中文
相关论文

相关论文: AMB3R: Accurate Feed-forward Metric-scale 3D Recon…

200 篇论文

Generating high-quality 3D content from text, single images, or sparse view images remains a challenging task with broad applications. Existing methods typically employ multi-view diffusion models to synthesize multi-view images, followed…

计算机视觉与模式识别 · 计算机科学 2025-06-03 Junlin Han , Jianyuan Wang , Andrea Vedaldi , Philip Torr , Filippos Kokkinos

Dense 3D reconstruction has many applications in automated driving including automated annotation validation, multimodal data augmentation, providing ground truth annotations for systems lacking LiDAR, as well as enhancing auto-labeling…

计算机视觉与模式识别 · 计算机科学 2024-02-13 Shihao Shen , Louis Kerofsky , Varun Ravi Kumar , Senthil Yogamani

Recent advancements in radiance field rendering, exemplified by Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS), have significantly progressed 3D modeling and reconstruction. The use of multiple 360-degree omnidirectional…

计算机视觉与模式识别 · 计算机科学 2025-05-27 Shintaro Ito , Natsuki Takama , Toshiki Watanabe , Koichi Ito , Hwann-Tzong Chen , Takafumi Aoki

Traditionally, creating photo-realistic 3D head avatars requires a studio-level multi-view capture setup and expensive optimization during test-time, limiting the use of digital human doubles to the VFX industry or offline renderings. To…

计算机视觉与模式识别 · 计算机科学 2025-09-16 Tobias Kirschstein , Javier Romero , Artem Sevastopolsky , Matthias Nießner , Shunsuke Saito

DUSt3R introduced a novel paradigm in geometric computer vision by proposing a model that can provide dense and unconstrained Stereo 3D Reconstruction of arbitrary image collections with no prior information about camera calibration nor…

计算机视觉与模式识别 · 计算机科学 2025-03-04 Yohann Cabon , Lucas Stoffl , Leonid Antsfeld , Gabriela Csurka , Boris Chidlovskii , Jerome Revaud , Vincent Leroy

Recent advancements in multi-view scene reconstruction have been significant, yet existing methods face limitations when processing streams of input images. These methods either rely on time-consuming offline optimization or are restricted…

计算机视觉与模式识别 · 计算机科学 2025-07-25 Zhuoguang Chen , Minghui Qin , Tianyuan Yuan , Zhe Liu , Hang Zhao

Feed-forward 3D reconstruction methods aim to predict the 3D structure of a scene directly from input images, providing a faster alternative to per-scene optimization approaches. Significant progress has been made in single-view and…

计算机视觉与模式识别 · 计算机科学 2025-06-05 Sam Bahrami , Dylan Campbell

The recent paradigm shift in 3D vision led to the rise of foundation models with remarkable capabilities in 3D perception from uncalibrated images. However, extending these models to large-scale RGB stream 3D reconstruction remains…

计算机视觉与模式识别 · 计算机科学 2026-02-05 Leonid Antsfeld , Boris Chidlovskii , Yohann Cabon , Vincent Leroy , Jerome Revaud

Current methods for dense 3D point tracking in dynamic scenes typically rely on pairwise processing, require known camera poses, or assume temporal ordering of input frames, thereby constraining their flexibility and applicability.…

计算机视觉与模式识别 · 计算机科学 2026-04-06 Vivek Alumootil , Tuan-Anh Vu

Object-centric scene understanding is a fundamental challenge in computer vision. Existing approaches often rely on multi-stage pipelines that first apply pre-trained segmentors to extract individual objects, followed by per-object 3D…

计算机视觉与模式识别 · 计算机科学 2026-05-14 Yi Du , Yang You , Xiang Wan , Leonidas Guibas

We introduce a new task, Map and Locate, which unifies the traditionally distinct objectives of open-vocabulary segmentation - detecting and segmenting object instances based on natural language queries - and 3D reconstruction, the process…

计算机视觉与模式识别 · 计算机科学 2025-06-05 Xuweiyi Chen , Tian Xia , Sihan Xu , Jianing Yang , Joyce Chai , Zezhou Cheng

Learning-based 3D object reconstruction enables single- or few-shot estimation of 3D object models. For robotics, this holds the potential to allow model-based methods to rapidly adapt to novel objects and scenes. Existing 3D reconstruction…

We present Gen3R, a method that bridges the strong priors of foundational reconstruction models and video diffusion models for scene-level 3D generation. We repurpose the VGGT reconstruction model to produce geometric latents by training an…

计算机视觉与模式识别 · 计算机科学 2026-03-24 Jiaxin Huang , Yuanbo Yang , Bangbang Yang , Lin Ma , Yuewen Ma , Yiyi Liao

Despite recent advancements in the Large Reconstruction Model (LRM) demonstrating impressive results, when extending its input from single image to multiple images, it exhibits inefficiencies, subpar geometric and texture quality, as well…

计算机视觉与模式识别 · 计算机科学 2024-12-03 Mengfei Li , Xiaoxiao Long , Yixun Liang , Weiyu Li , Yuan Liu , Peng Li , Wenhan Luo , Wenping Wang , Yike Guo

3D reconstruction of a scene from Synthetic Aperture Radar (SAR) images mainly relies on interferometric measurements, which involve strict constraints on the acquisition process. These last years, progress in deep learning has…

计算机视觉与模式识别 · 计算机科学 2025-02-18 Emile Barbier--Renard , Florence Tupin , Nicolas Trouvé , Loïc Denis

Feed-forward 3D reconstruction models such as DUSt3R, VGGT, and Depth Anything 3 (DA3) are transformer-based foundation models that infer camera geometry and dense scene structure in a single forward pass. Trained at scale in a supervised…

计算机视觉与模式识别 · 计算机科学 2026-03-18 Jelena Bratulić , Sudhanshu Mittal , Thomas Brox , Christian Rupprecht

City-scale 3D surface reconstruction from multiview images for downstream 3D simulation, poses highly challenging problems due to the scale and complexity of urban scenes. Existing city-scale 3D reconstruction methods based on NeRF,…

计算机视觉与模式识别 · 计算机科学 2026-05-29 Sayan Paul , Sourav Ghosh , Siddharth Katageri , Soumyadip Maity , Sanjana Sinha , Brojeshwar Bhowmick

Various datasets have been proposed for simultaneous localization and mapping (SLAM) and related problems. Existing datasets often include small environments, have incomplete ground truth, or lack important sensor data, such as depth and…

计算机视觉与模式识别 · 计算机科学 2023-01-04 Janne Mustaniemi , Juho Kannala , Esa Rahtu , Li Liu , Janne Heikkilä

Reconstructing surgical scenes from monocular endoscopic video is critical for advancing robotic-assisted surgery. However, the application of state-of-the-art general-purpose reconstruction models is constrained by two key challenges: the…

计算机视觉与模式识别 · 计算机科学 2026-03-10 Kaiyuan Xu , Fangzhou Hong , Daniel Elson , Baoru Huang

We present Dense-SfM, a novel Structure from Motion (SfM) framework designed for dense and accurate 3D reconstruction from multi-view images. Sparse keypoint matching, which traditional SfM methods often rely on, limits both accuracy and…

计算机视觉与模式识别 · 计算机科学 2026-01-29 JongMin Lee , Sungjoo Yoo