paper-with-me

홈 › Papers

LIST3R: Long-sequence Instance-aware 3D Reconstruction

2026-07-01 · Jing Gao, Wei Wang, Feiran Wang, Yan Yan arxiv

We present LIST3R, an instance-aware framework for long-sequence 3D reconstruction inspired by the way humans organize spatial memory around stable and recognizable objects. LIST3R organizes long-sequence reconstruction around instance anchors, using them to reconnect fragmented subsequences and consolidate local observations into a coherent global 3D scene. Given a long video, our approach partitions it into overlapping subsequences and builds a structured local instance library for each partial reconstruction, maintaining persistent trackable anchors with semantic and geometric evidence. These anchors are matched across subsequences to recover revisited regions and provide object-aware constraints for fragment alignment, producing a consistent global reconstruction. During this process, the evolving geometric evidence updates the local instance libraries and progressively organizes them into a unified global 3D instance library. Experiments on long-sequence benchmarks show that our method produces more accurate trajectories and higher-quality 3D reconstructions, highlighting the effectiveness of persistent instance anchors for organizing long-horizon 3D reconstruction. Our code is available on the project page: https://yixn965.github.io/LIST3R/.

📄 PDF Abstract BibTeX arXiv:2607.00375

Code (0)

등록된 구현이 없습니다.

Tasks

3D Reconstruction

Similar Papers 제목 키워드 기반

Uni-3D: A Universal Model for Panoptic 3D Scene Reconstruction

2023-01-01 · ICCV 2023 1 · Xiang Zhang, Zeyuan Chen, Fangyin Wei, Zhuowen Tu

Performing holistic 3D scene understanding from a single-view observation, involving generating instance shapes and 3D scene segmentation, is a long-standing challenge. Prevailing works either focus only on geometry …

3D Scene ReconstructionImage SegmentationPanoptic SegmentationScene Parsing+4

Panoptic 3D Scene Reconstruction From a Single RGB Image

2021-11-03 · NeurIPS 2021 12 · Manuel Dahnert, Ji Hou, Matthias Nießner, Angela Dai

Understanding 3D scenes from a single image is fundamental to a wide variety of tasks, such as for robotics, motion planning, or augmented reality. Existing works in 3D perception from a single RGB image tend to focus on…

2D Panoptic Segmentation3D Instance Segmentation3D Scene Reconstruction3D Semantic Segmentation+6

OcclusionFusion: Occlusion-aware Motion Estimation for Real-time Dynamic 3D Reconstruction

2022-03-15 · CVPR 2022 1 · Wenbin Lin, Chengwei Zheng, Jun-Hai Yong, Feng Xu

RGBD-based real-time dynamic 3D reconstruction suffers from inaccurate inter-frame motion estimation as errors may accumulate with online tracking. This problem is even more severe for single-view-based systems due to st…

3D ReconstructionGraph Neural NetworkMotion Estimation

LongDPM: Overlap-Aware 4D Reconstruction from Long Monocular Videos

2026-05-17 · Chenyi Xu, Yihao Wu, Liqi Yan, Chao Yang 외 arxiv

Recovering a dynamic 3D scene from a long monocular video is crucial for dense geometry, camera motion, and temporal correspondence to remain consistent in a shared coordinate system. Existing methods face two key challe…

Dynamic ReconstructionCamera Pose Estimation

Instance-aware Contrastive Learning for Occluded Human Mesh Reconstruction

2024-01-01 · Conference on Computer Vision and Pattern Recognition (CVPR) 2024 6 · Mi-Gyeong Gwon, Gi-Mun Um, Won-Sik Cheong, Wonjun Kim

A simple yet effective method for occlusion-robust 3D human mesh reconstruction from a single image is presented in this paper. Although many recent studies have shown the remarkable improvement in human mesh reconst…

3D Human Pose Estimation3D Multi-Person Mesh Recovery3D Multi-Person Pose EstimationContrastive Learning+1