CrossFit-GS is a new framework for pose-free 3D Gaussian Splatting that avoids the need for Structure-from-Motion by directly reconstructing scenes from unposed image sequences. The method partitions the input into interleaved subsets, maintaining two complementary submaps and cross-refining candidate poses against a frozen opposite submap to provide an independent geometric reference. Additional checkerboard validation and spatial coverage safeguards reject unreliable updates, and only verified poses are committed; after refinement, the final global representation is trained from scratch using the fixed refined poses, leading to reduced trajectory drift and improved camera pose estimation and novel-view synthesis across multiple benchmarks.
By Zijian Wu, Jinliang Wang, Mingfeng Jiang, Zidian Lin, Ying Song, Ziqian Lu
Pose-free 3D Gaussian Splatting (3DGS) aims to bypass cumbersome Structure-from-Motion (SfM) by directly reconstructing scenes from unposed image sequences. In this work, we present CrossFit-GS, a def...
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
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:2606. 29237v1 Announce Type: cross Abstract: Robust robot autonomy depends on scene representations that remain stable enough to support localization, navigation, and downstream decision making in dynamic environments.
By Qixin Xiao
arXiv:2504.15776v2 Announce Type: replace
Abstract: Public autonomous driving datasets underpin the training and benchmarking of perception, mapping, and localization algorithms, yet residual inaccur...
By Quentin Herau, Nathan Piasco, Moussab Bennehar, Luis Rold\~ao, Dzmitry Tsishkou, Bingbing Liu, Cyrille Migniot, Pascal Vasseur, C\'edric Demonceaux
arXiv:2609.13733v1 Announce Type: new
Abstract: Stable and reliable 4D spatial understanding is fundamental for autonomous driving systems. While feedforward reconstruction networks can estimate came...
By Meng-Li Shih, Shih-Yang Su, Yuliang Zou, Hao Xiang, Haidong Zhu, Vincent Casser, Brian Curless, Dmitry Kalenichenko, Mingxing Tan, Dragomir Anguelov
arXiv:2609.21347v1 Announce Type: new
Abstract: Recent progress in 3D Gaussian Splatting (3DGS) has enabled dense visual SLAM with pinhole cameras, yet most pipelines are not designed for panoramic i...
By Xiangfei Guo, Hao Shi, Yufan Zhang, Zhonghua Yi, Yongqi Mao, Xiaoting Yin, Kaiwei Wang
The paper introduces EgoGenEval, a benchmark that assesses visual generators’ physical consistency during ego‑motion by measuring Camera Motion Grounding and Scene State Preservation across 1,400 cases and 2,360 target views. It shows that current pose‑free models struggle to maintain both camera motion and scene state, and that pairwise supervision in training does not simultaneously improve these aspects. The authors suggest a trajectory‑centric approach that couples self‑conditioned rollouts with explicit pose and visibility supervision to address these limitations.
Track-Free Dense Structure from Motion (TFD‑SfM) is a new approach that jointly optimizes camera extrinsics, focal lengths, and dense 3D geometry from a strict cold start, without relying on precise metric initialization or known intrinsics. It replaces rigid track-building with soft, probabilistic decisions by modeling each pixel match as a 3D Gaussian whose variance is learned, allowing unreliable matches to contribute minimally and smoothing the optimization landscape. Using a kinematic relative‑pose parameterization and a dual‑hypothesis mechanism, TFD‑SfM achieves competitive or superior results on datasets such as DTU, Mip‑NeRF 360, ETH3D, and IMC2021, recovering accurate camera poses, intrinsics, and dense geometry from unordered, uncalibrated image collections.
By Pak Hong Chui, Hector Andrade-Loarca, Daniel Cremers
arXiv:2608.22039v1 Announce Type: new
Abstract: Structure-from-Motion (SfM) is a cornerstone of 3D perception, yet current methods often fail when applied to complex videos involving challenging came...
By Sara Sabour, Linyi Jin, Richard Tucker, Amir Hertz, Marcus Brubaker, Saurabh Saxena, Junhwa Hur, Andrea Tagliasacchi, Deqing Sun, David J. Fleet, Richard Szeliski, Noah Snavely
arXiv:2610.23039v1 Announce Type: new
Abstract: Feed-forward Gaussian models have made novel view synthesis almost instantaneous. Feed-forward methods predict Gaussians directly, either in two stages...
By Viruthshaan Vinasirajan, Ranga Rodrigo