Related papers: MoRe: Motion-aware Feed-forward 4D Reconstruction …

With the growing need for diverse and scalable data in indoor scene tasks, such as question answering and dense captioning, we propose 3D-MoRe, a novel paradigm designed to generate large-scale 3D-language datasets by leveraging the…

Volumetric video has emerged as a key medium for immersive telepresence and augmented/virtual reality, enabling six-degrees-of-freedom (6DoF) navigation and realistic spatial interactions. However, delivering high-quality dynamic volumetric…

Recent advances in diffusion models have improved controllable streetscape generation and supported downstream perception and planning tasks. However, challenges remain in accurately modeling driving scenes and generating long videos. To…

In cardiac CINE, motion-compensated MR reconstruction (MCMR) is an effective approach to address highly undersampled acquisitions by incorporating motion information between frames. In this work, we propose a novel perspective for…

In this work, we present a multimodal solution to the problem of 4D face reconstruction from monocular videos. 3D face reconstruction from 2D images is an under-constrained problem due to the ambiguity of depth. State-of-the-art methods try…

State-of-the-art methods can recover accurate overall 3D human body motion from in-the-wild videos. However, they often fail to capture fine-grained articulations, especially in the feet, which are critical for applications such as gait…

We propose 4DGT, a 4D Gaussian-based Transformer model for dynamic scene reconstruction, trained entirely on real-world monocular posed videos. Using 4D Gaussian as an inductive bias, 4DGT unifies static and dynamic components, enabling the…

We present STream3R, a novel approach to 3D reconstruction that reformulates pointmap prediction as a decoder-only Transformer problem. Existing state-of-the-art methods for multi-view reconstruction either depend on expensive global…

This paper tackles the challenge of robust reconstruction, i.e., the task of reconstructing a 3D scene from a set of inconsistent multi-view images. Some recent works have attempted to simultaneously remove image inconsistencies and perform…

Moving Object Detection (MOD) is a crucial task for the Autonomous Driving pipeline. MOD is usually handled via 2-stream convolutional architectures that incorporates both appearance and motion cues, without considering the inter-relations…

Human motion recovered from monocular videos often appears overly smooth or dynamically inconsistent, even when joint positions are numerically accurate. We observe that this limitation stems from the absence of reliable high-order temporal…

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 challenges: (1)…

In this paper, we propose MonoRec, a semi-supervised monocular dense reconstruction architecture that predicts depth maps from a single moving camera in dynamic environments. MonoRec is based on a multi-view stereo setting which encodes the…

Recently, Transformer-based image restoration networks have achieved promising improvements over convolutional neural networks due to parameter-independent global interactions. To lower computational cost, existing works generally limit…

A number of deep learning based algorithms have been proposed to recover high-quality videos from low-quality compressed ones. Among them, some restore the missing details of each frame via exploring the spatiotemporal information of…

We present MoE-DiffIR, an innovative universal compressed image restoration (CIR) method with task-customized diffusion priors. This intends to handle two pivotal challenges in the existing CIR methods: (i) lacking adaptability and…

In monocular videos that capture dynamic scenes, estimating the 3D geometry of video contents has been a fundamental challenge in computer vision. Specifically, the task is significantly challenged by the object motion, where existing…

We propose a learning-based method to reconstruct the local terrain for locomotion with a mobile robot traversing urban environments. Using a stream of depth measurements from the onboard cameras and the robot's trajectory, the algorithm…

3D spatial perception is fundamental to generalizable robotic manipulation, yet obtaining reliable, high-quality 3D geometry remains challenging. Depth sensors suffer from noise and material sensitivity, while existing reconstruction models…

Objects moving at high speed appear significantly blurred when captured with cameras. The blurry appearance is especially ambiguous when the object has complex shape or texture. In such cases, classical methods, or even humans, are unable…