yuchuan Cui, Yu Ma, Zizhan Guo, Wei Ye, Rui Fan
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 NAIMA, a guided depth super‑resolution framework that leverages global contextual semantic priors from pretrained vision transformer token embeddings. Its Guided Token Attention (GTA) module uses depth encodings as queries to attend over semantic tokens, with a zero‑initialized gate controlling the influence of semantic evidence. NAIMA achieves competitive in‑distribution performance while delivering superior cross‑dataset generalization without relying on decoded priors or auxiliary objectives.
By Tayyab Nasir, Daochang Liu, Ajmal Mian
DiNAT-IR introduces Dilated Neighborhood Attention (DiNA) to balance global context and local precision in image restoration. By combining sliding-window attention with mixed dilation factors and a channel-aware module, it addresses the limitations of channel-wise self-attention and improves pixel-level accuracy. The resulting Transformer-based architecture delivers competitive performance across multiple benchmarks for low-level vision tasks.
By Hanzhou Liu, Binghan Li, Chengkai Liu, Mi Lu
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
arXiv:2611.06015v1 Announce Type: new
Abstract: High-content multi-channel imaging, from Cell Painting assays to remote sensing, is central to modern scientific pipelines. Because these channels are...
By Jingwei Zhang, Srinivasan Sivanandan, Dimitris Samaras
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 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
arXiv:2609.39748v1 Announce Type: new
Abstract: Scaling has become a primary driver of progress in language and vision foundation models, yet its role in precise correspondence matching remains under...
By Yongjian Zhang, Longguang Wang, Zhuo Song, Zhiheng Fu, Liang Lin, Yulan Guo
The paper introduces an Attention-Driven Complementarity Resampling framework to enhance cross-modality object detection. It employs a shared channel spatial attention mechanism that exchanges semantic masks between modalities, encouraging the backbone to learn generalized features. Additionally, a learnable channel competition module samples and aggregates features channel‑wise, improving robustness and achieving competitive results on multiple datasets.
By Guandi Wang, Ming Li, Yunsen Xing, Junle Liu
arXiv:2608. 02092v2 Announce Type: replace Abstract: Deep multimodal fusion for object detection has demonstrated good performance through mining modal characteristics.
By Guandi Wang, Ming Li, Yunsen Xing, Junle Liu
DXPR is a depth‑based cross‑modal place recognition framework that matches monocular camera queries to a LiDAR map using a single vision foundation model backbone. By converting both modalities into a unified depth image representation, DXPR learns modality‑invariant global descriptors without modality‑specific encoders. A geometry‑aware overlap miner refines pairwise metric learning by computing pixel‑level overlap scores, and extensive tests on KITTI and Boreas show strong performance across seasons, weather, and day/night conditions, outperforming prior CMPR baselines.