Related papers: MoRe: Motion-aware Feed-forward 4D Reconstruction …
Recent advancements in sensor technology and deep learning have led to significant progress in 3D human body reconstruction. However, most existing approaches rely on data from a specific sensor, which can be unreliable due to the inherent…
Monocular SLAM has received a lot of attention due to its simple RGB inputs and the lifting of complex sensor constraints. However, existing monocular SLAM systems are designed for bounded scenes, restricting the applicability of SLAM…
We propose SLARM, a feed-forward model that unifies dynamic scene reconstruction, semantic understanding, and real-time streaming inference. SLARM captures complex, non-uniform motion through higher-order motion modeling, trained solely on…
For action recognition learning, 2D CNN-based methods are efficient but may yield redundant features due to applying the same 2D convolution kernel to each frame. Recent efforts attempt to capture motion information by establishing…
Synthesizing novel views of dynamic humans from stationary monocular cameras is a specialized but desirable setup. This is particularly attractive as it does not require static scenes, controlled environments, or specialized capture…
Multimodal Large Language Models have demonstrated remarkable capabilities in video understanding, yet face prohibitive computational costs and performance degradation from ''context rot'' due to massive visual token redundancy. Existing…
Recovering a dense 3D body mesh from monocular video remains challenging under occlusion from draping and continuously moving camera viewpoints. This configuration arises in surgical augmented reality (AR), where an anesthetized patient…
Scaling language models unlocks impressive capabilities, but the accompanying computational and memory demands make both training and deployment expensive. Existing efficiency efforts typically target either parameter sharing or adaptive…
Much progress has been made in reconstructing garments from an image or a video. However, none of existing works meet the expectations of digitizing high-quality animatable dynamic garments that can be adjusted to various unseen poses. In…
Video generation with controllable camera viewpoints is essential for applications such as interactive content creation, gaming, and simulation. Existing methods typically adapt pre-trained video models using camera poses relative to a…
Reconstructing dynamic 3D scenes from sparse multi-view videos is highly ill-posed, often leading to geometric collapse, trajectory drift, and floating artifacts. Recent attempts introduce generative priors to hallucinate missing content,…
Event cameras are bio-inspired sensors that offer several advantages, such as low latency, high-speed and high dynamic range, to tackle challenging scenarios in computer vision. This paper presents a solution to the problem of 3D…
High-quality 4D reconstruction enables photorealistic and immersive rendering of the dynamic real world. However, unlike static scenes that can be fully captured with a single camera, high-quality dynamic scenes typically require dense…
3D human motion prediction aims to generate coherent future motions from observed sequences, yet existing end-to-end regression frameworks often fail to capture complex dynamics and tend to produce temporally inconsistent or static…
We present V2M4, a novel 4D reconstruction method that directly generates a usable 4D mesh animation asset from a single monocular video. Unlike existing approaches that rely on priors from multi-view image and video generation models, our…
Feed-forward 3D reconstruction models based on Vision Transformers can directly estimate scene geometry and camera poses from a small set of input images, but scaling them to video inputs with hundreds or thousands of frames remains…
Modeling 3D articulated objects with realistic geometry, textures, and kinematics is essential for a wide range of applications. However, existing optimization-based reconstruction methods often require dense multi-view inputs and expensive…
Video restoration aims at restoring multiple high-quality frames from multiple low-quality frames. Existing video restoration methods generally fall into two extreme cases, i.e., they either restore all frames in parallel or restore the…
We present Light3R-SfM, a feed-forward, end-to-end learnable framework for efficient large-scale Structure-from-Motion (SfM) from unconstrained image collections. Unlike existing SfM solutions that rely on costly matching and global…
Reconstructing dynamic 3D scenes with photorealistic detail and strong temporal coherence remains a significant challenge. Existing Gaussian splatting approaches for dynamic scene modeling often rely on per-frame optimization, which can…