The paper investigates supervised RGB‑only multi‑view 3D reconstruction by leveraging video‑pretrained features and a pipeline that includes camera estimation, scene aggregation, epipolar transport, and residual pointmaps. Experiments on CO3D and indoor datasets compare global versus spatial camera regression and a joint relative‑objective configuration, revealing trade‑offs in trajectory, depth, and Chamfer distance metrics. The results emphasize that improvements in reconstruction stem from specific representation adaptations and component interactions rather than solely from predictive video pretraining.
PIVOT is a new multi‑trajectory dataset and evaluation framework that captures real‑world scenes with diverse camera paths, preserving both sensor‑derived measured poses and COLMAP‑optimized poses along with calibrated and optimized intrinsics. It defines three benchmark families—seen vs. unseen trajectory generalization, measured vs. optimized pose sensitivity, and calibrated vs. optimized intrinsics sensitivity—and introduces a directed pose‑space Chamfer distance to assess pose coverage. The first version of PIVOT includes five scenes recorded with a DJI Mini 4 Pro and offers an open processing and Nerfstudio‑based evaluation toolchain, revealing a consistent quality gap between held‑out and unseen trajectories and significant sensitivity to pose source and camera intrinsics.
By Mary Raymond
arXiv:2609.01530v1 Announce Type: new
Abstract: Self-supervised pre-training via cross-view completion learns strong features for 3D vision from co-visible regions of image pairs. However, the refere...
By Thibaut Loiseau, Guillaume Bourmaud, Vincent Lepetit
arXiv:2608.22465v1 Announce Type: new
Abstract: High-fidelity free-viewpoint video (FVV) and interactive rendering increasingly rely on explicit Gaussian representations, yet practical deployment rem...
By Xinhui Liu, Lei Liu, Zhenghao Chen, Lebin Zhou, Wei Wang, Wei Jiang
arXiv:2607. 00832v1 Announce Type: cross Abstract: A single panorama captures the full visual sphere from one camera center, yet confines users to looking around in place without enabling true scene exploration.
By Zhenjia Li, Jinrang Jia, Yifeng Shi
Free-viewpoint 3D scene media is increasingly important for immersive applications, yet practical capture often suffers from severe view sparsity and motion blur. Although neural rendering has advanced sparse-view synthesis, existing blur-aware methods typically require substantial multi-view redundancy, accurate camera poses, or costly per-scene optimization.
arXiv:2608.13147v2 Announce Type: replace
Abstract: Camera-based autonomous driving perception requires a shared representation that preserves metric 3D structure across synchronized multi-camera str...
By Longfei Xu, Xiaohui Wang, Zehao Huang, Han Li, Ya Yang, Naiyan Wang, Si Liu
BEAST3D is a self‑supervised framework that learns 3D visual representations from unlabeled, calibrated multi‑view video of animals. It uses a vision transformer to predict 3D Gaussian splats, reconstructing held‑out views via differentiable rendering while simultaneously segmenting the animal. The method works with as few as four views, produces viewpoint‑invariant features, and transfers to tasks such as novel view synthesis, multi‑view pose estimation, and neural encoding across four species.
By Yanchen Wang, Lenny Aharon, Wangshu Zhu, Kyle Daruwalla, Linghua Zhang, Jiaru Zou, Selmaan Chettih, Helen Hou, Liam Paninski, Matthew R Whiteway
The paper addresses the lack of standardized evaluation for single‑view novel view synthesis by highlighting the importance of aligning a method’s reference frame with the ground‑truth camera pose. It proposes using traditional 2D‑to‑2D and 2D‑to‑3D image matching to align 3D reconstructions and restricts evaluation to co‑visible regions where a correct ground truth exists. Experiments show that with proper alignment, 3D Gaussian‑based methods reach state‑of‑the‑art performance, and a simple baseline using a video generator and geometry estimator matches specialized novel‑view synthesis models without task‑specific training.
By Yang-Che Tseng, Erqun Dong, Jeong-gi Kwak, Gopal Sharma, Shakiba Kheradmand, Stephan Garbin, Hossam Isack, Kwang Moo Yi
TAPVid-MV is a new benchmark for tracking any point in 3D across multiple synchronized camera views. It comprises 284 sequences, 1,142 calibrated camera streams, and 109,769 point tracks, covering indoor and outdoor domains and derived from various modalities such as depth, LiDAR, SLAM, and simulation. The dataset is visually verified, and evaluation shows that current multi‑view trackers do not consistently outperform monocular trackers, highlighting geometry recovery as a key bottleneck.
By Skanda Koppula, Frano Rajic, Abdullah Faiz Ur Rahman, Yi Yang, Ignacio Rocco, Jeet Thakwani, Rishabh Kabra, Andrew Zisserman, Joao Carreira, Siyu Tang, Carl Doersch, Gabriel Brostow
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
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