中文
相关论文

相关论文: RealX3D: A Physically-Degraded 3D Benchmark for Mu…

200 篇论文

The default strategy for training single-view Large Reconstruction Models (LRMs) follows the fully supervised route using large-scale datasets of synthetic 3D assets or multi-view captures. Although these resources simplify the training…

计算机视觉与模式识别 · 计算机科学 2024-06-13 Hanwen Jiang , Qixing Huang , Georgios Pavlakos

We introduce a set of image transformations that can be used as corruptions to evaluate the robustness of models as well as data augmentation mechanisms for training neural networks. The primary distinction of the proposed transformations…

计算机视觉与模式识别 · 计算机科学 2022-05-02 Oğuzhan Fatih Kar , Teresa Yeo , Andrei Atanov , Amir Zamir

Reconstructing 3D objects from a single image is an intriguing but challenging problem. One promising solution is to utilize multi-view (MV) 3D reconstruction to fuse generated MV images into consistent 3D objects. However, the generated…

计算机视觉与模式识别 · 计算机科学 2024-01-30 Yizheng Chen , Rengan Xie , Qi Ye , Sen Yang , Zixuan Xie , Tianxiao Chen , Rong Li , Yuchi Huo

The outstanding performance of Large Multimodal Models (LMMs) has made them widely applied in vision-related tasks. However, various corruptions in the real world mean that images will not be as ideal as in simulations, presenting…

计算机视觉与模式识别 · 计算机科学 2024-10-10 Chunyi Li , Jianbo Zhang , Zicheng Zhang , Haoning Wu , Yuan Tian , Wei Sun , Guo Lu , Xiaohong Liu , Xiongkuo Min , Weisi Lin , Guangtao Zhai

Multiview 3D evaluation assumes that the images being scored are observations of one static 3D scene. This assumption can fail in NVS and sparse-view reconstruction: inputs or generated outputs may contain artifacts, outlier frames,…

计算机视觉与模式识别 · 计算机科学 2026-05-19 Soumava Paul , Prakhar Kaushik , Alan Yuille

We are witnessing a proliferation of textured 3D models captured from the real world with automatic photo-reconstruction tools. Digital 3D models of this class come with a unique set of characteristics and defects -- especially concerning…

图形学 · 计算机科学 2020-12-29 Andrea Maggiordomo , Federico Ponchio , Paolo Cignoni , Marco Tarini

Dense 3D reconstruction and ego-motion estimation are key challenges in autonomous driving and robotics. Compared to the complex, multi-modal systems deployed today, multi-camera systems provide a simpler, low-cost alternative. However,…

计算机视觉与模式识别 · 计算机科学 2023-08-29 Aron Schmied , Tobias Fischer , Martin Danelljan , Marc Pollefeys , Fisher Yu

Image restoration under adverse conditions, such as underwater, haze or fog, and low-light environments, remains a highly challenging problem due to complex physical degradations and severe information loss. Existing datasets are…

计算机视觉与模式识别 · 计算机科学 2026-04-15 Deqing Yang , Yingying Liu , Qicong Wang , Zhi Zeng , Dajiang Lu , Yibin Tian

3D perception, especially point cloud classification, has achieved substantial progress. However, in real-world deployment, point cloud corruptions are inevitable due to the scene complexity, sensor inaccuracy, and processing imprecision.…

计算机视觉与模式识别 · 计算机科学 2022-06-15 Jiawei Ren , Liang Pan , Ziwei Liu

Reconstructing physically valid 3D scenes from single-view observations is a prerequisite for bridging the gap between visual perception and robotic control. However, in scenarios requiring precise contact reasoning, such as robotic…

机器人学 · 计算机科学 2026-05-19 Tianyi Xiang , Jiahang Cao , Sikai Guo , Guoyang Zhao , Andrew F. Luo , Jun Ma

Most image deblurring methods assume an over-simplistic image formation model and as a result are sensitive to more realistic image degradations. We propose a novel variational framework, that explicitly handles pixel saturation, noise,…

计算机视觉与模式识别 · 计算机科学 2018-06-05 Jérémy Anger , Mauricio Delbracio , Gabriele Facciolo

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

3D object detection is an important task in autonomous driving to perceive the surroundings. Despite the excellent performance, the existing 3D detectors lack the robustness to real-world corruptions caused by adverse weathers, sensor…

计算机视觉与模式识别 · 计算机科学 2023-03-21 Yinpeng Dong , Caixin Kang , Jinlai Zhang , Zijian Zhu , Yikai Wang , Xiao Yang , Hang Su , Xingxing Wei , Jun Zhu

We present a method for relighting 3D reconstructions of large room-scale environments. Existing solutions for 3D scene relighting often require solving under-determined or ill-conditioned inverse rendering problems, and are as such unable…

计算机视觉与模式识别 · 计算机科学 2026-01-30 Xiaoyan Xing , Philipp Henzler , Junhwa Hur , Runze Li , Jonathan T. Barron , Pratul P. Srinivasan , Dor Verbin

While Vision-Language Models (VLMs) achieve near-perfect scores on digital document benchmarks like OmniDocBench, their performance in the unpredictable physical world remains largely unknown due to the lack of controlled yet realistic…

计算机视觉与模式识别 · 计算机科学 2026-03-05 Changda Zhou , Ziyue Gao , Xueqing Wang , Tingquan Gao , Cheng Cui , Jing Tang , Yi Liu

We present SyncFix, a framework that enforces cross-view consistency during the diffusion-based refinement of reconstructed scenes. SyncFix formulates refinement as a joint latent bridge matching problem, synchronizing distorted and clean…

计算机视觉与模式识别 · 计算机科学 2026-04-16 Deming Li , Abhay Yadav , Cheng Peng , Rama Chellappa , Anand Bhattad

3D scene reconstruction from 2D images is one of the most important tasks in computer graphics. Unfortunately, existing datasets and benchmarks concentrate on idealized synthetic or meticulously captured realistic data. Such benchmarks fail…

计算机视觉与模式识别 · 计算机科学 2025-06-10 Weronika Smolak-Dyżewska , Dawid Malarz , Grzegorz Wilczyński , Rafał Tobiasz , Joanna Waczyńska , Piotr Borycki , Przemysław Spurek

Occlusions are a common occurrence in unconstrained face images. Single image 3D reconstruction from such face images often suffers from corruption due to the presence of occlusions. Furthermore, while a plurality of 3D reconstructions is…

计算机视觉与模式识别 · 计算机科学 2022-04-04 Rahul Dey , Vishnu Naresh Boddeti

Three-dimensional (3D) reconstruction from two-dimensional images is an active research field in computer vision, with applications ranging from navigation and object tracking to segmentation and three-dimensional modeling. Traditionally,…

计算机视觉与模式识别 · 计算机科学 2024-09-17 Sierra Bonilla , Chiara Di Vece , Rema Daher , Xinwei Ju , Danail Stoyanov , Francisco Vasconcelos , Sophia Bano

Restoring images affected by various types of degradation, such as noise, blur, or improper exposure, remains a significant challenge in computer vision. While recent trends favor complex monolithic all-in-one architectures, these models…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Joanna Wiekiera , Martyna Zur