English
Related papers

Related papers: Lumos3D: A Single-Forward Framework for Low-Light …

200 papers

We analyze multi-bounce propagation of light in an unknown hidden volume and demonstrate that the reflected light contains sufficient information to recover the 3D structure of the hidden scene. We formulate the forward and inverse theory…

Reconstructing 3D scenes from a single image is a fundamentally ill-posed task due to the severely under-constrained nature of the problem. Consequently, when the scene is rendered from novel camera views, existing single image to 3D…

Computer Vision and Pattern Recognition · Computer Science 2025-10-10 Sarosij Bose , Arindam Dutta , Sayak Nag , Junge Zhang , Jiachen Li , Konstantinos Karydis , Amit K. Roy Chowdhury

In this work, we introduce Prometheus, a 3D-aware latent diffusion model for text-to-3D generation at both object and scene levels in seconds. We formulate 3D scene generation as multi-view, feed-forward, pixel-aligned 3D Gaussian…

Computer Vision and Pattern Recognition · Computer Science 2025-01-03 Yuanbo Yang , Jiahao Shao , Xinyang Li , Yujun Shen , Andreas Geiger , Yiyi Liao

Despite significant progress in monocular depth estimation in the wild, recent state-of-the-art methods cannot be used to recover accurate 3D scene shape due to an unknown depth shift induced by shift-invariant reconstruction losses used in…

Computer Vision and Pattern Recognition · Computer Science 2020-12-18 Wei Yin , Jianming Zhang , Oliver Wang , Simon Niklaus , Long Mai , Simon Chen , Chunhua Shen

This paper presents our approach to the NTIRE 2026 3D Restoration and Reconstruction Challenge (Track 1), which focuses on reconstructing high-quality 3D representations from degraded multi-view inputs. The challenge involves recovering…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Yuhao Liu , Dingju Wang , Ziyang Zheng

In nighttime circumstances, it is challenging for individuals and machines to perceive their surroundings. While prevailing image restoration methods adeptly handle singular forms of degradation, they falter when confronted with intricate…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Yifan Chen , Fei Yin , Chunle Guo , Chongyi Li , Yujiu Yang

We introduce NoPoSplat, a feed-forward model capable of reconstructing 3D scenes parameterized by 3D Gaussians from \textit{unposed} sparse multi-view images. Our model, trained exclusively with photometric loss, achieves real-time 3D…

Computer Vision and Pattern Recognition · Computer Science 2024-11-01 Botao Ye , Sifei Liu , Haofei Xu , Xueting Li , Marc Pollefeys , Ming-Hsuan Yang , Songyou Peng

3D Gaussian Splatting (3DGS) has established itself as a leading technique for 3D reconstruction and novel view synthesis of static scenes, achieving outstanding rendering quality and fast training. However, the method does not explicitly…

Computer Vision and Pattern Recognition · Computer Science 2026-03-04 Margherita Lea Corona , Wieland Morgenstern , Peter Eisert , Anna Hilsmann

2D Gaussian Splatting (2DGS) is an emerging explicit scene representation method with significant potential for image compression due to high fidelity and high compression ratios. However, existing low-light enhancement algorithms operate…

Computer Vision and Pattern Recognition · Computer Science 2026-01-23 Yuhan Chen , Wenxuan Yu , Guofa Li , Yijun Xu , Ying Fang , Yicui Shi , Long Cao , Wenbo Chu , Keqiang Li

In real-world scenarios, image impairments often manifest as composite degradations, presenting a complex interplay of elements such as low light, haze, rain, and snow. Despite this reality, existing restoration methods typically target…

Computer Vision and Pattern Recognition · Computer Science 2024-07-11 Yu Guo , Yuan Gao , Yuxu Lu , Huilin Zhu , Ryan Wen Liu , Shengfeng He

In 3D reconstruction, the problem of inverse rendering, namely recovering the illumination of the scene and the material properties, is fundamental. Existing Gaussian Splatting-based methods primarily target static scenes and often assume…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Joanna Kaleta , Piotr Wójcik , Kacper Marzol , Tomasz Trzciński , Kacper Kania , Marek Kowalski

We present a novel diffusion-based approach for coherent 3D scene reconstruction from a single RGB image. Our method utilizes an image-conditioned 3D scene diffusion model to simultaneously denoise the 3D poses and geometries of all objects…

Computer Vision and Pattern Recognition · Computer Science 2024-12-16 Manuel Dahnert , Angela Dai , Norman Müller , Matthias Nießner

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,…

Computer Vision and Pattern Recognition · Computer Science 2023-08-29 Aron Schmied , Tobias Fischer , Martin Danelljan , Marc Pollefeys , Fisher Yu

Reconstructing dynamic 3D scenes from monocular video has broad applications in AR/VR, robotics, and autonomous navigation, but often fails due to severe motion blur caused by camera and object motion. Existing methods commonly follow a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Zhijing Wu , Longguang Wang

3D Gaussian Splatting (3DGS) is a powerful reconstruction technique, but it needs to be initialized from accurate camera poses and high-fidelity point clouds. Typically, the initialization is taken from Structure-from-Motion (SfM)…

Computer Vision and Pattern Recognition · Computer Science 2025-04-15 Jizong Peng , Tze Ho Elden Tse , Kai Xu , Wenchao Gao , Angela Yao

Recovering high-quality 3D human motion in complex scenes from monocular videos is important for many applications, ranging from AR/VR to robotics. However, capturing realistic human-scene interactions, while dealing with occlusions and…

Computer Vision and Pattern Recognition · Computer Science 2021-08-25 Siwei Zhang , Yan Zhang , Federica Bogo , Marc Pollefeys , Siyu Tang

Light field imaging is a rich way of representing the 3D world around us. However, due to limited sensor resolution capturing light field data inherently poses spatio-angular resolution trade-off. In this paper, we propose a deep learning…

Computer Vision and Pattern Recognition · Computer Science 2018-04-30 Anil Kumar Vadathya , Saikiran Cholleti , Gautham Ramajayam , Vijayalakshmi Kanchana , Kaushik Mitra

In low-light environments, conventional cameras often struggle to capture clear multi-view images of objects due to dynamic range limitations and motion blur caused by long exposure. Event cameras, with their high-dynamic range and…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Jingqian Wu , Peiqi Duan , Zongqiang Wang , Changwei Wang , Boxin Shi , Edmund Y. Lam

Imaging in low light is difficult because the number of photons arriving at the sensor is low. Imaging dynamic scenes in low-light environments is even more difficult because as the scene moves, pixels in adjacent frames need to be aligned…

Image and Video Processing · Electrical Eng. & Systems 2020-07-20 Yiheng Chi , Abhiram Gnanasambandam , Vladlen Koltun , Stanley H. Chan

3D scene reconstruction is essential for applications in virtual reality, robotics, and autonomous driving, enabling machines to understand and interact with complex environments. Traditional 3D Gaussian Splatting techniques rely on images…

Graphics · Computer Science 2025-03-04 Changlin Song , Jiaqi Wang , Liyun Zhu , He Weng