FFVO: A Feedforward Pose Decoder for Long-Horizon Visual Odometry

• URL: http://arxiv.org/abs/2609.13733v1
• Date: Sat, 12 Sep 2026 05:56:52 GMT
• Title: FFVO: A Feedforward Pose Decoder for Long-Horizon Visual Odometry
• Abstract summary: We propose Feedforward Visual Odometry (FFVO), a pose-specialized adaptation of joint reconstruction architectures for efficient and temporally stable camera-pose estimation.<n>FFVO uses (i) a compact camera-token representation for computationally efficient temporal aggregation, (ii) a hierarchical local-to-global temporal decoder, and (iii) intermediate trajectory supervision that promotes temporal stability.
• Score: 31.83986431141471
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Stable and reliable 4D spatial understanding is fundamental for autonomous driving systems. While feedforward reconstruction networks can estimate camera motion and 3D structure in one pass, pose estimation over long videos remains challenged by computational cost, long-context ambiguity, and temporal instability. To address these challenges, we propose Feedforward Visual Odometry (FFVO), a pose-specialized adaptation of joint reconstruction architectures for efficient and temporally stable camera-pose estimation. FFVO uses (i) a compact camera-token representation for computationally efficient temporal aggregation, (ii) a hierarchical local-to-global temporal decoder that mitigates geometric ambiguity by separating short-range motion aggregation from sequence-level integration, and (iii) intermediate trajectory supervision that promotes temporal stability. Extensive evaluation on the Waymo Open Dataset (WOD), KITTI, and a large-scale proprietary benchmark demonstrates that our method performs favorably against existing feedforward approaches, and greatly reduces jitter and drift. These results support FFVO as an effective feedforward camera-pose decoder in long-horizon visual odometry settings.

Related papers

• Revisiting Local Context for Long-Horizon Streaming 3D Reconstruction [10.383154504465232]
  ABot-Recon is a simple streaming model that caches KV features from only the preceding 11 frames.<n>It predicts a point map in the current camera coordinate system together with an adjacent-frame relative pose.<n>To reduce accumulated drift, a lightweight temporal refiner improves relative rotations using recent visual and motion context.
  arXiv  Detail & Related papers  (2026-08-27T15:07:38Z)
• EvTrajGS: Accurate and Efficient 3D Gaussian Splatting from Unposed Event Streams [108.45551580182384]
  EvTrajGS is an accurate and efficient 3D Gaussian Splatting framework for unposed event streams.<n>Our method enables reliable joint pose-scene optimization from coarse pose priors, eliminating the need for computationally expensive SLAM-style pipelines.
  arXiv  Detail & Related papers  (2026-08-09T09:00:30Z)
• NoDrift3R: Raymap-Guided Coupling for Drift-Robust Unposed Feed-Forward 3D Reconstruction [25.145305440192875]
  Pose-Free Feed-forward 3D Gaussian Splatting has recently emerged as a powerful paradigm for fast scene reconstruction.<n>However, its performance degrades significantly in long image sequences due to cumulative camera pose estimation drift.<n>We propose a synergistic pose-free framework that explicitly couples geometry and appearance via a Raymap-Guided Coupling Module.
  arXiv  Detail & Related papers  (2026-07-08T09:02:18Z)
• Sphere-VIO: Fast and Robust Visual-Inertial Odometry via Unified Spherical Representation for Heterogeneous Multi-Camera Systems [11.777651307702174]
  Multi-camera visual-inertial odometry (VIO) overcomes the inherent limitations of pure visual systems by expanding the field of view.<n>We present Sphere-VIO, a lightweight filter-based VIO framework with unified spherical representation for heterogeneous multi-camera systems.<n>We show that Sphere-VIO achieves superior trade-offs between accuracy, robustness, efficiency, and cross-camera generality.
  arXiv  Detail & Related papers  (2026-06-29T07:46:08Z)
• Event-based SLAM Benchmark for High-Speed Maneuvers [68.148886127117]
  Event-based cameras are bio-inspired sensors with pixels that independently and asynchronously respond to brightness changes at microsecond resolution.<n>Existing event-based approaches, although successful in mitigating motion blur caused by high-speed maneuvers, suffer from many limitations.<n>We introduce a benchmarking framework for event-based state estimation, called EvSLAM, characterized by sufficient variation in data collection platforms.
  arXiv  Detail & Related papers  (2026-04-27T04:36:41Z)
• RAFT-MSF++: Temporal Geometry-Motion Feature Fusion for Self-Supervised Monocular Scene Flow [51.43025173196566]
  Monocular scene flow estimation aims to recover dense 3D motion from image sequences.<n>We propose RAFT-MSF++, a self-supervised multi-frame framework that fuses temporal features to jointly estimate depth and scene flow.<n>Experiments show that RAFT-MSF++ achieves 24.14% SF-all on the KITTI Scene Flow benchmark, with a 30.99% improvement over the baseline and better robustness in occluded regions.
  arXiv  Detail & Related papers  (2026-04-21T11:32:49Z)
• DAGE: Dual-Stream Architecture for Efficient and Fine-Grained Geometry Estimation [72.89376712495464]
  DAGE is a dual-stream transformer that disentangles global coherence from fine detail.<n>A low-resolution stream operates on aggressively downsampled frames with alternating frame/global attention to build a view-consistent representation.<n>A high-resolution stream processes the original images per-frame to preserve sharp boundaries and small structures.<n>This design scales resolution and clip length independently, supports inputs up to 2K, and maintains practical inference cost.
  arXiv  Detail & Related papers  (2026-03-04T05:29:29Z)
• UCM: Unifying Camera Control and Memory with Time-aware Positional Encoding Warping for World Models [54.564740558030245]
  We present UCM, a novel framework that unifies long-term memory and precise camera control via a time-aware positional encoding warping mechanism.<n>We also introduce a scalable data curation strategy utilizing point-cloud-based rendering to simulate scene revisiting.
  arXiv  Detail & Related papers  (2026-02-26T12:54:46Z)
• GeoMotion: Rethinking Motion Segmentation via Latent 4D Geometry [61.24189040578178]
  We propose a fully learning-based approach that directly infers moving objects from latent feature representations via attention mechanisms.<n>Our key insight is to bypass explicit correspondence estimation and instead let the model learn to implicitly disentangle object and camera motion.<n>Our approach achieves state-of-the-art motion segmentation performance with high efficiency.
  arXiv  Detail & Related papers  (2026-02-25T11:36:33Z)
• DVLO4D: Deep Visual-Lidar Odometry with Sparse Spatial-temporal Fusion [28.146811420532455]
  We introduce DVLO4D, a novel visual-LiDAR odometry framework that leverages sparse spatial-temporal fusion to enhance accuracy and robustness.<n>Our method has high efficiency, with an inference time of 82 ms, possessing the potential for the real-time deployment.
  arXiv  Detail & Related papers  (2025-09-07T11:43:11Z)
• An End-to-End Framework for Video Multi-Person Pose Estimation [3.090225730976977]
  We propose VEPE (Video Endto-End Pose Estimation), a simple and flexible framework for end-to-end pose estimation in video.<n>We show that our approach outperforms two-stage models by 300% and by inference by 300%.
  arXiv  Detail & Related papers  (2025-09-01T03:34:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.